Intelligent Human Systems Integration (IHSI 2026): Disruptive and Innovative Technologies

AHFE International

Accelerating Open Access Science in Human Factors Engineering and Human-Centered Computing

Intelligent Human Systems Integration (IHSI 2026): Disruptive and Innovative Technologies

book-cover

Editors: Tareq Ahram, Waldemar Karwowski, Laura Giraldi, Elisabetta Benelli

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2026

ISBN: 978-1-964867-76-2

DOI: 10.54941/ahfe1007058

Articles

Artificial Intelligence Maturity Model (AIMM)

Maturity models have long served as effective frameworks for guiding organizations toward progressively advanced practices, offering structured pathways for capability development and benchmarking. Models such as the Capability Maturity Model Integration (CMMI), Organizational Project Management Maturity Model (OPM3), Portfolio, Program and Project Management Maturity Model (P2CMM), and the Data Management Maturity Model (DMM) have each demonstrated the value of systematic assessment in driving adoption, standardization, and continuous improvement across diverse fields. Despite the rapid rise of artificial intelligence (AI) adoption, no broadly accepted maturity model exists to help organizations evaluate and advance their AI capabilities. This paper introduces the Artificial Intelligence Maturity Model (AIMM), a structured framework designed to assess individual and organizational sophistication in AI agent utilization. The proposed model defines distinct maturity levels, enabling organizations to identify their current state, benchmark progress, and establish a roadmap for advancement. By providing a standardized approach to AI capability assessment, AIMM can accelerate more effective use of AI technologies across industries.

James Helfrich, Chris Mijangos Xicara

Conference Proceedings

An Experimental Study on Consensus Building with an AI Chatbot Across Two Topics

Consensus building is the process by which multiple people, through dialogue or negotiation, arrive at a single conclusion that all parties can accept. This study aims to experimentally examine how dialogue with an AI chat (chatbot) influences changes in human opinions. In this study, we prepare an AI that exhibits logical behavior and investigate the role it plays in consensus building with humans across two topics. Building on the further development of this line of research and its findings, we expect to derive design guidelines for AI-assisted consensus-building systems and to consider measures addressing the risk of AI inappropriately manipulating human opinions, thereby contributing to the creation of safe and trustworthy communication environments.2. MethodsThe AI chat used in the consensus-building experiment was configured as follows:•Exchange opinions with the goal of reaching a single conclusion.•Conduct the discussion for approximately 10 minutes.In addition, at the outset the AI chat indicates:•That the interaction is with an AI chat.•That the AI chat initially holds the opposite opinion to the participant’s.The dialogue topics with the AI chat comprised one familiar everyday choice and one societal issue:•Lunch: Whether to go to “Hama Sushi” (a conveyor-belt sushi restaurant) or “MOS Burger” (a burger shop).•Genome-edited crops: Whether to support or oppose their introduction into society.3. ExperimentWe conducted an experiment using the AI chat configured above. To determine whether people change their opinions after a brief exchange with the AI chat, participants engaged in consensus building with the AI chat for roughly 10 minutes. Each participant discussed one of the two topics— “Lunch” or “Genome”—with the AI chat.This experiment was approved by the Kyoto Tachibana University Research Ethics Committee. The generative AI engine used was GPT 4o.Participants were 200 men and women aged 20–69, recruited via a research firm. 4. ResultsThe experiment was conducted in February 2025, and data were obtained from all 200 participants. Among those discussing “lunch,” 29 out of 100 participants changed their opinion before and after the dialogue with the AI chat (29%). For the topic “genome-edited crops,” 27 out of 100 participants changed their support/oppose stance (27%).5. ConclusionTo examine the impact of AI chat on changes in human opinions, we conducted 10-minute dialogue experiments using an AI chat. The results showed that, after a short dialogue with AI, 29% of participants changed their view on the lunch choice (Hama Sushi vs. MOS Burger), and 27% changed their stance on the societal introduction of genome-edited crops. These findings suggest that even brief communication with AI may exert a measurable influence on human opinions.Future work includes analyses that incorporate participants’ prior awareness and level of interest in the topic, in order to further elucidate how AI affects human opinion-formation processes.

Kyoko Ito, Kiyokazu Ujiie

Conference Proceedings

An Agent-Based Simulation Framework for ADHD: Modeling Attention Regulation and Adaptive Therapeutic Interventions

ADHD involves fluctuating attention, impulsivity, and reward sensitivity, varying across individuals and contexts. Current interventions are often generic, overlooking this heterogeneity. This paper introduces a simulation-based framework for modeling attentional regulation and evaluating interventions with Adaptive Therapeutic Interfaces (ATIs), which personalize support based on cognitive dynamics. The framework uses empirically grounded parameters for attention, inhibition, reward sensitivity, and temporal discounting across ADHD subtypes. Agent-based simulations model attentional fluctuations, hyperfocus, and responses to Just-in-Time Adaptive Interventions (JITAIs). Validation against meta-analytic benchmarks achieved an 87.5% pass rate, replicating realistic error patterns. Three experiments (N=50 per condition) showed state-responsive strategies outperformed fixed-timing ones by 9.9-14.1% versus 2.0-3.0% (p < .001). State-responsive interventions demonstrated superior scalability, with 86.5% universality versus 69.5% and broader coverage. Personalized intensity provided additional benefits for profiles with lower baseline capacity (+5.7%). The findings highlight that adaptive timing outperforms fixed schedules by 4-5×, that intensity should inversely relate to baseline capacity, and that state-responsive approaches cover more of the population. By modeling ADHD as a dynamic regulation system rather than a static deficit, this framework enables rapid, interpretable testing of personalized strategies without costly pilot studies, guiding the development of human-centred, neurodiversity-affirming ATIs that enhance engagement, safety, and learning, advancing evidence-based mental health applications.

Valentina Ezcurra, Ancuta Margondai, Cindy Von Ahlefeldt, Anamaria Acevedo Diaz, Soraya Hani, Julie Rader, Nikita Islam, Sara Willox, Mustapha Mouloua

Conference Proceedings

CRMSON: Co-Designing Adaptive and Ethical AI Systems to Address Mental Health Barriers in Aviation

In aviation, the ability to maintain an aeromedical certificate is essential for employment, yet the very system designed to ensure safety often discourages mental health disclosure. Drawing on novel survey data (n = 1,577), this study reveals a striking paradox: while 98% of pilots and air traffic controllers identify mental health as a major industry concern, only 12% report accessing available support services. Barriers are primarily psychological—rooted in stigma, mistrust, and fear of career repercussions—rather than structural. In the United States, mandatory disclosure requirements on aeromedical forms exacerbate this culture of silence, compelling many to conceal symptoms or avoid care altogether.In response, this paper introduces CRMSON, the first AI-powered resilience platform co-designed by pilots, for pilots. Grounded in human-centered design and ethical AI principles, CRMSON delivers discreet, evidence-based microinterventions that cultivate emotional intelligence—a proven predictor of psychological resilience. Through qualitative research, participatory design workshops, and model validation across industry experts, CRMSON integrates affective science with operational realism to provide stigma-free, context-aware support.Rather than replacing professional care, CRMSON functions as scaffolding within constrained systems—reinforcing emotional regulation, self-awareness, and adaptive coping. This work reframes AI not as surveillance or automation but as an ethical architecture of care, restoring agency to aviation professionals navigating the tension between safety and psychological well-being.

Kimberly Perkins, Fabio Mattioli

Conference Proceedings

Usability Evaluation of FAIR Data Planning in the Data Stewardship Wizard

This study employs a Cognitive Walkthrough–oriented usability evaluation to examine how the Data Stewardship Wizard (DSW) supports the creation of FAIR-compliant data management plans. Although the FAIR principles (Findable, Accessible, Interoperable, Reusable) provide a widely accepted foundation for responsible data handling, their practical adoption often reveals cognitive and interaction-related challenges for users. Through a qualitative assessment, paired participants performed representative DSW tasks—project creation, questionnaire completion, model migration, and output generation. The walkthrough analysis highlighted several usability obstacles, including unclear navigation cues, limited progress feedback, and ambiguous system responses, all of which affected users’ orientation and comprehension of the tool’s structure.Insights from the evaluation informed targeted interface adjustments that improved clarity, workflow predictability, and collaboration transparency. These refinements reduced cognitive load and enhanced the overall intuitiveness of the system, contributing to broader acceptance among the DSW user community. The study underscores that usability evaluation is integral to the effective implementation of FAIR principles. By integrating cognitive analysis with data stewardship workflows, the work demonstrates how user-centred design can strengthen the practical application of FAIR guidelines and support more efficient and consistent data management planning.

Josef Pavlicek, Petra Pavlickova

Conference Proceedings

Seeing the Invisible Load: XR + Multimodal Sensing for Cognitive Ergonomics in Industrial Training

Extended reality (XR) technologies are increasingly positioned as disruptive Industry 5.0 tools for human-centric industrial training and intelligent human–system integration. Coupled with multimodal sensing (eye tracking, EEG, HRV, GSR, and other physiological signals), XR environments promise to make otherwise invisible cognitive demands observable, especially for novice trainees entering complex industrial settings. Yet the evidence base is fragmented: (1) there is no quantitative synthesis of the cognitive ergonomics benefits of XR plus sensing; (2) little is known about which XR–sensor configurations yield the strongest effects; (3) prior reviews rarely focus on industrial and manufacturing tasks; (4) multimodal signals are used predominantly for post-hoc diagnosis rather than real-time adaptation; and (5) trade-offs between egocentric, in-situ capture and controlled laboratory configurations are poorly characterized. This paper presents a meta-analysis of empirical studies that (a) used XR for training or performance support, (b) integrated at least one multimodal sensing channel, and (c) reported training- or work-relevant outcomes such as workload, situation awareness, task performance, or transfer. For this paper, we focused on manufacturing and industrial tasks (e.g., assembly, inspection, maintenance) and on novice or early-career operators. The synthesis yields evidence indicating where XR plus multimodal sensing robustly improves cognitive ergonomics for industrial novices, where effects are weak or inconsistent, and which broad modality–sensor pairings are most often associated with reduced workload, enhanced situation awareness, and lower error rates. Results indicated that egocentric, in-situ capture increases ecological validity without systematically degrading training and performance benefits but also reveal a major gap: most systems treat multimodal data as diagnostic rather than as inputs to intelligent, closed-loop adaptation. Building upon these findings, we design guidance for intelligent interfaces and human-machine teaming in industrial systems emphasizing XR modalities and adaptive policies for future cognitive ergonomics-Industry 5.0 embedded systems.

Jessica Johnson, Andwele Grant

Conference Proceedings

Conceptual Framework for Designing Domain-Specific LLM-Based Information Systems

Retrieval-augmented generation (RAG) based on large language models (LLMs) has established itself as a key technology for combining domain-specific information with generative language skills, thereby providing transparent, up-to-date information. Many firms are already piloting such LLM-based information systems, but report a high degree of complexity in planning and implementation. A generally accepted regulatory framework that consistently maps key decisions is not yet available to companies. This article therefore presents a multi-level system that organizes design decisions throughout the configuration process. This framework is intended to support users in the planning, realizing, evaluation, and further development of an LLM-based information system. To achieve this goal, a qualitative-empirical research design was chosen. First, publications from the period 2022 to 2025 were identified and selected using a systematic literature search in accordance with the PRISMA guideline. The selected publications were then evaluated using a qualitative content analysis. The result is a system that was reviewed, revised and finalized at an expert workshop.

Dominik Ullrich, Jens Wallys, Sven Hinrichsen

Conference Proceedings

Shaping Conversations: Custom GPTs to Spark Reflection in Design

This paper documents the development and evaluation of a customized GPT designed to facilitate metacognitive reflection on cognitive biases in design decision-making. Leveraging the OpenAI GPTs platform, a specialized conversational agent was created by integrating a structured knowledge base of twelve categories of cognitive biases with prompt engineering strategies oriented toward progressive disclosure. The system aimed to stimulate reflective thinking in design students by gradually surfacing relevant biases through contextual interactions rather than through systematic enumeration.The paper details the construction of the chatbot, including the design of system instructions, the organization of the knowledge base, and the definition of conversation starters used to initiate dialogues. Particular emphasis was placed on turn-taking management and the principle of one-question-per-turn, in line with established theories of cognitive load management. Despite these design directives, the analysis of conversations conducted with a sample of design students revealed significant limitations in the effective implementation of conversational principles. In seven out of ten interactions, the system presented full lists of biases in sequence, contradicting the intended principle of progressive disclosure and generating cognitive overload.Empirical analysis highlights three main issues: structural rigidity, with responses derived from repetitive templates and limited adaptability to specific project contexts; information dumping, characterized by lengthy outputs and simultaneous multiple questions; and restricted personalization, reduced to superficial lexical substitutions without meaningful contextual selection of relevant biases. These shortcomings reflect the architectural constraints of the platform at the time of the study (early 2024), when persistent memory and advanced retrieval mechanisms for dynamic context management were not yet available.Although the outcomes diverged from the original objectives, the work offers valuable contributions. First, it provides a systematic documentation of the iterative development process of a customized GPT for design reflection, emphasizing the need to balance prescriptive directives with conversational flexibility in prompt engineering. Second, it identifies practical considerations for the design of educational chatbots: the necessity of more sophisticated architectural controls to prevent enumeration, the importance of conversational management policies (anti-repetition, recap, one lever per turn), and the role of knowledge bases in contextual adaptation. Finally, the paper discusses how technological advances introduced in late 2024, such as persistent memory in GPT models and the integration of retrieval-augmented generation (RAG), may mitigate some of the observed failure modes, opening pathways for more effective implementations in the future.In conclusion, this study contributes to the understanding of how conversational AI platforms can be tailored to support reflective processes in educational and design contexts. While the experiment revealed the limitations of prompt-engineering-based solutions, the findings underscore the potential of specialized GPTs as metacognitive support tools and as catalysts for embedding reflective practices in design education.

Elena Cavallin, Simone Spagnol

Conference Proceedings

Privacy at the Core: Toward Automated Detection of Privacy-Sensitive Content in an LLM-Based Care Documentation Support System

Large language models (LLMs) introduce new opportunities in residential care, including the potential to assist with care documentation. However, if introduced unreflected, such technologies present challenges and potential harms to privacy and personal integrity. In this paper, we present a framework for automated filtering of privacy-sensitive content from LLM-supported care documentation. Our framework is based on Nissenbaum's theory of privacy as contextual integrity. As an initial step, we present the generation of a synthetic dataset derived from privacy-sensitive interactions between care workers and care recipients in the real world. We analyze the conversations by privacy categories and show that both care recipients and care workers are affected. Our contributions include a methodology for generating privacy-preserving synthetic datasets and insights into the content requirements of a dataset for fine-tuning an LLM to detect privacy-sensitive segments. In addition, we show that value-sensitive design can result in innovative approaches to creating technology that is safe, meaningful, and protective of important human values.

Reinhard Kletter, Sabine Theresia Koeszegi

Conference Proceedings

Dynamic Difficulty Adjustment via Dynamic Scripting: An Empirical Study of Player Flow in a Brawler Game

Getting the level of challenge right in action games has always been difficult, especially in fast-moving titles where player skill can vary sharply from one person to the next. Fixed difficulty options rarely adjust well to how someone is actually performing in the moment. To explore a more responsive solution, we created a side-scrolling brawler in Unity with two different enemy control setups: one powered by real-time adaptive scripting and another built around a standard, non-adaptive AI. In the adaptive version, enemy actions shifted in priority based on the outcome of earlier encounters, while the underlying finite state machine remained unchanged so that behavior changes felt consistent rather than erratic. The study used a quasi-experimental setup with 42 participants recruited online. Each person filled out a short survey before playing, completed one version of the game, and then responded to a follow-up questionnaire focused on attention, perceived difficulty, and immersion. This approach made it possible to see how players responded as enemy behavior gradually changed during a single play session. The results show how dynamic scripting behaves in a fast-paced game with constant enemy encounters and how players respond when the difficulty shifts during play. For game designers, the patterns in the data argue for testing longer play sessions and not relying on just one way of adjusting difficulty.

Justin Gold, Khaldoon Dhou

Conference Proceedings

Sinusoidal time-based features and human error metrics: Advancing software defect prediction in safety-critical systems

Defect detection in safety-critical software remains difficult despite advanced tools and mature quality assurance, largely due to the human origins of many errors. Building on prior work introducing human error–driven metrics that outperform traditional code measures, this study enhances predictive accuracy by prioritizing higher recall to strengthen defect triage in environments where missing defects carries severe risk and moderate false positives are acceptable. We integrate temporal cyclicality into defect prediction by transforming code commit timestamps into sine features via a parameterized sinusoidal model, optimized with a genetic algorithm to capture daily and periodic developer activity patterns. These features preserve non-linear, cyclical relationships linked to defect introduction, allowing machine learning models to exploit latent human-behavioural signals. Evaluation across three open-source safety-critical systems shows average recall gains of 48.68% over code metrics baselines and 9.27% over previously defined human error metrics. Embedding periodic human activity patterns alongside human-error features significantly improves defect prediction. The approach is interpretable, and generalizable, offering a pathway for broader application and future integration with adaptive, human-centric software quality models.

Carlos Andres Ramirez Catano, Makoto Itoh

Conference Proceedings

Designing an Experimental Method for Evaluating Divergent Thinking with a Color Queue under Time Constraints

The Alternative Uses Test (AUT) is a common method for evaluating divergent thinking. In the AUT, users are asked to generate as many alternative uses as possible for a given object. Divergent thinking is then assessed based on the quantity and quality of these responses. However, the AUT has its drawbacks: the difficulty of the task can vary depending on the object presented, and differences in native language can also affect the difficulty level. To address these issues, we developed a Color Queue Creation Task (CQCT) where users create a queue of colors, and their divergent thinking is evaluated based on the pattern of this color queue. In this study, we conducted a preliminary experiment to verify that the task and evaluation index of the CQCT are effective for assessing divergent thinking.This task requires users to generate a one-dimensional color queue consisting of 100 elements. It is supposed that the higher the randomness and lack of regularity in the generated color queue, the higher the score for divergent thinking. We hypothesize that individuals with high flexibility—a key aspect of divergent thinking—can recall ideas randomly from a given set of options, leading to less biased thinking. Therefore, they should be able to generate a more random and less structured color sequence.Our evaluation metric for flexibility is based on the idea that even when consciously trying to make random choices, individuals with low flexibility tend to repeatedly select the same options due to inherent cognitive biases or personal preferences. The index assesses the regularity of the color sequence by focusing on the combinations of adjacent colors. A greater bias in these combinations indicates a more regular, and thus less flexible, sequence.We conducted a preliminary experiment in which participants performed the CQCT under two conditions: with and without a time constraint, in addition to completing the traditional AUT. The two primary goals were to verify that the CQCT's flexibility score is affected by the presence of a time constraint and to examine the relationship between the flexibility scores of our new task and the traditional AUT. We hypothesized that adding a time constraint would limit a person's ability to make random choices, thereby revealing their underlying cognitive biases and lowering their flexibility scores. Eight participants with no color vision deficiency joined the experiment and conducted the CQCT under the conditions both with and without a time constraint.The results showed that six out of the eight participants demonstrated higher flexibility scores on the CQCT without a time constraint compared to the condition with a time constraint. This finding suggests that our CQCT has the potential to be a valid tool for measuring the effects of environmental or conditional changes on cognitive flexibility. A significant relationship with the AUT could not be confirmed because of the limited sample size. Future work will involve a larger sample size to further validate these findings and the use of post-task surveys to better understand the participants' thought processes during the task.

Taiki Matsunaga, Ryunosuke Fukada, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda

Conference Proceedings

Designing Experiments to Explore Optimal Timing for Refreshing Breaks During Cognitive Tasks Using Time-Series Changes

In recent years, with the advancement of the information society, intellectual work has become increasingly prevalent, heightening the need for strategies to enhance its performance. To prevent a decline in intellectual work performance among office workers, taking short, proactive breaks such as around 20 seconds can be an effective strategy [1]. However, workers tend to avoid taking breaks voluntarily [2]. Thus, this study proposes a new concept of a refreshing break that uses airflow stimuli to notify break time without discomfort and to regain their focus on subsequent tasks through the refreshing effects of airflow stimuli. As the optimal timing for the refreshing break could vary between individuals, the first step of this study was to identify the timing at which individuals desire a refreshing break through a laboratory experiment.In this preliminary experiment, 8 university students participated, and each performed the 2 sessions of the 45-minute comparison task [3]. In the first session, airflow stimuli were automatically exposed at the timings of 5, 35, and 40 minutes to experience the efficacy of a refreshing break. At each timing, the airflow stimuli were exposed for 30 seconds to each participant’s hands. In the second session, participants pressed a button to request airflow whenever they felt the need to take a break with refreshing airflow stimuli, and the 30-second airflow stimuli were applied at those timings. The purpose of this session was to explore the optimal timing for each participant to take a refreshing break that would allow them to maintain concentration.Time-series analysis of concentration levels [4], based on response time data, was conducted to see the relationship between the shift in concentration and break timing. The results suggested that breaks taken at timings when concentration started to decline help restore concentration to higher levels and suppress further decline, whereas breaks taken based solely on subjective judgment were not always well timed. Subjective questionnaires indicated that none of the participants reported discomfort with the airflow stimuli, and thus, there is the possibility that airflow stimuli could serve as a comfortable cue to indicate break timing. Based on these findings, future research should aim to identify individual patterns of concentration decline by increasing the number of experimental sessions, as well as compare adaptive break-timing methods with regular periodic airflow stimulation. This comparison may help determine optimal break timing independent of self-judgment.[1] Dianita, O., et al. (2024) Systematic micro-breaks affect concentration during cognitive comparison tasks: quantitative and qualitative measurements. Advances in Computational Intelligence, 4(7).[2] Finstad, K., et al. (2006) Breaks and task switches in prospective memory. Applied Cognitive Psychology, 20(5), pp. 705-712.[3] Ueda, K., et al. (2016). Development of "Comparison Task" to measure intellectual concentration affected by room environment. Proceedings of the 2016 International Conference on Communication and Information Systems, pp. 58-64.[4] Ueda, K., et al. (2022). An analysis of the effect of integrated thermal control on cognitive task performance using time-series changes in intellectual concentration. AHFE 2022, 56, pp. 205-211.

Reika Abe, Masato Yamazaki, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda, Fumiaki Obayashi

Conference Proceedings

The Effect of Fading-In Light Transitions to Induce Micro-Refresh on Intellectual Work

Enhancing intellectual productivity is a critical issue in the modern information society. Previous studies have suggested that short breaks can effectively sustain cognitive performance [1]. "Micro-refresh" (MR), a brief break of a few to several tens of seconds aimed at maintaining concentration without significantly disrupting workflow [2], can be a promising strategy. However, effective methods for inducing MR remain unclear. This study focuses on dynamic lighting changes in an office environment as a novel method to induce MR. The primary objective is to conduct a preliminary experiment to investigate whether switching between lighting environments designed for work and refreshment can induce MR and support intellectual concentration during cognitive tasks.In this study, seven university students participated in a laboratory experiment. They performed a comparison task [3] under two lighting conditions: a switch condition and a no-switch condition. In the switch condition, the lighting environment alternated through fading-in between an approximately 750 lx task-and-ambient lighting designed for concentration and a brighter, uniform ambient lighting designed for refreshment. This switch occurred for 30 seconds a 10-minute cycle. In the no-switch condition, the task-and-ambient lighting was maintained in approximately 750 lx. To assess performance, the Concentration Time Ratio (CTR), an objective measure of intellectual concentration [4], was calculated from task response times. Subjective evaluations were also collected through questionnaires assessing fatigue and concentration levels, as well as feelings of detachment and refreshment, after each task set.As a result, the CTR improved for four of the seven participants under the switch condition. The average CTR for all participants was also slightly higher in the switch condition compared to the no-switch condition. Subjective results indicated that the switch condition tended to suppress increases in fatigue and declines in concentration. Furthermore, they reported greater feelings of refreshment and a lower tendency for detachment from the task in the switch condition. Post-experiment questionnaires revealed that most participants found the lighting environment in the switching condition comfortable and the switching frequency and duration appropriate.These findings from this preliminary study suggested that dynamic lighting changed during intellectual work had the potential to enhance subjective feelings of refreshment and contribute to the maintenance of concentration. However, the effect on CTR showed considerable individual differences, and it was observed that some participants did not utilize the intended MR periods for rest. Although these results are preliminary, they are expected to provide　valuable insights for designing office lighting systems that support intellectual productivity, further validation with a larger sample size and clearer instructions regarding the purpose of MR is necessary to generalize the findings.[1] Kristin, M. F., Paul, N. R., & William, S. H. (2016) Rest improves performance, nature improves happiness: Assessment of break periods on the abbreviated vigilance task. Consciousness and Cognition, 42, pp. 277–285.[2] Kitayama, K., Dianita, O., Ueda, K., Ishii, H., Shimoda, H., & Obayashi F. (2023). Micro-Refresh to Restore Intellectual Concentration Decline During Oﬃce Work: An Attempt at Quantitative Eﬀect Evaluation. Intelligent Human Systems Integration, 69. pp. 87–93.[3] Ueda, K., Tsuji, Y., Shimoda, H., Ishii, H., Obayashi, F., & Taniguchi, K. (2016). Development of "Comparison Task" to Measure Intellectual Concentration by Room Environment. Proceedings of the 2016 International Conference Affected on Communication and Information Systems, pp. 58–64.[4] Uchiyama, K., Oishi, K., Miyagi, K., Ishii, H., & Shimoda, H. (2014). Process in Evaluation Index of Intellectual Productivity Based on Work Concentration. Lecture Note on Software Engineering, Vol.2, No.1, pp. 21–25.

Masato Yamazaki, Reika Abe, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda, Fumiaki Obayashi

Conference Proceedings

Exploring Privacy in Digital Mental Health: User and Psychotherapist Perspectives

The rapid adoption of psychological consultation applications in Saudi Arabia has created both opportunities for accessible mental health support and challenges related to data privacy and security. Through 13 semi-structured interviews with users and psychotherapists, this study explores privacy behaviors, concerns, and protective practices regarding psychological consultation applications. The findings reveal that most users have limited concern for privacy when engaging with psychological applications, largely placing their trust in the platforms because of their perceived legitimacy and official approval. Users also rarely read privacy policies and typically relied on basic protective measures, such as using strong passwords, to safeguard their personal information. Psychotherapists emphasized adherence to professional integrity, ethical guidelines, and regulatory requirements. The findings from this study highlight the importance of raising user awareness about privacy policies, enhancing regulatory frameworks for digital health platforms, and integrating cybersecurity best practices. Such measures are critical for ensuring the long-term sustainability of digital mental health services.

Abdulmajeed Alqhatani

Conference Proceedings

Fake Aircraft, Real Threats: Training Air Traffic Controllers for Cyberattacks

As part of the modernisation of Air Traffic Management (ATM), an increasing number of technologies are being deployed to improve the provision of Air Traffic Services. For example, the large-scale implementation of Automatic Dependent Surveillance–Broadcast (ADS-B) helps controllers gain better situational awareness of aircraft in the airspace and manage traffic with greater safety and efficiency. Digitalisation in aviation, however, is accompanied by cybersecurity risks, and recent statistics indicate a substantial increase in cyberattacks within the aviation sector. The sources of vulnerability are multifaceted. Increased connectivity and human factors pose exploitable entry points for attackers. The cyber threats here are not typical IT incidents like phishing, but critical operational threats, like malicious aircraft injection. Training operators is crucial; air traffic controllers (ATCOs) must be able to distinguish real traffic from false information to react appropriately. The article’s study introduces an initial training concept tested in a half-day session using the Attack Simulator developed by Linköping University. It features six cyber threats exploiting ADS-B system vulnerabilities that ATCOs may face during duty.The participants in the study were eight experienced Swedish ATCOs. None of them had received prior training specific to cyberattacks in ATM, nor had they encountered the Attack Simulator used in this study. The study followed a repeated-measures design, with each participant completing three simulation runs of 25 minutes. The first run was a familiarisation session that allowed participants to get used to the Attack Simulator; no data from this phase were included in the analysis. In the second and third runs of the experiment, we conducted actual measured simulations with cyberattacks. Before the second run (Run 2), participants received a briefing on the types of cyberattacks that could occur during the simulation. Prior to the third run (Run 3), participants were presented with a video-animated knowledge transfer session designed to improve their understanding of how cyberattacks manifest within the simulation environment. In both Run 2 and Run 3, six types of attacks could occur, with a 30% probability for pre-spawned aircraft and a 40% probability for newly spawned aircraft. This experimental design was intentionally selected to mimic real-world cyberattacks and to minimise the chances of participants anticipating all potential stimuli and adjusting their responses accordingly. During these simulation runs, we recorded performance scores, which were later weighted based on the detection rate of specific attacks and the total number of events per scenario. For any omission or incorrect guess regarding an event type, the points deducted for that event type were multiplied by the detection rate of the event type. The points awarded for a correct identification were multiplied by “1 minus the detection rate of the event”. Thus, events that were more difficult to correctly identify were penalised less than those that were easier to correctly identify. The obtained score at the end of a scenario was divided by the total number of attacks that occurred during the simulation run. This approach ensured that participants’ reactions were evaluated in the context of the actual events they experienced. It is essential to note that air traffic control (ATC) tasks have been excluded from the analysis, as evaluating operator performance related to ATC tasks was outside the scope of this study. After each experimental run, participants completed post-simulation questionnaires that assessed situational awareness (SASHA), perceived workload (NASA-TLX), stress (SSSQ), and tailored questions regarding their confidence in correctly identifying and labelling the attacked aircraft. Results show improved ATCO performance scores, confirmed by participant feedback. The significant increase between Run 2 and Run 3 likely results from a learning effect due to repeated practice, video-based knowledge transfer, or both. Future studies with larger samples should include varied conditions to better identify the effects of each variable and their interaction.Subjective assessments of situation awareness, workload, and stress were on average acceptable across both runs. Individually, some variation appeared in global scores and assessments, likely due to the probabilistic event generation by the Attack Simulator, producing different scenarios for each participant. Answer patterns indicated that self-reported awareness, workload, and stress are linked to the volume of traffic and the frequency of attack occurrences. With more resources and higher sample sizes, future studies should design identical scenarios.

Maria Hagl, Supathida Boonsong, Tim H Stelkens-kobsch, Tim Ruediger, Andrei Gurtov, Gurjot Singh Gaba

Conference Proceedings

TEE Protected Drone Inspection for Critical Infrastructure: Securing Edge Analytics and Trust at Scale

Operators of critical infrastructure are required to inspect distributed assets on a regular basis to ensure safety and reliability. These assets span a wide range of domains, including bridges and roads, rail corridors, pipelines, power transmission lines, solar farms, wind turbines, telecom towers, ports, and large industrial facilities. Traditionally, inspections have been performed by field workers. While expert technicians are indispensable, manual patrols expose personnel to electrical, physical, and environmental hazards, which may constrain inspection frequency, coverage, and data quality. In recent years, many organizations have started to utilize drone technology to enhance safety, improve efficiency, and reduce operational costs. Unmanned aerial vehicles (UAVs) are a promising productivity amplifier: a pilot can dispatch a drone to nearby functional locations, collect high-resolution RGB and thermal imagery, run analytics to identify assets and assess their conditions, then send the data back for gatekeeping, desktop analysis, and master data updates. Yet the edge-centric workflow that makes drones efficient (e.g., sensing, filtering, and triage on board) also expands the attack surface. A compromised UAV or malicious insider can exfiltrate or manipulate observations and processing results, eroding trust and undermining downstream analytics.This paper proposes a trusted execution environment (TEE)–protected surveillance solution for UAVs that enforces end-to-end confidentiality and integrity across the entire data lifecycle. We isolate acquisition and pre processing inside a hardware rooted enclave, use encryption for sealed storage and in flight telemetry, and expose a remotely attested interface to the ground system. The design has four pillars. (1) Remote attestation for trusted loading: Before a flight, the ground station verifies that only vetted processing binaries are measured and loaded into the enclave. Mission keys are released only after successful attestation, binding computation to a specific enclave identity and configuration and ensuring information integrity. (2) Confidential processing in the enclave: Sensor data collection, feature extraction, data processing and analytics execute entirely within the enclave. Encryption keeps data confidential at rest and in transit while outside of the enclave, preventing leakage even if the host OS is compromised. (3) In enclave anomaly screening: To resist data poisoning and spoofed inputs, we deploy an autoencoder based anomaly detector inside the enclave. Trained on nominal RGB/thermal signatures from prior inspections, the model reconstructs incoming observations and flags high residual frames indicative of adversarial, fake, or tampered sensor data (e.g., GAN synthesized frames, injected hot spots, or replays). Flags and reconstruction scores are attached to each packet to inform downstream trust decisions. (4) Enclave signed results for verifiable provenance: Processed outputs are signed inside the enclave with keys cryptographically bound to the attested enclave instance. The ground station verifies these signatures and associated quotes, ensuring results arrive intact and unhampered and establishing a non repudiable chain of custody from edge to cloud.We designed the framework and security protocols of this system and studied different use cases to understand the feasibility of the proposed design. Our findings show that the framework increases operational efficiency in infrastructure surveillance and simultaneously enforces lifecycle security for surveillance data across acquisition, transport, and processing.

Yongzhi Wang

Conference Proceedings

Stress-Aware Urban Mobility: Predicting User Comfort with Physiological and Geo-Semantic Features

Human comfort and stress in urban mobility are increasingly recognized as critical dimensions for designing adaptive and user-centered transport systems. While most mobility research focuses on efficiency, reliability, and safety, the experiential quality of travel remains underexplored. This study contributes to closing this gap by developing and empirically validating machine learning models capable of predicting passenger stress in real-world on-demand public transport scenarios through a unique integration of physiological, mobility and semantic geodata. A field study was conducted in Neustrelitz (Germany) with 18 participants to capture naturalistic mobility behavior. Trajectory data were collected using the DLR MovingLab smartphone app and synchronized with physiological signals recorded by Garmin smartwatch sensors. In addition, qualitative interviews and standardized stress inventories were conducted before, during, and after the trips to better understand daily mobility routines and to interpret the physiological measurements. After preprocessing, 28,831 data points were enriched with more than 70 features covering transport modes, weather conditions and semantically annotated geodata such as road categories, intersection density and land-use characteristics. Machine learning models, including XGBoost and neural networks, were applied to predict stress levels. Results showed that semantic environmental factors such as proximity to intersections, traffic signals, or commercial areas emerged as significant predictors, highlighting the value of semantic awareness in transport system design. By linking physiological stress markers with contextual geodata, this study establishes a foundation for stress-aware mobility services that adapt dynamically to human needs and support the design of healthier, more inclusive, and more sustainable transport environments.

Karan Shah, Rene Kelpin, Alexander Steinmetz

Conference Proceedings

AI-Powered Tactile Glove for Human Recognition in Low-Visibility Fire Environments

Firefighters and rescue robots often face extremely low-visibility environments during fire emergencies, making it difficult and dangerous to locate and save victims. To address this challenge, we developed an AI-powered glove capable of automatically recognizing human body parts without requiring visual input or manual guidance.The system integrates 22 flexible, fire-resistant cermet matrix sensors onto a heat-resistant glove, forming a tactile sensing array. When the glove comes into contact with different body parts—such as the shoulder, arm, chest, or abdomen—it detects distinct pressure patterns that generate unique electrical signal distributions. These signals are then analyzed by a deep learning model trained to identify specific human body parts with high accuracy.This fusion of tactile sensing and artificial intelligence enables precise human recognition in low-visibility fire conditions, enhancing the safety and effectiveness of rescue operations. The project demonstrates how AI can be seamlessly integrated into real-world problem-solving to support first responders in life-saving missions.

Feng Jiang, Yongshi Guo, Jianhua Yan

Conference Proceedings

Bridging Ancient Art and Modern Technology: AI-Driven Storytelling of Dunhuang Mogao Grottoes

Artificial intelligence (AI) is rapidly transforming creative design, raising critical questions about its role as a collaborator rather than a replacement for human creativity. This project investigates human–AI co-creation in the digital preservation and storytelling of the Dunhuang Mogao Grottoes, a UNESCO World Heritage site and a pivotal crossroads of Silk Road civilizations. Facing accelerating threats from environmental degradation and mass tourism, the Grottoes require preservation strategies that move beyond static digital archiving toward dynamic cultural revitalization.Positioning AI as an active creative partner, the study explores how artists train and guide Artificial Intelligence–Generated Content (AIGC) systems to interpret and reimagine the iconography and narratives of the Mogao murals. Through iterative collaboration, AI contributes visual variations and motion design, while human expertise ensures historical context, aesthetic judgment, and narrative coherence. The outcome is a high-quality moving-image sequence that fuses AI-generated visuals with human-centered storytelling, transforming ancient Buddhist parables into immersive digital experiences.Beyond offering an innovative model for heritage conservation and audience engagement, this research advances discourse in digital media arts by demonstrating how AI can amplify, rather than replace, human creativity. By bridging ancient art with cutting-edge technology, the project proposes a scalable framework for integrating AI-driven production into the preservation of cultural heritage and contemporary digital storytelling.

Yang Liu, Xinran Mao, Jiexin Sun, Jiayi Qian, Sibei Chen, Cherine Abigail Kurniawan, Clement Fernando Kusuma, Fang Liu

Conference Proceedings

Synthetic Network Metric Generation via Conditional DDPM with Categorical and Continuous Log-Metric Conditions

Recent network systems increasingly rely on synthetic data for tasks such as anomaly detection, performance analysis, and digital-twin-based evaluation. However, most existing generators focus solely on metric time-series and overlook the contextual information embedded in operational logs. As a result, they fail to reproduce the joint behavior that emerges when metric fluctuations are closely linked to event-driven operational states. To address this limitation, we develop a conditional denoising diffusion probabilistic model (DDPM) that generates metric sequences using both categorical and continuous conditions derived from metrics and logs. These heterogeneous conditions are transformed into a unified vector and injected into the diffusion process, enabling the model to capture dependencies between system events and metric dynamics. Experiments on real network traces demonstrate that our conditional diffusion models—based on U-Net, CSDI, and SSSD architectures—substantially outperform unconditional diffusion baselines and show strong fidelity and downstream utility. These findings indicate that context-aware diffusion modeling provides a robust foundation for synthetic metric generation in AIOps and digital-twin environments where access to real operational data is limited.

Sangwon Oh, Hoyong Ryu, Jaehyung Park, Jinsul Kim

Conference Proceedings

Strategic Defense against Hybrid Threats under Emerging Disruptive Technologies: A Stochastic Modeling Framework

The fundamental unpredictability of Emerging Disruptive Technologies creates profound strategic asymmetries in hybrid threats, as defenders must prepare for unknown capabilities while attackers exploit breakthroughs. This research introduces a new model to analyze how technological uncertainty transforms optimal strategies for defensive actors, proving essential for developing robust strategies as the pace of technological innovation accelerates and the window between innovation and weaponization narrows. In this work, technological uncertainty is modelled as a stochastic evolutionary process, focusing on the defender's challenge of resource allocation. Through a parametrized model design, the framework provides high customisability for different scenarios and technology-specific insights relevant for developing optimized allocations of defense resources. We compare a naive baseline resource allocation against an optimized allocation in a simulated scenario, showcasing the need for differentiated defense postures and showcasing the need for differentiated defense postures and illustrating a novel pathway for reasoning under deep technological uncertainty. The experiments show a significant superiority of technology-tailored resource allocations, reducing overall attack impact and planning uncertainty.

Stefan Klug, Jonas Schmänk, Maximilian Moll, Stefan Pickl

Conference Proceedings

How should we design AI tools that handle personal information? Evaluating AI-generated personalized care advice based on deeply personal data

AI systems typically rely on commonly available knowledge from the internet—that is, public “common sense.” However, when applying AI in personalized service domains such as healthcare and elder care, it becomes essential to incorporate deeply personal information, such as individuals’ life histories. This paper introduces a case study of an AI tool that provides personalized care advice to care workers, aiming to derive insights for designing services that focus on the individuality of each service user. We developed a prototype tool using a profile sheet constructed from real narratives. Care workers’ evaluations, analyzed qualitatively, yielded insights regarding AI usefulness, individualized care, practical applicability, advice presentation, limitations and risks, and AI use contexts.

Masayuki Ihara, Hiroko Tokunaga, Tomomi Nakashima, Hiroki Goto, Yuuki Umezaki, Yoko Egawa, Shinya Hisano, Takashi Minato, Yutaka Nakamura, Shinpei Saruwatari

Conference Proceedings

Mission management in human autonomy teams – an HMI design concept for managing multiple uncrewed aerial systems from a fighter cockpit

Future air combat will be a complex interaction of crewed and uncrewed aerial vehicles. While many systems will act highly automated or even autonomously, human operators will remain essential for defining mission objectives, setting priorities, and making decisions that require human judgement. Effective collaboration between the human and the highly automated planning systems appears to be a crucial requirement for the success of such a human autonomy team. We present our human-machine interface (HMI) concept for the collaborative management of multiple drones in a future fighter cockpit – resulting from a user-centered development approach with several fighter pilots. We first used an Abstraction Hierarchy to identify the properties that are relevant to describe a mission plan proposed by the highly automated system. This hierarchical structure was then applied to the HMI design so as to tailor the level of detail of the displayed information precisely to the pilot’s situation-specific needs. This includes that information from the complex planning algorithms is presented to the pilots in a transparent and comprehensible way. Finally, an interaction concept was developed for the pilots to be able to easily input their preferences into the planning system.

Johannes Maria Ernst, Birte Thomas- Friedrich, Max Friedrich

Conference Proceedings

Hybrid Human–AI Interaction in Game-Theoretic Corporate Governance: Matching ESG Targets with Overarching Sustainable Development Goals

Corporate governance may admit multiple Nash equilibria. I develop a game-theoretic framework in which AI functions as an equilibrium selector by reducing information frictions, synchronizing beliefs, and expanding the basin of attraction for high‑ESG outcomes. Using 450 firms (2014–2024), I estimate that governance-directed AI adoption lifts ESG by 8–15% and is associated with lower implied cost of equity, higher Tobin’s Q, greater investment, and tighter credit spreads. Mechanism tests show improved disclosure (+8.24), tighter target discipline, and dampened strategic complementarities, with stronger effects in network‑central firms and high‑complementarity industries. Effects grow over time and are most pronounced where disclosure is complex. The results link governance technology to financing conditions and firm value.

Roberto Moro-visconti

Conference Proceedings

Distance Estimation in a Telepresence Scenario Using a 360° Monoscopic Camera, an AGV and an HMD

As telepresence has an increasing number of use cases where veridical perception of distances is crucial, understanding influences on distance perception gets more important. Many researchers focus on stereoscopic virtual environments and most often find that distances get underestimated. But when an operator is remotely controlling a robot, the remote location is often monitored by a monoscopic camera, featuring less cues for distance estimation. Hence, this paper proposes the design and evaluation of a study on distance perception in a monoscopic telepresence environment. Live footage of a 360° camera on an autonomous guided vehicle was shown to the participants via head-mounted-display, while they controlled the movement of the vehicle with a controller. Participants (n = 16) operated the vehicle and completed three different tasks related to distance and spatial perception: (1) In the move-to-target task, distances to a target object were estimated by moving the robot to the target; (2) in the verbal estimation task, they verbally judged different distances; and (3) in the passability judgment task, they assessed whether the vehicle could fit through a gap between two objects. Tasks (1) and (2) were studied with 5 target distance values between 0.7 m and 4 m and task (3) was repeated for 5 gap widths that were up to 15 cm smaller or higher than the AGV width. Each estimation task was tested with and without a visual distance estimation aid (DEA), which consisted of a grid of known size that was displayed in the camera video. Statistical analysis suggests an influence of target distance. For the move-to-target and passability judgement task significant differences were found across all pairwise comparisons, but for verbal estimation only for distances in personal space, i.e. < 2 m. The applied distance estimation assistant did not have a significant impact on the results, improving move-to-target estimations slightly (6.6 %) while somewhat decreasing the accuracy of verbal estimations, i.e. raising overestimation by around 3 %. Besides the small impact, most participants reported feeling safer in correctly estimating distances with the DEA activated, while some reported higher strain on concentration or misjudging the positioning of the grid.Overall, distances were overestimated in the move-to-target task (M = 110.7 %, SD = 17.8 %), while verbal estimates were more balanced, with both over- and underestimations occurring (M = 99.3 %, SD = 22.2 %). In the passability judgment task, participants consistently overestimated the width of gaps, with up to 62.5 % judging them to be wider than they actually were. Underestimation occurred in only about 4 % of trials. This overall overestimation of distances does not fit to typical findings of distance perception in stereoscopic virtual environments and could be influenced by different factors, e.g. bad image quality of the camera or less spatial cues. It could also be attributed to the small camera height of 1 m, since empirical results in the literature unequivocally suggest that lowering the eye-height leads to increasing distance overestimation.

Nick Weidensager, Jennifer Brade, Sven Winkler, Franziska Klimant, Philipp Klimant

Conference Proceedings

Career Design for Discovering Meaningful Work: A Narrative and Meaning Innovation Approach

The advent of generative AI is expected to reduce human working hours, requiring a transformation in the meaning of work. According to a survey in Japan, approximately 64.5% of workers cited “earning income” as their primary reason for working, while only about 20% cited “to utilize my abilities” or “to find purpose.” However, in the author’s career counseling practice, many clients express a desire for meaningful work and fulfillment. This suggests that while they may not currently experience intrinsic value in their work, they fundamentally seek meaning in employment. Against this backdrop, this study aims to establish a career design methodology that redefines the meaning of work.This study employed a qualitative approach. First, an integrated framework was constructed, leading to a hypothesis for a career design process focused on meaningful work. Drawing on Mark L. Savickas’s narrative career counseling and Roberto Verganti’s innovation of meaning, a hypothetical career design process was proposed to reveal both the inner sense of meaning in work and the creation of new societal value for the same individual. Three key processes were emphasized: (1) creating a personal history to discover new narratives, (2) uncovering value through dialogue with a career designer, and (3) receiving insights from industry experts (interpreters). The hypothesis was then analyzed and examined through text-based online chat communications and one-on-one online coaching sessions conducted over several months with five Japanese business professionals.As a result of engaging in the hypothesized career design process, three of the five participants were able to clarify their personal meaning of work and build new careers. Analysis of the success factors revealed that the three emphasized processes were effective. For example:Participant A discovered (1) narratives such as “the confident self” and “the self who loves making things” from his personal history; (2) “the artisan-like self” with the career designer; and (3) the career of “tatami craftsman” with the interpreter.Participant B discovered (1) the narrative of “the self interested in human behavior” from his personal history; (2) “the self who enjoys experiencing nature” with the career designer; and (3) the career of “nature school instructor” with the interpreter.Participant C discovered (1) the narrative of “the self who loves hospitality” from his personal history; (2) “the self who helps the socially vulnerable” with the career designer; and (3) the career of “coaching students at a free school” with the interpreter.These findings highlight the importance of balancing coaching with critical dialogue. While traditional counseling emphasizes drawing meaning from the client, career designers must also encourage the questioning of assumptions and critical reflection. To reinforce extrinsic meaning, it is essential to propose specific occupations or work styles that align with both intrinsic and extrinsic dimensions and demonstrate their significance.This research provides a career design process that addresses the challenge of lost meaning in work caused by technological advancement. By employing two design methodologies—narrative and meaning innovation—this process demonstrates the potential to generate both individual fulfillment and new societal value.

Hiroyuki Yanase

Conference Proceedings

Cultural Dynamics in Next-Generation Cockpit Design: Integrating Human Factors, Inclusivity, and System Resilience in Transportation Aviation

The next generation of cockpit design must evolve beyond ergonomic optimization to incorporate cultural and cognitive inclusivity. This study proposes a framework for integrating cultural intelligence (CQ) into cockpit development, applying the International Civil Aviation Organization (ICAO) ADDIE model to embed intercultural human factors throughout the design lifecycle. Empirical insights from accident investigations and Crew Resource Management (CRM) studies show that communication failures linked to power distance, uncertainty avoidance, and language proficiency remain critical risk factors in mixed-nationality flight decks. Traditional design has focused primarily on physical ergonomics and automation management; this framework extends these considerations to encompass cultural ergonomics, AI-mediated communication, and adaptive multimodal interfaces. By combining cultural intelligence theory with human–machine interaction design, the paper advances a systematic model for culturally adaptive cockpits. Initial results from simulator-based evaluations suggest that adaptive alerting, explainable automation, and co-authorable checklists improve communication efficiency, decision latency, and challenge–response equity. The findings underline that cockpit inclusivity and resilience depend on both technological innovation and the cultural adaptability of human–system interfaces.

Debra Henneberry, Dimitrios Ziakkas, Eleftherios Bokas, Konstantinos Pechlivanis

Conference Proceedings

Knowledge Engineering with Large Language Models: Accelerating Fuzzy Rule Bases Development for Energy-Aware Expert Systems

Expert systems offer a promising way to automatically identify energy efficiency potentials in industry and thereby contribute to energy cost savings and decarbonization. In these systems, domain-specific knowledge is embedded and linked to automated analyses of measurement data. Until now, knowledge engineers have extracted, structured, and represented the necessary domain-specific knowledge in a form usable by expert systems, which is time-consuming and costly. This article presents a hybrid approach that couples expert systems with large language models to support the work of knowledge engineers. Energy performance indicators, selected by the energy manager, serve to quantify changes in energy performance and reproduce the heuristic decision-making of human experts on a quantitative basis. These indicators then form the basis for a rule set that targets areas with the highest potential energy savings. For practical implementation, a fuzzy rule base is applied because it captures decisions made under imprecise information and allows conditions and conclusions that can be partially true or false. Building the fuzzy rule base involves assigning membership functions to input and output variables and defining their linguistic partitioning, since these choices shape both sensitivity and interpretability. The rule base is implemented as generally understandable IF–THEN rules. The premise consists of energy performance indicators that are associated with linguistic variables and combined using logical operators. The conclusion contains priority numbers, which are also associated with linguistic variables and express the energy efficiency potential. In the hybrid setup presented in this article, large language models formalize given energy performance indicators and fuzzy rules, propose membership functions to populate the fuzzy rule base, and generate visualization scripts in Python. This leads to accelerated development while preserving transparent, comprehensible, and reproducible decision logic characteristic of expert systems. The approach is demonstrated using a foam panel production line in the chemical industry.

Borys Ioshchikhes, Ann-kathrin Bischoff, Jerome Stock, Micheal Frank, Matthias Weigold

Conference Proceedings

Transparency for Trust: Enhancing Acceptance and System Integration of Intelligent AI in Healthcare

The integration of intelligent systems into healthcare has transformed how diagnosis, therapy, and clinical decision-making are conceptualized and delivered. Artificial intelligence (AI) now supports a wide range of functions, from predictive analytics to personalized interventions. Despite these advances, the acceptance of AI in healthcare remains uneven, shaped not only by technical performance but also by the degree of transparency surrounding its capabilities and limitations. Without clear communication, trust becomes unstable, oscillating between overreliance and outright rejection. This paper examines transparency as the essential foundation for trust calibration, proposing that transparent AI systems enhance user confidence, preserve the therapeutic alliance, and ultimately contribute to better patient care. Building on prior research in neuroadaptive AI and virtual reality therapy for children with autism spectrum disorder, where transparent EEG-based engagement metrics increased acceptance by clinicians and caregivers, the authors argue that transparency should be understood as a core design principle for the system integration of intelligent AI in healthcare. A synthesis of literature across healthcare AI, trust-in-automation, and human–computer interaction demonstrates consistent evidence that transparency mechanisms improve acceptance. Studies on explainable AI indicate that visual explanations and confidence indicators significantly increase appropriate reliance while reducing the risks of miscalibration. The Human Identity and Autonomy Gap (HIAG) framework provides a valuable lens for interpreting these outcomes, illustrating how transparency mediates trust across cognitive, emotional, and social dimensions. Cognitively, transparency clarifies the reliability and scope of AI decision-making; emotionally, it reduces user uncertainty and anxiety; socially, it preserves clinician authority while fostering collaboration with patients and caregivers. Yet transparency must go beyond technical disclosure. Systems must communicate strengths and limitations, such as bias, data dependency, and contextual blind spots, while ensuring that transparency does not overwhelm users with excessive detail. Evidence also shows that transparency must be culturally adaptive, since trust and adoption vary across professional and cultural contexts, with some prioritizing certainty and governance while others value autonomy, discretion, and relational trust. This paper contributes to theory and practice by proposing design and policy guidelines that embed transparency into healthcare AI development. Strategies include adaptive interfaces that communicate uncertainty through confidence dashboards, culturally sensitive explanations that reflect global variability, and training modules that prepare clinicians and caregivers to interpret AI outputs responsibly. By positioning transparency as a prerequisite rather than an afterthought, intelligent systems can be integrated into healthcare workflows in ways that align with human values, safeguard professional autonomy, and foster equitable adoption across diverse settings. Ultimately, transparency transforms AI from a black-box technology into a trusted partner in healthcare innovation. These insights provide not only a conceptual framework for understanding trust calibration in AI-enabled healthcare but also a roadmap for developing intelligent systems that deliver meaningful, safe, and ethically grounded improvements in patient care, ensuring that future applications truly advance medical practice and human well-being.

Nikita Islam, Ancuta Margondai, Julie Rader, Sara Willox, Cindy Von Ahlefeldt, Mustapha Mouloua, Valentina Ezcurra

Conference Proceedings

Integrated Disaster Situation Management System with Domain-Specific Ontology Model

Disaster response and management in the era of climate change require seamless coordination across numerous agencies, systems, and stakeholders. A shared understanding of the situation is critical as responders from different organizations (e.g., fire, medical, military) must work in concert under high pressure. The common ontological definition is important for various stakeholders and expert groups to understand disaster during its different stages for controlling and managing salvation and recovery. Semantic interoperability works in practice between different organizations by creating a common language and meaning structure that enables information to be exchanged and understood without misunderstanding. This is achieved through a common ontology that defines key concepts unambiguously. This research examines the creation of common ontology and semantics aspects during nature disaster identification and management. In this study the MobiJOPA™ has been the use case environment system. It was created recently by the Start-up company Husqtec Corp., which is concentrating on situation and operational management. Use case has been a water flow disaster, which is a quite common type of disaster due to the influence of climate change. During the research has been answered to the following research questions: •How is the integrated situation awareness system dynamics structured and organized?•How is system functioning and human interoperability organized by the ontology interface?•How is data, information, and knowledge economy structured and managed?•How is stakeholder training organized, and knowledge gathered to create an ontology interface, routing common disaster understanding?Semantic infrastructure supports information integration by combining heterogeneous data sources, such as sensors and social media, into a unified information model. Semantic interoperability is not an abstract benefit; it operationalizes the data in ways that closely support the real tasks and decisions of emergency management. It creates a common operating environment where each piece of information is readily available to those who need it, in a form they can understand and trust. It moves the focus from low-level data wrangling to higher-level analysis and action. Building such interoperability requires understanding the real-world semantics, linking formal data to meanings that make sense to humans in their roles. In other words, the ontology must be grounded in the language and practice of emergency responders. This ensures that technology aligns with human thinking, further enhancing clarity and coordination. Semantic interoperability enabled by a common ontology and robust system architecture provides shared situational awareness and efficient coordination in disaster management. It reduces information fragmentation and miscommunication.

Vesa Salminen, Matti Pyykkönen, Ari Saarinen, Nikolai Ylirotu

Conference Proceedings

Human system integration in future AI-supported MUM-T mission management

Manned-Unmanned Teaming (MUM-T), i.e. the cooperation between manned and unmanned resources, will play a central role in future combat and mission management. In line with current technological advances, future MUM-T systems however will not only see cooperation with highly autonomous unmanned resources. In addition, AI-powered systems will support human operators during every step of planning, decision making and mission management. This integration of AI in existing mission management processes and systems has to take the needs of the humans into account to optimally support and enhance the human operators’ performance in mission management and fully harness the advantages of MUM-T and AI. Thus, future AI-supported mission management systems should be developed in a human-centered design process including future users instead of mainly focusing on what is possible from an engineering perspective. Therefore, this paper outlines our approach to human system integration in the development of AI-supported mission management systems along the example of developing an HMI for fighter pilots. After first understanding and describing the system in which mission management takes place, the main human factors issues that should be taken into account when developing systems for AI-supported MUM-T mission management are summarized. Then, we give a short overview of the user-centered development of the HMI mock-up and summarize the results of a user evaluation. Implementing such a human-centered development process will ensure the success of future AI-supported mission management systems.

Birte Thomas- Friedrich, Johannes Maria Ernst, Max Friedrich

Conference Proceedings

The Transparency Paradox: How AI Explanations Reduce Perceived Autonomy in Organizational Decision-Making

Artificial intelligence transparency is widely assumed to enhance user experience, yet this study reveals a paradox: detailed AI explanations reduce perceived autonomy. In a between-subjects experiment (N = 557), business students made organizational decisions with either transparent AI recommendations (detailed rationales) or basic recommendations (minimal explanation). Participants receiving detailed explanations reported significantly lower autonomy (M = 3.73) than those receiving basic recommendations (M = 3.84), d = -0.19. Personality substantially moderated effects: Openness to Experience reversed the paradox (interaction = -0.227), with intellectually curious individuals benefiting from transparency, while Extraversion amplified autonomy reduction (interaction = 0.173). Males showed twice the autonomy reduction of females (0.137 vs. 0.063), and effects disappeared by ages 23-25. Neither AI familiarity, attitudes, nor decision complexity moderated effects, suggesting fundamental psychological responses. Despite reduced autonomy, participants maintained positive AI attitudes, revealing dissociation between momentary decision control and general acceptance. Findings challenge universal transparency mandates and suggest personality-adaptive systems may better serve diverse users.

Ancuta Margondai, Sara Willox, Anamaria Acevedo Diaz, Soraya Hani, Nikita Islam, Mustapha Mouloua

Conference Proceedings

Integration of Musculoskeletal and Autonomic Ocular Cues in Virtual Humans: Effects on Emotion Perception and Authenticity

Virtual human facial emotion expression is typically driven by musculoskeletal control, whereas autonomic physiological cues remain underused. We conducted a virtual reality study with a 5×5 factorial design that crossed five levels of musculoskeletal valence with five ocular states ranging from high parasympathetic activity to high sympathetic activity. Ocular physiology was implemented through parametric control of pupil diameter and scleral redness. Nineteen participants rated each stimulus for perceived valence and authenticity. While musculoskeletal cues were the primary driver of perceived valence, ocular physiology produced significant modulatory effects, even at the resolution of current headsets. This indicates that observers are sensitive to subtle ocular changes. For authenticity there was no direct effect of physiological cues, but there was a significant interaction with musculoskeletal cues, showing that authenticity judgments depend on their combination. Together, these findings suggest that adding physiologically plausible ocular signals enhances the social believability and improves the perception of emotions in virtual humans, with implications for training, serious games, social robotics, and behavioral science.

Yvain Tisserand, Elise Prigent, Eva R Pool, Aline Layachi, Michel-ange Amorim, David Rudrauf

Conference Proceedings

Effects of AI Conversational Agents on Stress Reduction: A Meta-Analysis (2015- 2025)

Between 2015 and 2025, researchers conducted randomized and quasi-experimental trials to investigate whether AI chatbots can reduce perceived stress in adults. These interventions typically delivered CBT, mindfulness, or positive psychology techniques through mobile or web-based platforms. Stress was most commonly assessed using the Perceived Stress Scale (PSS); few studies included physiological measures such as HRV. A review of 34 studies (29 RCTs, 5 quasi-experiments) across diverse populations, such as students, healthcare workers, older adults, and individuals with chronic illnesses, revealed that most interventions lasted between 1 and 16 weeks. About half of the trials reported significantly greater stress reductions in chatbot users compared to controls, generally with small to moderate effect sizes. The remaining studies showed no significant differences. Several studies also reported meaningful improvements in anxiety, depression, or coping self-efficacy, even when stress effects were minimal. The findings suggest that the efficacy of chatbots for stress reduction is mixed and context-dependent, likely moderated by factors such as population, intervention design, and engagement level. Chatbots are seen as promising, scalable tools for stress management; however, future trials should include standardized outcomes, objective stress markers, and longer follow-up periods to better understand their sustained impact.

Cindy Von Ahlefeldt, Ancuta Margondai, Mustapha Mouloua, Valentina Ezcurra, Soraya Hani, Anamaria Acevedo Diaz

Conference Proceedings

The Silent Impact of AI: Unveiling Motivational Side Effects in the Digital Workplace

As artificial intelligence (AI) becomes increasingly embedded in knowledge-intensive work, concerns are growing about its psychological impact on employees. While much of the existing literature emphasizes productivity gains and task automation, this study explores a less visible dimension: the potential motivational side effects of AI integration. Specifically, we investigate how the use of AI tools in professional contexts may affect perceived social presence, cognitive effort, motivation, and ultimately, task performance.Grounded in the High-Performance Cycle (Locke & Latham, 2002) and complemented by theories of social presence, perceptual fluency, and cognitive engagement, we develop a comprehensive mediation model. The model hypothesizes that AI usage may reduce motivation indirectly through decreased perceptions of social presence and lower cognitive investment in tasks. Motivation, in turn, is expected to predict self-reported performance outcomes. We further examine whether technological self-efficacy moderates these pathways.To empirically test our model, we conducted a cross-sectional survey with 297 professionals who regularly use AI systems such as generative language models, automation platforms, and AI-driven analytics tools. Participants were recruited via professional networks (e.g., LinkedIn, Prolific Academic) and selected based on their experience with AI in daily work tasks. All key variables - AI usage, perceived social presence, cognitive effort, motivation, and performance - were measured using validated Likert-scale instruments. Data were analyzed using structural equation modeling (SEM) and bootstrapped mediation tests.Results reveal that AI usage has a statistically significant negative effect on both social presence (β = -0.42) and cognitive effort (β = -0.38), which in turn positively influence motivation (β = 0.35 and β = 0.31, respectively). Motivation emerged as the strongest predictor of performance (β = 0.58). Mediation analyses confirmed that the effects of AI on performance are fully mediated by motivational and perceptual variables. Additionally, exploratory moderation analyses showed that technological self-efficacy buffers the negative impact of AI usage on motivation, suggesting individual resilience factors play a role.This study contributes to the literature by extending motivational theories into AI-mediated work contexts and identifying key psychological mechanisms behind technology-induced disengagement. It highlights that AI systems, while operationally efficient, may alter the subjective experience of work in ways that reduce intrinsic engagement. The findings have implications for organizational design, system architecture, and human-AI interaction strategies. They also call for the development of motivationally aware AI systems and for training programs that enhance technological self-efficacy.In sum, our results underscore that the impact of AI is not only functional but also psychological. The future of work will depend not just on how well machines perform, but on how well they preserve the human motivation to engage, create, and perform.

Karsten Huffstadt

Conference Proceedings

When to Trust the Machine: A Simulation Framework for Human–AI Collaboration

Artificial intelligence in safety-critical areas like transportation needs proper trust calibration for safe human–AI collaboration. This study explored how transparency affects trust development through a simulation of human–AI interaction in automated driving. A discrete event simulation modeled human agents interacting with an automated driving assistant at different reliability and transparency levels. Trust changed asymmetrically, decreasing three times faster after errors than it increased after corrections. Transparency was tested in four conditions: none, confidence only, rationale only, and full transparency (confidence, rationale, and uncertainty). Analysis of 24 million decisions from 24,000 runs showed significant effects of reliability and transparency on trust calibration and a notable interaction. High transparency reduced calibration error by 42.5% and improved task accuracy beyond human baseline, increased acceptance 2.4 times, and decreased overtrust and undertrust significantly. Decision latency rose slightly but remained acceptable. Time-series analyses indicated trust aligned with actual AI reliability only under transparent conditions. Transparency explained 73% of trust calibration variance, surpassing the impact of AI reliability alone. These results highlight transparency as vital for calibrated trust and safe reliance in human–AI systems, offering quantitative guidance for explainable AI design in transportation and safety-critical fields.

Soraya Hani, Ancuta Margondai, Sara Willox, Cindy Von Ahlefeldt, Valentina Ezcurra, Anamaria Acevedo Diaz, Nikita Islam, Mustapha Mouloua

Conference Proceedings

Conditioned to Interact: A Computational Simulation of Pavlovian-Instrumental Transfer in Intelligent System Design

Intelligent systems increasingly leverage behavioral conditioning mechanisms to guide human engagement, yet the systematic effects of these mechanisms on human-AI interaction remain underexplored through computational modeling. This study presents a novel agent-based simulation framework that models Pavlovian-Instrumental Transfer (PIT) dynamics in human-intelligent system interactions, providing insights into how conditioned cues shape user behavior and offering design principles for ethical intelligent system development. Pavlovian-Instrumental Transfer occurs when conditioned cues, such as notification icons, vibrations, or interface animations, enhance the probability of operant behaviors by associating them with rewards. While PIT has been extensively documented in psychology and neuroscience, its systematic role in shaping human interactions with intelligent systems remains fragmented, and its potential for constructive applications in human-centered AI design has received limited scholarly attention.This study employs a computational approach grounded in established reinforcement learning theory to develop a multi-agent simulation platform. Individual users are modeled as learning agents with empirically derived parameters for learning rates, reward sensitivity, and Pavlovian bias, based on validated human PIT research. The simulation incorporates multiple intelligent system scenarios, including adaptive learning platforms, autonomous vehicle interfaces, smart home systems, and safety-critical dashboards, each implementing different conditioning paradigms and transparency levels.The simulation framework replicates established human PIT effects before extending to intelligent system contexts, ensuring empirical validity. Key manipulations include cue modalities (visual, auditory, haptic), reinforcement schedules (fixed versus variable ratio), and novel parameters relevant to intelligent system design, such as conditioning transparency and user autonomy controls.The framework identifies three principles for ethical intelligent system design: conditional transparency (making conditioning mechanisms visible without eliminating their beneficial effects), adaptive autonomy (implementing user control mechanisms for personal conditioning parameters), and context-sensitive scheduling (aligning reinforcement patterns with user goals rather than system metrics).This computational approach offers significant methodological innovations for research on integrating human-intelligent systems. By enabling ethical testing of potentially problematic conditioning scenarios before real-world deployment, the simulation provides a pathway for developing beneficial human-AI interactions. The framework demonstrates how behavioral science principles can inform intelligent system design while maintaining user well-being and autonomy. The study contributes to intelligent systems research by providing the first systematic computational model of behavioral conditioning in human-AI interaction, establishing empirically grounded design guidelines for ethical conditioning implementation, and offering a scalable methodology for testing human-centered AI principles before deployment. This work positions behavioral conditioning as both a diagnostic tool for identifying exploitative AI practices and a constructive framework for developing next-generation human-intelligent system integration that enhances human capabilities while preserving agency in an increasingly automated world.

Julie Rader, Ancuta Margondai, Sara Willox, Soraya Hani, Nikita Islam, Valentina Ezcurra, Mustapha Mouloua

Conference Proceedings

Human-Centered Harmonic Analysis of the Beatles’ Yesterday: Chord Wheel, Process Diagrams, and Eye-Tracking Insights

This paper presents an innovative approach to analyzing the harmony of the well-known and iconic song Yesterday by the Beatles using the chord wheel diagram in combination with BPMN-based process modeling. While classical methods of harmonic explanation rely on standard notation (including tablature) and chord symbols, our method focuses on visual and procedural representations. According to our findings, these representations reduce cognitive load and thereby improve understanding of music. They are, however, primarily intended for amateur musicians rather than trained professionals.The chord wheel diagram developed by our team provides an interactive visualization of tonal relationships, enabling users to follow the sequence of chord formation within a key, while also explaining chord progressions and their structural logic. Based on this, process diagrams modeled in BPMN formalize the sequential logic of harmonic development and its direct connection to the song’s melody. This dual representation—circular tonal mapping and algorithmic procedural modeling—offers students an accessible way to understand why the harmonic structure of Yesterday creates its characteristic expressive quality.To evaluate the usability and clarity of this approach, we conducted a qualitative study supported by eye-tracking experiments. Eye movement data revealed which parts of the diagrams were more difficult for participants to comprehend, highlighting critical points of cognitive overload. Based on this analysis, we define how process models can be refined to guide attention more effectively, reduce ambiguity, and improve the integration of harmonic and melodic information.Our findings suggest that this combination of chord wheel visualization, BPMN process modeling, and eye-tracking–driven analysis provides unique insights into how non-professional musicians interact with harmonic structures. Compared with conventional notation, participants perceived visual and process-based models as more intuitive, especially when applied to familiar repertoire such as Yesterday.We argue that integrating computational models with human-centered visualization and empirical usability testing represents a promising alternative for music education and harmonic analysis. By applying principles of human–computer interaction to music theory, this study shows how modern computer science technologies can support creativity, learning, and meaningful interaction in music.

Josef Pavlicek

Conference Proceedings

Improving the accuracy of automatic object tracking by using posture recognition

In recent years, in addition to classical machine vision algorithms, AI-based techniques such as image segmentation and object detection and recognition have been utilised in the transport sector for various purposes. These include vehicle-on-board applications for driver assistance or autonomous “self-driving”, such as object detection for collision avoidance and traffic monitoring and management applications. One application in the field of aviation is “remote tower”. “Tower” air traffic controllers work by observing the traffic at airports directly from a control tower building. Remote tower uses video cameras to replace the “out-of-the-window” tower view, enabling the physical tower to be eliminated and allowing controllers to provide services from a remote location. Digitization of the image stream also gives the opportunity to develop functions to support the controller tasks and improve situational awareness.This paper describes the development of a system to support remote tower operators in airport traffic control. The system features pan-tilt-zoom (PTZ) cameras with an automatic tracking function for aircraft flying in the vicinity or moving on the surface of the airport. The function operates in two modes: “sensor” tracking based information from an aircraft surveillance sensor, and “optical” tracking based on recognising and tracking aircraft or ground vehicles from PTZ camera images.This paper discusses the challenges and solutions concerning the automatic tracking function of the PTZ camera utilising image recognition.Challenges in Automatic Object Tracking Using Image Recognition:This research has developed functionality for recognising target such as aircraft and vehicles at airports and their surroundings in video images using YOLO. YOLO incorporates both target extraction and recognition processes within images, having the advantage of enabling rapid processing up to target recognition.On the other hand, several challenges arise when using YOLO recognition results for target tracking. One such challenge is the occurrence of “switching” during target tracking. Target switching refers to instances, when multiple aircraft are present in the image, tracking shifts to an object with higher recognition accuracy, or where tracking mistakenly follows another target if the originally recognised and tracked target was lost by an obstacle. As our first trial, to suppress this “switch”, we attempted a method whereby the velocity vectors of each object are calculated from the image recognition results, and the difference between the velocity vectors of the target object and other recognised objects is used as a discrimination parameter.This method determined how closely “current movement” matched “past movement”. These were estimated as a cubic function between “current movement” and “past movement”, using information on the “last position of the past movement”, the “first position of the current movement”, the “velocity of the past movement”, and the “velocity of the current movement”. Movements were judged to be closer together when the coefficients for the cubic “change in acceleration” and the quadratic “acceleration” were smaller. However, as a result, when aircraft crossed at slow speeds, fluctuations in the image recognition segmentation frames interfered, preventing the detection of velocity vectors. Furthermore, in cases where detection was unstable due to factors such as aircraft becoming obscured, resulting in gaps in the data, the coefficients became smoother. This led to instances where other targets were misidentified.Object identification based on posture detection:This paper investigated whether continuous tracking of target aircraft could be achieved even in crossing situations by learning aircraft orientation using YOLO v8 and identifying the aircraft's orientation. To recognise aircraft orientation, the ‘Posing’ function was utilised for ‘Pose’ learning. Annotation data comprising six points—nose, fuselage, right wing, left wing, tail, and vertical tail fin—was created and used for training.In the case study, we could determine the aircraft's orientation through image recognition. By utilising this orientation recognition result as a determination parameter for tracking, we confirmed that continuous tracking is achievable even in situations where automatic target tracking would previously be impossible using only velocity vectors.

Satoru Inoue, Mark Brown, Tomofumi Yamada

Conference Proceedings

AI-Driven Text-to-Speech for Non-Playable Characters in XR Educational Environments

This case study explores the implementation of a text-to-speech (TTS) engine integrated with conversational artificial intelligence (AI) to create interactive non-playable characters (NPCs) for Virtual and Mixed Reality (VR/XR) educational environments. The primary objective was to design a course that introduces students to three transformative technologies—AI, Virtual Reality (VR), and Extended Reality (XR)—while encouraging them to develop AI-driven, voice-acted NPCs as educational tools. These NPCs serve as interactive agents to support the students' learning experience within immersive environments. Throughout the study, various state-of-the-art AI tools were evaluated in combination with leading game engines to determine the most effective and accessible development environment for educational purposes. The project was conducted at Ocean Center, an initiative of the Amazonas State University in Brazil, which offers free technology-focused courses to the population of the western Amazon region. Among the Center's offerings are AR, VR, and XR courses, now enhanced with AI integration to broaden students' technological skillsets. By combining conversational AI with TTS capabilities in immersive VR/XR settings, the project provides a comprehensive framework that empowers students to create engaging, intelligent virtual characters. This approach not only enhances their technical competencies but also fosters creativity and innovation. The results suggest a promising model for integrating emerging technologies into education and may serve as inspiration for educators and institutions seeking to adopt immersive, AI-enhanced learning methodologies worldwide.

Sylker Silva, Isabelly Oliveira, Rodrigo Costa

Conference Proceedings

From Human Systems Integration to Human Systems Migration: First sketch from the automated driving system project MiRoVA

With the advancement of artificial intelligence (AI), machines are gaining unprecedented autonomous capabilities. This progress presents a significant challenge in how to seamlessly integrate humans, machines, organizations, and the environment into meaningful socio-technical systems. This process is called Human System Integration (HSI) and a prime example is vehicle automation in the transportation sector. In this sector AI enables a spectrum of automation levels, culminating in highly and fully automated systems. In the center of this integration challenge lies the concept of control. Traditional control theory, which focuses on a single entity’s command and execution, is no longer sufficient to address this growing complexity. The rise of automated systems makes new control paradigms necessary. Shared control, where humans and machines collaboratively operate the vehicle, and traded control, where authority is passed back and forth; both provide more dynamic and flexible solutions. The synthesis of these approaches, cooperative control, represents a new frontier for integrating people with intelligent technologies. As these paradigms become increasingly relevant, they demand novel methodologies that extend beyond traditional engineering and human-in-the-loop experiments. To bridge the gap from initial theoretical concepts to practical design patterns and implementations, a deeper and more systematic investigation into the human-system relationship is required, moving toward a holistic understanding of human adaptation, trust, and collaboration with vehicle automation. Challenges for human adaptation introduced by the rapid evolution of intelligent technologies cannot be neglected, as failures in human-system coordination can have direct implications for public safety and societal acceptance. This gives rise to the crucial concept of Human Systems Migration (HSM), which is now scientifically defined and investigated. It describes the dynamic process of humans and technologies moving together through new system configurations. In this context, the DFG-funded research group MiRoVA (Migration of Road Vehicle Automation) was established to investigate and exemplify Human Systems Migration in the domain of automated vehicle systems.In this paper, we present Human Systems Migration as key paradigm for understanding the integration of people and intelligent technologies. We illustrate these paradigms with the MiRoVA project, where we explore migration paths through different automation levels and analyze the resulting processes of adaptation and collaboration. We view the migration challenge on various levels, including a technological, game theoretical, as well as micro and macro perspective. These considerations not only address the integration of people and automation, but also extend to broader concerns such as social development, autonomy, safety and sustainability. Our interdisciplinary approach provides a foundation for bridging theoretical models with design patterns and practical implementations, addressing critical questions of trust, safety, and societal acceptance of vehicle automation.

Frank Flemisch, Tassilo Ianniello, Paul Weiser, Justin Osmanov, Tianyu Tang, Kai Storms, Can Kemmler, Marvin Baumann, Bettina Abendroth, Klaus Bengler, Steven Peters, Peter Vortisch

Conference Proceedings

Harnessing Emerging Technologies to Enhance Decision-Making in Competency-Based Training and Assessment

The transition from traditional training methods to Competency-Based Training and Assessment (CBTA) represents a paradigm shift in aviation education, aligning learning outcomes with operational realities rather than rote procedural mastery. This study advances CBTA by re-envisioning decision-making—a complex ICAO core competency—as a dynamic, human-centered process cultivated within adaptive and operationally authentic environments rather than through procedural repetition. Using the ICAO ADDIE framework, the research identifies recurrent decision-making challenges from accident data and training records, designs culturally intelligent and human-factors-integrated learning modules, develops AI-driven digital twins, immersive VR/AR simulations, and smart haptic systems to replicate complex operational contexts, and implements these innovations across pilot, air traffic, and maintenance training programs. Evaluation integrates quantitative metrics—reaction times, decision accuracy, workload indices—with qualitative insights from reflective debriefings and peer assessment to measure competency growth. AI enhances objectivity and reduces assessor bias through real-time behavioral analytics, while immersive and tactile simulations provide exposure to rare, high-risk scenarios that cannot be safely recreated in live training. The resulting ecosystem transforms CBTA from static evaluation toward a responsive, data-informed socio-technical model in which human expertise and technological adaptability co-evolve. The study contributes theoretically by redefining CBTA as an adaptive learning system, practically by producing validated decision-making modules, and strategically by offering policy guidance to regulators such as ICAO, EASA, and FAA for the inclusive and harmonized integration of emerging technologies into aviation training frameworks.

Debra Henneberry, Dimitrios Ziakkas, Ioanna Lekea, Konstantinos Pechlivanis

Conference Proceedings

Human-Centered Safety and Ergonomic Design for Women in High-Risk Industrial Occupations: A Systematic Review within Intelligent Systems Context

Women’s participation in high-risk sectors such as mining, construction, transportation, and healthcare continues to increase, yet industrial safety and ergonomics remain dominated by gender-neutral design assumptions. This systematic review synthesizes evidence on physical, psychosocial, and organizational challenges faced by women in hazardous environments through a human-cantered systems lens. Following PRISMA 2020 guidelines, 24 peer-reviewed studies (2010–2025) from Scopus, Web of Science, and PubMed were analyzed. The literature highlights exposure to musculoskeletal disorders (MSDs), PPE mismatch, postural load, and inequitable access to safety resources. Thematic analysis reveals that ergonomic inequalities intersect with exclusion from safety training and organizational barriers in risk management. Findings underscore the need for interdisciplinary approaches integrating ergonomics, intelligent systems, and gender studies to enable safer and more inclusive workplaces for women in high-risk occupations.

Sevinc Serpil Aytac, Hüsre Gizem Akalp, Nurettin Yamankaradeniz, Nuran Bayram Arlı

Conference Proceedings

Latency, Sensitivity & Optimizing Workload in Drone Control: Neuroergonomic and Neurodiverse Insights for Equitable, Therapeutic, and Inclusive Action

As small Unmanned Aerial Systems (sUAS) become vital beyond industries into therapeutic contexts, understanding how control interface parameters, like latency and joystick sensitivity. affect neurodiverse users is critical. Unoptimized interfaces can exacerbate stress, cognitive overload, and social alienation among individuals with ADHD, Autism, or Dyslexia. This study examines how varying latency and sensitivity influence cognitive workload, task performance, and psychological outcomes, integrating neurophysiological and behavioural data to inform inclusive sUAS design. Using real-time EEG to measure theta, alpha, and beta brainwave activity, results reveal that low latency and medium sensitivity yield optimal performance for neurotypical users, while neurodiverse individuals exhibit unique workload thresholds. Findings emphasize the importance of EEG-driven adaptive interfaces to mitigate cognitive strain and personalize control configurations. This neuroergonomic framework advances equitable, cognitively sustainable drone systems, promoting therapeutic potential, enhanced accessibility, and safer human–machine interaction for neurodiverse populations.

Suvipra Singh, Charlotte Geary

Conference Proceedings

Regulatory Pathways for Inclusive Human Systems in Aviation: Embedding Ethics and Emerging Technologies into Global Oversight

Aviation oversight is evolving in response to emerging technologies such as Artificial Intelligence (AI), Advanced Air Mobility (AAM), and digital-twin ecosystems. These innovations enhance safety and efficiency but also challenge the inclusivity, transparency, and ethical legitimacy of global regulatory systems. This paper explores how international authorities, including the International Civil Aviation Organization (ICAO), the European Union Aviation Safety Agency (EASA), and the Federal Aviation Administration (FAA), can embed inclusivity and ethics within the design and implementation of oversight mechanisms. Using the ICAO ADDIE framework (Analysis, Design, Development, Implementation, Evaluation), the study proposes a conceptual model for integrating inclusivity indicators, cultural intelligence, and AI-driven analytics into certification, training, and surveillance processes. Case vignettes demonstrate how inclusive governance can improve trust, fairness, and adaptability in areas such as community engagement and algorithmic transparency. The findings indicate that inclusivity should evolve from an aspirational value to an auditable regulatory requirement, supported by measurable indicators and interoperable data standards. By aligning the principles of the EASA AI Roadmap 2.0 and the proposed AI Code of Ethics with adaptive oversight practices, regulators can enhance both safety and social legitimacy. Ultimately, sustainable innovation in aviation depends not only on technological advancement but also on regulatory ecosystems that recognize diversity, foster dialogue, and institutionalize ethical accountability.

Dimitrios Ziakkas, Debra Henneberry, Anastasios Plioutsias

Conference Proceedings

The Role of Ethics and Public Acceptance in Transportation Accident Investigations: The Greek Case Study

Transportation safety investigations aim not only to identify technical failures but also to understand the broader human and organizational factors that contribute to accidents. In recent years, public acceptance has emerged as a critical determinant of the effectiveness of these investigations. Communities increasingly demand accountability, transparency, and ethical integrity in the processes that follow aviation and transportation accidents. The Greek case study presented here, centered on the War Games Laboratory of the Hellenic Air Force Academy (Department of Aeronautical Sciences, Division of Leadership-Command, Humanities and Physiology), and the National and Kapodistrian University of Athens Science, Technology and Innovation in Society (STIS) Laboratory, examines how ethics and public acceptance interact as fundamental components of accident investigation, prevention, and systemic resilience. The study is part of a broader research hub (2024–2027), in collaboration with Coventry University, Purdue University and Centre for Research and Technology Hellas (CERTH), which explores the role of individual and organizational ethics in shaping safety outcomes across civil and military aviation. Ethical lapses—such as the concealment of errors, tolerance of procedural violations, or pressure to prioritize efficiency over safety—often act as hidden precursors to accidents. Yet without public trust, the findings of investigative bodies risk being disregarded or contested, limiting their impact on future safety improvements. This dual lens of ethics and acceptance situates the human factor not only within operational decision-making but also within the socio-cultural ecosystem in which aviation systems are embedded. Methodologically, the project employs the International Civil Aviation Organization (ICAO) ADDIE approach (Analysis, Design, Development, Implementation, Evaluation) to integrate ethical reflection into the investigative and training cycle. The Analysis phase systematically reviews Greek and international accident reports, highlighting instances where ethical considerations shaped either the causation or the outcome of investigations. The Design and Development phases employ the War Games Laboratory to create immersive simulations of ethically complex accident scenarios. Finally, the Evaluation phase measures changes in ethical awareness, decision-making behavior, and levels of public trust in investigative outcomes. Artificial intelligence (AI) and data analytics allow the detection of hidden ethical vulnerabilities in accident databases, while virtual reality simulations in the War Games Laboratory provide immersive environments for training and reflection. This alignment of ethics with smart, adaptive systems mirrors the role of smart materials in aerospace. By focusing on the Greek case study, this research demonstrates how national institutions can serve as laboratories for integrating ethics and public trust into global aviation safety practices.

Dimitrios Ziakkas, Debra Henneberry, Ioanna Lekea

Conference Proceedings

Ethics as a Human Factor in Flight Safety: Developing a Training Tool for the Prevention of Ethics-Related Aviation Accidents and Critical Incidents

The integration of emerging technologies with human factors research has reshaped the way aviation safety is understood and managed. While advances in smart materials enhance aircraft resilience by adapting to external pressures and mitigating physical risks, this study argues that the ethical dimension of human performance functions as an equally adaptive safeguard in complex socio-technical systems. By conceptualizing ethics as a human factor, this research explores how inclusive human-system integration requires not only technical robustness but also ethical resilience across individuals, organizations, and regulatory frameworks. Traditional approaches to aviation safety emphasize physiological, psychological, and cognitive dimensions, yet overlook the ethical decisions that underpin operational outcomes. Systematic analysis of aviation accidents reveals recurring ethical deviations—such as concealment of errors, tolerance of procedural violations, or organizational pressures—that directly compromise safety. Like smart materials that redistribute stress to prevent catastrophic failure, ethically resilient systems redistribute responsibility and accountability, ensuring transparency, communication, and procedural adherence. Positioning ethics as a structural layer of resilience connects the material and human dimensions of safety in a unified framework.The research employs a three-phase, mixed-methods methodology. First, accident reports and safety databases are reviewed to identify and classify ethical lapses as causal or contributory factors. Second, a conceptual model is developed that maps the pathways through which individual moral choices and organizational culture interact with technical and procedural constraints to influence safety outcomes. Third, this model informs the design of an interactive digital training tool—an e-learning platform that integrates realistic scenarios, simulations, and reflective exercises. Inclusive human-system design requires not only that aircraft adapt to stresses but also that humans and organizations adapt ethically to pressures of efficiency, hierarchy, and cultural diversity. Smart technologies and ethically resilient human systems create a synergistic model that enhances safety, prevents preventable accidents, and fosters trust in aviation as a global, inclusive enterprise.

Dimitrios Ziakkas, Debra Henneberry, Ioanna Lekea

Conference Proceedings

Moving Towards Industry 5.0: Competency-Based Training Assessment & Sector Unification

This paper outlines a structured approach for transferring Competency-Based Training and Assessment (CBTA) frameworks from aviation into industrial production environments, in support of the broader Industry 5.0 transition. A five-phase implementation strategy was developed and applied in a Greek manufacturing facility, incorporating task decomposition, digital proficiency audits, and behaviorally anchored assessments across three domains: digital competence, intercultural intelligence, and role-specific technical proficiency. Observable behaviors were evaluated using structured rubrics, allowing for performance calibration beyond traditional skill verification. Initial findings revealed marked variation in digital readiness and resistance to automation across hierarchical levels, with trust emerging as a psychological rather than cognitive barrier. Intercultural training showed limited transferability unless explicitly role-adapted. Drawing on the aviation precedent, the model demonstrated efficacy in improving coordination, safety compliance, and behavioral clarity in supervisory roles. The concept of sector unification is advanced as a method for achieving methodological interoperability across industries by aligning competency taxonomies, enhancing workforce mobility, and promoting systemic learning without compromising role specificity or operational safety.

Konstantinos Pechlivanis, Dimitrios Ziakkas, Konstantinos Akylidis

Conference Proceedings

Bioinspired Design in Additive Manufacturing: A Review of AI, Multi-Scale Strategies, and Fabrication Constraints

Bioinspired design represents a paradigm shift in engineering, drawing upon millions of years of evolutionary optimization to create advanced structures and materials. This comprehensive review examines the intersection of bioinspired design principles with additive manufacturing (AM) technologies, focusing on multi-scale strategies and the inclusion of artificial intelligence (AI) to create lightweight, efficient, and multifunctional components. We analyse key biological design principles, including hierarchical organization, lightweight efficiency, and multifunctionality, demonstrating how these can be translated into engineering solutions through AM. The review covers state-of-the-art design strategies, including lattice structures, topology optimization, generative design, and multi-scale modelling approaches, with a particular focus on the constraints imposed by fabrication processes. We examine digital tools that facilitate the translation of biological models into manufacturable designs, including computer-aided design systems and AI platforms. Current challenges in scaling, first-time-right fabrication, and complexity management are critically assessed, along with knowledge gaps in structure-property-process relationships. The outlook section presents future directions for industrial integration, emphasizing the potential for bioinspired AM to revolutionize multiple sectors, from aerospace to biomedical applications

Ramon Angosto Artigues, Andrea Fernández Martínez, Ander Reizábal López-para, Iñigo Flores Ituarte, Amirmohammad Daareyni, Santiago Muíños Landín

Conference Proceedings

Toward Pigment-Free Leather: A Structural Color Design Framework Based on Photonic Crystal Principles

The large scale use of synthetic dyes in leather finishing raises growing environmental concerns and constrains long term colour stability. This conceptual study explores pigment free structural colour for leather based on photonic crystal principles and natural examples of structural colour. By transferring these optical mechanisms to fibrous leather substrates, we propose a multilayer L0–L4 surface architecture and a set of integration routes that embed periodic or quasi ordered nanostructures onto prepared grain. The framework links optical design parameters (feature size, refractive index contrast and angular response) with human factors requirements such as visual naturalness, glare acceptability and perceived premium feel. Rather than reporting experiments, the paper offers a design first roadmap and evidence seeking strategy for developing structural colour leather as a more sustainable complement to dye based colouration.

Dehe Yao, Ruan Xiaoxue Bai

Conference Proceedings

From Concept to Construction: A Framework for Smart Building Material Innovation in South Africa

The construction industry is increasingly turning to smart materials as a response to the global demand for energy-efficient, sustainable, and cost-effective infrastructure. In South Africa, recent amendments to SANS 10400-XA have intensified the need for compliant thermal solutions in residential and commercial buildings. This paper follows a qualitative case-study approach, using the development of CemBrick’s new thermal brick, designed to replace traditional cavity wall construction while exceeding regulatory thermal performance benchmarks, as the central example. It incorporates comparative cost analysis, regional construction practices, and regulatory mapping to inform the development of a framework for future smart material applications in South Africa. The case study highlights that the thermal brick offers significant advantages over traditional cavity wall construction, including improved thermal performance, reduced project timelines, simplified labour requirements, and cost savings. Furthermore, the innovation journey exposed systemic gaps in material approval, industry adoption, and labour readiness. The findings are based on a single case study situated within a specific geographic and regulatory context (Free State, South Africa). Broader applicability of the framework may require further validation across material types, regions, and regulatory bodies. This innovation drive however extended beyond material design, involving testing protocols, market adoption hurdles, and alignment with national regulatory bodies. Building on this practical insight, the paper proposes a generalisable framework for smart material innovation in the South African built environment. The framework maps out key stages including problem identification, research and development, regulatory engagement, pilot implementation, and skills development. The aim is to guide future innovators and manufacturers, consultants, and researchers through the systemic pathways required to bring smart materials from concept to mainstream application in a developing country context. This paper contributes in bridging the gap between material science, policy, and practice, offering a blueprint for innovation ecosystems that support smart, sustainable, and scalable construction solutions in South Africa and similar markets. This paper further presents one of the first documented smart masonry case studies from South Africa, and introduces a structured innovation framework tailored to the local built environment. It bridges material science, policy, and construction practice, offering both scholarly and industry value.

Liezl Le Roux, Tascha Bremer

Conference Proceedings

Preventing Violence in Schools: A Psychoeducation Program Examining the Effects on Teachers Perceptions and Attitudes Toward Violence and Bullying

Violence is a phenomenon as old as human history and has become one of the fundamental issues threatening both societal life and individual well-being in recent years. Schools institutions in which individuals experience their first socialization processes after the family are among the environments where incidents of violence occur most frequently in modern society. In educational settings, peer bullying, defined as intentional and repetitive behaviors based on a power imbalance among children, has significant physical, psychological, social, and academic adverse effects, particularly on children and adolescents. In efforts to prevent violence and peer bullying, teachers and school counseling (SC) professionals carry substantial responsibility. The existing literature shows that studies involving teachers and other school personnel, who play a critical role in intervening in bullying incidents, are largely descriptive. Psychoeducational programs designed to modify the perceptions and attitudes necessary for effective intervention remain limited. In light of this information, the present study experimentally examined changes in the perceptions and attitudes of teachers and SC professionals regarding incidents of violence and peer bullying through the psychoeducational program titled “Preventing Violence in Schools: Where Do I Stand?”, developed by the researchers.In this study, an explanatory sequential mixed-methods design was employed. Following the collection of quantitative data addressing the research question, the results were examined using a phenomenological design, one of the qualitative research approaches. The sample consisted of 36 participants—20 school counseling (SC) professionals and 16 subject-area teachers from public schools in Istanbul, Türkiye—selected through stratified random sampling. For program evaluation, participants were assigned to two groups with distributions parallel to the SC sample. Prior to the experimental intervention, all participants completed a personal information form and the “Teacher Attitudes Toward School Bullying Scale,” developed by Yeşilyaprak and Dursun Balanuye (2012), as a pre-test measure. Following the eight-week psychoeducational program, the same scale was administered again as a post-test. Additionally, qualitative data were collected using the “Interview Form on Perceptions of Bullying and Violence,” which consisted of open-ended questions aimed at obtaining a deeper understanding of participant views.According to the results of the study, no statistically significant differences were found between pre-test and post-test scores across the subdimensions. The variables of professional seniority and age showed statistically significant positive correlations with the “harsh attitude” subdimension. When SC professionals and subject-area teachers were compared, “harsh attitude” scores differed significantly in both the pre-test and post-test, with subject-area teachers scoring higher in both measurements. The number of children participants had was positively correlated with the “indifference attitude” subdimension in both pre- and post-test assessments at a statistically significant level.Qualitative findings showed that both groups viewed bullying as a power-driven and repetitive pattern. Subject-area teachers linked gaps in prevention to systemic and administrative issues, while SC professionals emphasized limited stakeholder cooperation. Regarding intervention, teachers prioritized disciplinary procedures and coordination with the counseling service, whereas SC professionals favored child-centered and team-based consultation practices. In case analyses, both groups underscored the importance of victim safety, emotional support, collaboration, and a holistic response.

Ozlem Ozden Tunca, Alp Giray Kaya, Ayca Cikrikci, Cetin Kılıc, Havvane Sama Cicek, Turker Cevher, Esra Betul Ergul

Conference Proceedings

Smart materials from Absorbent hygiene products (AHP) waste: a model of inclusive circular economy

In recent decades, the concept of sustainability has undergone a profound transformation: from a marginal idea, it has now become a guiding principle in environmental policies and design practices. Two key milestones in this process are the Brundtland Report (1987) and the Caring for the Earth strategy (1991), which provided a global framework for sustainable living, consolidating sustainability as a guiding principle for environmental and design policies. However, the various definitions proposed by international bodies and organizations reveal a certain conceptual ambiguity, from the systemic definition put forward by the US EPA (2025), to the visions focused on responsible resource management by Greenpeace (2025), up to the United Nations 2030 Agenda (2015). In this sense, sustainability today appears as a shared but non-univocal concept.Absorbent hygiene products (AHP) represent a waste stream with a high impact in terms of volumes, management costs and raw material waste, but also characterized by a recycling experience already tested. Some industrial plants are financed in Italy currently being funded by the PNRR (National Recovery and Resilience Plan) as part of waste management and the circular economy, in Mission 2 (Green Revolution and Ecological Transition) and aim to support the construction or modernisation of innovative plants. The funds are intended to create a national network of plants that can give “true circularity” to this fraction of waste, preventing it from ending up in landfill or incineration.The market survey carried out by Legambiente and Mizzouri (2025) on extended producer responsibility (EPR) for diapers, based on over 100,000 data points derived from 502 interviewed parents, highlights both a low initial awareness of the end-of-life of AHP and of the available recycling technologies, and a significant willingness to pay more if a transparent and virtuous supply chain is guaranteed. This result underscores the importance of communication, trust in public actors, and service design in making technological recycling systems inclusive, fostering citizen participation and the valorization of secondary raw materials (SRM).This contribution describes the ongoing research project within the International PhD in Civil and Environmental Engineering (40th cycle) at the Department of Civil and Environmental Engineering of the University of Perugia, conducted in collaboration with Gesenu S.p.A.The proposed case study concerns the new AHP plant of Gesenu at the Ponte Rio (Perugia) waste management hub, funded by the NRRP and designed for a capacity of 5,000 tonnes per year (Pera, 2025). The research analyses AHP collection systems at national and international levels, evaluating dedicated and accessible configurations for nurseries, families, older adults and people with disabilities, as well as the role of municipalities as mediators between the plant, citizens and producers.The research delves into the AHP treatment process, with particular attention to the recovery of SRM such as plastics and cellulose, and to the preliminary assessment of environmental and economic performance compared to traditional disposal scenarios such as landfilling and incineration. On the design side, a product concept is developed starting from the SRM obtained from AHP recycling, exploring applications that can make the material and emotional return of citizens’ separate collection behaviour tangible.In order to propose innovative solutions for collection systems, plant technologies and SRM outputs, several national and international case studies are analysed through comparative sheets, useful both for mapping the state of the art and as input to enhance the research case study. Among these, the RE-CIG project, launched in 2019, demonstrates how a complex urban waste stream - cigarette butts - can be transformed into SRM through an integrated approach combining technological innovation, social awareness-raising and institutional collaboration.In conclusion, the research aims to demonstrate the environmental, economic and social validity of Gesenu’s AHP plant, proposing an integrated model in which smart materials derived from recycling converge into a replicable circular economy ecosystem, contributing to sustainable innovation and social inclusion through responsible design practices and circular supply chains.

Benedetta Terenzi, Giovanna Binetti

Conference Proceedings

Identification of Preferred Relaxation and Sleeping Postures in Highly Automated Vehicles

The advancement of automated driving technologies to SAE-Level 4 introduces new opportunities for optimizing vehicle interiors for relaxation and sleep. As the driver is no longer required to permanently monitor the driving process, the in-vehicle time can be repurposed for rest and recovery, especially on long-distance journeys. Although the automated driving system in SAE-L4 independently carries out the driving task, manual driving will still be necessary. Therefore, the cockpit layout of these vehicles must still enable safe manual driving. Current vehicle interiors, and especially driver cockpits, are not designed for relaxation and sleeping. Adaptations of the vehicle interior creating an appropriate environment are needed to relax and to sleep in a small space such as a vehicle’s interior.In this contribution, preferred relaxing and sleeping postures in vehicles are identified to derive comprehensive ergonomic and safety-related requirements for the design of highly automated vehicles. The goal is to establish interior concepts that not only provide comfort but also meet safety standards and accommodate varied user needs. This includes a comprehensive literature review, expert interviews, observational studies conducted in a recliner within a vehicle environment, and the analysis of existing solutions for relaxation and sleep in transportation modes. Additionally, a biomechanical simulation of posture scenarios using RAMSIS simulation tool is employed to visualize sleeping postures within vehicle interiors. Particular attention is paid to the conflict between ergonomic comfort and safety requirements, especially in the context of take-over situations, where users may need to resume vehicle control under certain edge cases.The findings indicate that relaxation and sleep postures are significantly influenced by ergonomic design, seat configurations, and spatial constraints within the vehicle. Key ergonomic requirements for optimal comfort include support for the head, neck, lower back, and legs, as well as adjustable seating options to accommodate side, back, and reclining positions. Special emphasis is placed on leg support and adjustable footrests to maintain comfort and reduce fatigue during extended periods of relaxation or sleep. Furthermore, the study reveals significant discrepancies between perceived and actual ergonomic effectiveness of current seat designs, especially in reclining configurations.Based on the results, specific design recommendations are proposed to enhance sleeping comfort in SAE-Level 4 vehicles. These include optimized seat adjustability, improved head, neck, and leg support, modular seat configurations that support dynamic posture changes, as well as enhanced safety mechanisms. The contribution concludes that addressing these requirements is critical to making sleep a viable and comfortable option during automated driving, ultimately contributing to enhanced well-being and travel experience for passengers.Acknowledgements: This research was supported by Federal Ministry for Economic Affairs and Climate Action in the national research project SALSA.

Miriam Schäffer, Souren Kosejian, Marat Nikita Pak, Wolfram Remlinger

Conference Proceedings

Designing User Interfaces for Semi-Autonomous Tram Systems: Human–Machine Interaction, Future Scenarios, and the Transition Toward Automated Mobility

The integration of semi-autonomous systems in public transport introduces new design challenges related to user experience, human–machine interaction, and situational awareness. This research, conducted within the Master’s program in Advanced Sustainable Design at the University of Florence in collaboration with an industry leader in autonomous tram technology, explores how user interfaces (UIs) can effectively mediate between automation and human control in complex operational contexts. Using the semi-autonomous tram line of Florence as a case study, the project investigates present issues and future scenarios for interface evolution in public transportation.Students were divided into project groups and engaged in a comprehensive research process combining design thinking and human-centered design approaches. The methodology included a review of the scientific literature, benchmarking of international case studies, and extensive on-field investigation. Empirical data were collected through direct observation, interviews with drivers, and anonymous questionnaires aimed at identifying recurring challenges, user needs, and perceptions of trust and safety in interactions with semi-autonomous systems. This multi-layered analysis enabled a critical comparison between theoretical frameworks and operational realities, revealing gaps and opportunities for UI innovation. The collected evidence was organized into categories of disruptions frequently observed in semi-autonomous scenarios, including issues related to attention management, information overload, and the adaptation of human skills to automated contexts.A parallel line of research explored the evolving role of the driver, focusing on ergonomic factors, cognitive load, stress management, and the need for continuous monitoring of attention and physical condition. Findings demonstrate that the effectiveness of semi-autonomous mobility systems depends largely on the quality of human–machine interaction and the system’s ability to support the operator during high-complexity events. Multimodal feedback—visual, auditory, and tactile—proved to be essential for maintaining situational awareness and reducing reaction time.Building on these insights, the project proposed several future-oriented interface solutions. These included adaptive dashboards capable of dynamically reorganizing information, multimodal alert systems designed to mitigate cognitive overload, and AI-driven virtual assistants to support drivers in diagnosing anomalies, prioritizing warnings, and managing emergency procedures. These speculative scenarios position UIs as cooperative partners that can enhance transparency, reliability, and trust while ensuring meaningful human oversight.Looking ahead, the study highlights the potential of emerging technologies such as Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR) to improve information delivery and skill development. AR overlays within the driver’s field of view could present contextual information—track status, obstacle alerts, route variations—without increasing distraction, while immersive technologies could support training and simulation.Ultimately, this research demonstrates the value of design-driven methodologies in shaping next-generation UIs for public transport systems. By integrating human factors, emerging technologies, and speculative design approaches, the project outlines how adaptive, multimodal, and intelligent interfaces can enhance safety, efficiency, and comfort while guiding the cultural and professional transition toward autonomous mobility.

Laura Giraldi, Elisabetta Benelli, Francesca Morelli

Conference Proceedings

Human-centered approach for the development of the housing for an ultrasound probe

The development of the housing for an ultrasound probe is a challenging aspect of design, as it must combine functionality, ergonomics, and usability for the medical device. This project shows how the development of the housing for an ultrasound probe adopts a human-centered approach, basing the design on the needs of the end user, particularly for those working in a healthcare institution, where the high-pressure environment is a fundamental aspect to consider.For this reason, it is relevant to involve the final user since the preliminary steps of development, thought iterative and interactive test cycles, for the evaluation of ergonomics aspects, like the weight, grip and shape, and of usability features like graphics, symbols and reference on the housing. Housing probes include minor but impactful features that are not arbitrary choices of design, but they are the output of studies on the behavior and activities conducted by the physicians, promoting precision and reducing the risk of injuries. Attention to details is crucial to reduce the mental workload and enhance usability.These aspects must match mandatory requirements, for example biocompatibility in material selection, and they need to be inserted into a structure that allows the device to achieve a good result in terms of performance, as well as being easy and comfortable for the user.In conclusion, the development of the housing for an ultrasound probe requires to match regulatory, performance and user-based requirements. Human centered approach consents to achieve harmony between these aspects, emphasizing the importance of user feedback to achieve a higher level of satisfaction and simplify workflows, as well as improving comfort during the use of diagnostic medical devices.

Marianna Oliverio, Enrico Trallori, Matteo Lapi

Conference Proceedings

The Mirror Effect: How Intelligent Systems Create Emotional Connection Through Language Reflection

Conversational AI systems are increasingly described as empathetic and emotionally attuned, suggesting users treat AI as social agents capable of emotional reciprocity. While this framing has informed socially interactive system design, it risks anthropomorphizing AI beyond its computational capacities. The mechanisms by which conversational AI generates a sense of connection remain poorly understood, with critical implications for trust calibration and ethical deployment. This study introduces the Mirror Effect: the hypothesis that perceived AI empathy emerges from grammatical reflection rather than genuine understanding. Analysis of 76,497 turn pairs from EmpatheticDialogues quantified linguistic mirroring across lexical, semantic, syntactic, and stylistic dimensions. Results revealed a striking dissociation: minimal lexical overlap (4.8%) while exhibiting strong syntactic alignment (67.2%), a 14-fold difference. Despite using almost entirely different vocabulary, systems consistently mirrored users' grammatical structures. Over half (53.4%) of exchanges showed syntactic alignment exceeding 70%, demonstrating systematic structural reflection. These findings reconceptualize AI empathy as projection through grammatical mirroring: users encounter their own linguistic architecture reflected back and interpret that familiarity as mutual understanding. The AI functions as an "invisible mirror", users attribute structural familiarity to AI understanding rather than recognizing their own patterns reflected back. Practically, findings suggest prioritizing syntactic alignment while maintaining lexical diversity. Ethically, the automaticity of syntactic mirroring necessitates transparency about engineered connection mechanisms. As conversational AI proliferates in therapy, companionship, and education, understanding that users engage with augmented reflections of themselves becomes essential for responsible development and informed consent.

Anamaria Acevedo Diaz, Ancuta Margondai, Valentina Ezcurra, Sara Willox, Sophia Fernanda Sakakibara Olgini Capello, Mustapha Mouloua

Conference Proceedings

Influence of operator physical characteristics on compliance with collaborative robot

This work investigates the influence of human physical characteristics on behavioural compliance during human–robot collaborative tasks. Using data derived from a collaborative robot experiment published in Behaviour-Based Biometrics for Continuous User Authentication to Industrial Collaborative Robots, participant attributes such as height, gender, and handedness were analyzed against the frequency of non-compliance events. The analysis combined statistical correlation metrics with machine learning-based feature importance estimators to provide both linear and nonlinear perspectives. Pearson, Spearman, and Kendall correlations were computed to quantify monotonic relationships, while model-driven approaches including Random Forest, Gradient Boosting, XGBoost, Mutual Information, and SHAP were used to capture higher-order dependencies. The results show that height exhibits the strongest nonlinear influence on operator compliance, indicating that anthropometric factors substantially affect user behaviour and task adherence. In contrast, gender and handedness were found to contribute moderately, primarily through secondary interaction effects. These findings emphasize the need to account for physical characteristics when designing adaptive and personalized control interfaces for collaborative robots.

Sandi Baressi Šegota, Darko Etinger, Nikola Tankovic, Romeo Šajina, Vedran Mrzljak, Ivan Lorencin

Conference Proceedings

Promoting Pro-Environmental Behavior through Destructive Experiences in Virtual Reality: Design and Implementation of the VR Experience

In recent years, the worsening of environmental issues such as global warming and resource depletion has highlighted the growing importance of individual pro-environmental behavior (PEB). However, everyday actions such as waste sorting, energy saving, and water conservation often fail to translate into consistent practice. Therefore, new external approaches are required to motivate such behaviors. Recent studies suggest that positive emotions such as enjoyment and a sense of achievement can encourage PEB. This study focused on positive emotions such as exhilaration and achievement.In this research, we attempted to promote PEB by providing an exhilarating and rewarding experience through destructive actions in virtual reality (VR). Destructive behavior is often characterized by strong physical and sensory stimulation and has the potential to evoke feelings of exhilaration and satisfaction. However, in real-world contexts it is often avoided because it involves danger and is socially inappropriate. In contrast, VR makes it possible to safely engage in such experiences without inducing guilt, allowing for the design of interactions that effectively elicit only positive emotions. By leveraging these characteristics, VR-based destruction experiences can offer new opportunities for behavioral change. Specifically, we developed a destruction-based task using two-choice quiz questions related to environmental issues. In this task, they answer by destroying with a handheld stick the panel corresponding to the option they believe to be correct, which is presented in the VR environment. When the correct option is chosen, the panel shatter dramatically with visual effects, accompanied by exhilarating sound effects. This design is intended to reinforce the sense of exhilaration and achievement through both visual and auditory stimulation.The experiment was conducted with 10 university students, divided into a test group with the destruction experience (n = 5) and a control group without the destruction experience (n = 5). Although both groups answered the same questions, the method of responding differed, which served as the basis for comparison. The measurement items included the Pro-Environmental Behavior Test (PEBT) to evaluate pro-environmental behavioral implementation, the Multiple Mood Scale (MMS) to assess emotional states, and a post-experience questionnaire. The questionnaire focused on key factors contributing to a sense of exhilaration, and participants’ overall impressions of the experience were also collected through free descriptions.As a result of the experiment, the test group scored higher on the PEBT compared to the control group, indicating that pro-environmental behavior was more strongly promoted. In addition, an increase in “active pleasure” was observed in the MMS, suggesting that the destruction experience significantly induced positive emotions. Free responses also included several positive comments such as “I felt refreshed” and “The destruction was fun.” These results suggest that VR-based destruction experiences can serve as an effective method for promoting pro-environmental behavior through positive emotions. Although this study was limited by the small number of participants, the clear emotional effects and changes in behavior observed even in a small-scale experiment are noteworthy. Future research should increase the sample size to examine statistical validity and further clarify the semantic relationship between destruction experiences and pro-environmental behavior.

Shunya Tanaka, Wataru Ogomori, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda

Conference Proceedings

Designing User-Centered Exercise Science Education: Integrating HCI Principles to Address Fitness Technology Disparities

Despite explosive growth in the fitness technology sector ($257 billion globally in 2024), digital health and fitness technologies systematically exclude older adults, individuals with disabilities, racial and ethnic minorities, and lower socioeconomic populations. This paper presents a curriculum framework integrating Human-Computer Interaction (HCI) principles into exercise science education to prepare professionals who can evaluate, select, and advocate for accessible, equitable fitness technologies. Drawing on Misericordia University's newly launched Exercise Science program, the framework addresses critical gaps at the intersection of technology, health equity, and professional education through four key domains: user research and persona development; usability testing methodologies; accessibility evaluation; and cultural competency in technology. This model positions exercise science graduates as essential intermediaries between technology developers and underserved populations, transforming their role from passive technology consumers to active advocates for inclusive design and health equity.

Tiffany Mulally

Conference Proceedings

Integrating uncertainty-aware stress detection with spoken dialogue-based interaction for human-centered stress management

Stress is a major factor influencing both mental and physical health, contributing to anxiety, depression, and cardiovascular disease. Traditional stress management tools, such as meditation apps and therapy, often depend on self-reports or fixed schedules, limiting their effectiveness in real-time situations. Physiological signals, such as heart rate, respiration rate, electrodermal activity, and inter-beat intervals, provide objective and non-invasive markers of stress that cannot be consciously manipulated, offering a reliable alternative. However, stress detection using these signals is complicated by inter-individual variability, sensor noise, and overlapping physiological patterns. Therefore, for building reliable and trustworthy stress management systems, it is essential to quantify the uncertainty in the stress predictions and to solicit assistance from the human user to resolve the uncertainty. This results in a human-centered approach for stress management. This work proposes a system that integrates physiological computing and machine learning with dialogue systems. Stress detection is performed using random forest classifiers and a convolutional neural network trained on the publicly available WESAD dataset. Feature extraction from electrodermal activity and inter-beat intervals enables classification of stress versus baseline states. To estimate uncertainty in the predictions, entropy-based measures are applied to the random forest and Monte Carlo dropout is used for the convolutional neural network. Predictions and their confidence scores are fed into a dialogue manager, which tailors stress management interventions accordingly. High-confidence predictions trigger context-appropriate stress recovery strategies, such as guided breathing exercises, while low-confidence cases prompt clarifying dialogue, allowing the user to confirm or correct the system prediction. Experiments demonstrated that a 60-second window provided the best trade-off between temporal resolution and classification accuracy, with the random forest achieving 76% accuracy and the convolutional neural network achieving 75%. Uncertainty quantification helped to identify low-confidence predictions and prevent inappropriate interventions. The system actively integrates people into the stress management cycle by using a dialogue manager to combine tailored, stress-level-based responses with a fallback to user input for low-confidence scenarios. The proposed system has applications in healthcare, especially in personal mental health management, particularly in contexts where immediate and adaptive stress support is required, such as high-pressure jobs or remote healthcare settings.

Prachi Sheth, Jordan Schneider, Teena Hassan

Conference Proceedings

Human-Centred Classification of Remote Operation Intervention Scenarios for Automated Vehicles

The deployment of automated vehicles (AVs) offers substantial societal benefits but faces significant challenges, particularly in complex urban environments. Remote operations (ROs) enabled safety interventions serve as a critical intermediary, allowing human operators to intervene when AVs encounter limitations. However, to inform RO workstation design and understand human intervention capabilities, real-world scenario data is critical. To address this gap, we conducted semi-structured interviews with 13 local safety experts at the Birmingham National Exhibition Centre (NEC), UK, resulting in a catalogue of 105 functional scenarios. We identified prevalent scenario types, AV-related challenges, and scenario complexity. These findings inform RO workstation and human machine interface (HMI) design and highlight the need for real-world scenario generation to support RO capability assessment. This study contributes to a framework for enhancing human-AV interactions, understanding RO safety requirements, and advancing ROs.

Marko Medojevic, Adam Bogg, Stewart Birrell, Kevin Vincent, Rav Babbra

Conference Proceedings

Morphing Systems: Analysing the Influence of Different Parameters on the Perception of Morphing

Gestalt-changing products allow customers to tailor a product to their individual needs or enable the product to adapt to them. While the initial and target states of such changes are often clear, the kind of change and how it is perceived by the user are often unclear but essential. Morphing is a special form of gestalt change, in which the transformation is perceived as a smooth change over time (Rommel et al. 2025). The defined characteristics help to categorize morphing and allow a comparison to other types of gestalt changes. At the same time, different parameters were identified which allow a high degree of variety. This paper analyses these parameters in detail to determine how they influence the perception of a gestalt change as morphing. To investigate these parameters, an online survey was conducted with n = 103 participants. In the survey, 11 different gestalt changes were presented and evaluated. Two of these served as references: one representing a purely morphing change and the other a purely distinct change. According to Seeger (2005), a product’s gestalt can be divided into four subgestalts: layout, shape, colour and surface and graphic. To assess whether a change in a single subgestalt is perceived as morphing, and to identify which subgestalt is most dominant in shaping this perception, four animations were designed in which only one subgestalt changed. Additional models were included to examine how combinations of smooth and erratic transitions affect the perception of a gestalt change as morphing. The study also explores the impact of transition speed and animation curves. After viewing each animation, participants completed a questionnaire assessing both, the overall perception of the gestalt change and the specific morphing characteristics observed during the transition.The results of the online survey provide a basis for distinguishing morphing from other types of gestalt changes. More importantly, they suggest morphing should be understood as a spectrum, where specific parameters can enhance or diminish the perception of a change as morphing. The data also shows that certain subgestalts have a stronger influence than others. Specifically changes in layout have a high impact on a change being perceived as morphing. Moreover, it can be seen that short changing times, combining distinct and morphing changes and certain animation curves can disrupt or even break the perception of morphing entirely. Finally, changes in specific subgestalts, like the layout, more strongly contribute to perceiving the resulting gestalt as a distinctly new one.The article provides reliable statements on the possible parameter spectrum for morphing. Based on these results, further investigations are possible, especially in comparison to other types of gestalt change. Rommel et al. 2025 Rommel, Pascal; Holder, Daniel; Schmid, Peter; Maier, Thomas: Morphing Systems: Defining the Characteristics of Morphing in Modern Product Design. In: Stuttgarter Symposium für Produktentwicklung SSP 2025: Tagungsband zur Konferenz, 2025, p.199-209Seeger 2005 Seeger, Hartmut: Design technischer Produkte, Produktprogramme und -systeme: Industrial Design Engineering. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005

Pascal Rommel, Enzo Castagna, Daniel Holder, Thomas Maier

Conference Proceedings

A Synergistic, Non-Invasive Sensing-Fusion Approach for Predictive Kinetosis Monitoring in Autonomous Vehicles

The coming of autonomous vehicles promises a "passenger economy," a vision jeopardized by the challenge of kinetosis (motion sickness). Effective mitigation requires non-invasive, predictive monitoring, yet current methods are impractical. This paper presents a robust methodology that validates a synergistic fusion of thermal and visible-light imaging as a reliable respiratory biomarker. Our system employs a thermal camera to track temperature differentials at the nostrils and an RGB camera to monitor thoraco-abdominal movements. We introduce a real-time signal processing pipeline featuring: (1) dynamic, multi-modal region-of-interest tracking, (2) independent signal "activity gating" to reject noise, and (3) a temporal peak-fusion algorithm to compute a single, robust breathing rate. The primary contribution is the demonstration of this system's technical feasibility and resilience to real-world failure modes. In a pilot study, we demonstrate high accuracy against a ground-truth metric and, crucially, show the system maintains a stable output during facial and torso occlusions that would cause single-modality systems to fail. This robust, non-invasive system represents an important technical step toward truly human-centric autonomous vehicles such as the C2CBridge Vehicle.

Philipp Román, Eva Maria Knoch

Conference Proceedings

Do Not Adjust Your Set! How a Visual Alert Reduced Unnecessary Human Intervention in an Automated Vehicle

Human remote operators, teaming with Automated Vehicles (AV), will need to be provided information from the AV to make decisions on how, or when, to intervene in the AV operations. As an extension to research into how many AVs an individual can successfully monitor, the authors designed and implemented a human machine interface (HMI) that provided key information on the probability that an AV might need an intervention from a remote operator. A key element of that interface was the provision of feedback indicating if a vehicle was stationary, provided in the form of a timer, and a visual alert given 10s after the vehicle came to a halt. An experiment was conducted into the efficacy of this visual alert, by on occasion removing it from use. It was expected that the absence of the visual alert would lead to more incidents where a remote operator missed a requirement to intervene. However, the results indicated that in the absence of the alert the remote operator was more likely to intervene. This paper examines how elements of the HMI design affected the participants decision to intervene in AV operations, and concludes that by offering transparent system-state feedback, the HMI effectively counters the innate psychological pressure to act, reassuring the operator that inaction can be an appropriate and system-approved response.

Adam Bogg, Stewart Birrell

Conference Proceedings

Algorithmic Personalisation Versus Informational Diversity. The Instagram User’s Perception

The contemporary information ecosystem, dominated by social digital platforms, has undergone a major transformation in how users access and consume content, largely due to the growing integration of algorithms. These computational systems act as gatekeepers that filter and reorganise information according to logics that anticipate and shape user preferences. Although algorithmic personalisation offers convenience, it raises significant ethical and democratic concerns regarding the plurality of voices and free access to information. This study examines the guiding question: “What perceptions do Instagram users demonstrate about the relationship between algorithmic personalisation and information diversity?” The objective is to evaluate users’ levels of awareness and criticism regarding the impact of algorithms on news consumption, contributing to a broader understanding of how automated systems structure information flows and influence access to diverse perspectives. A mixed-methods approach was employed, combining a questionnaire (n=114 valid responses) and semi-structured interviews (n=11). This design captures how users perceive algorithmic influence on their informational experience and the degree to which they feel their informational freedom is affected. Findings reveal a central paradox: although users acknowledge algorithmic personalisation as part of their everyday digital experience, they demonstrate limited understanding of its broader consequences for information diversity and the potential erosion of pluralism. Despite recognising the influence of their interactions on the content they receive, their critical comprehension remains superficial. The study contributes to human–computer convergence research by demonstrating how user behavior is shaped by systems operating under technological monopoly and centralised control, constraining autonomy and challenging the foundational principles of transparency and agency in human–computer interaction.

Gabi Araujo, Andreia Pinto De Sousa

Conference Proceedings

Neuroergonomic and Neurodiverse Revaluation of VR, AR, and Traditional Drone Control Systems for Equitable, Therapeutic, and Inclusive Operation

The growing use of small Unmanned Aerial Systems (sUAS) extends beyond industry to therapeutic and recreational applications for neurodiverse individuals. Yet, poorly optimized interfaces can heighten stress, cognitive overload, and social alienation. This study compares Virtual Reality (VR), Augmented Reality (AR), and traditional physical controllers to examine their effects on cognitive workload, task performance, and emotional well-being among individuals with ADHD, Autism, and Dyslexia. Using EEG to assess neural activity and behavioural metrics to evaluate accuracy and task completion, results reveal distinct cognitive and emotional responses. VR enhanced immersion but increased cognitive strain, particularly for dyslexic users; AR balanced engagement but posed navigation challenges for autistic participants; and traditional controllers provided stable, low-stress performance. Findings highlight the need for cognitively adaptive, equitable sUAS interfaces that integrate real-time physiological feedback to reduce mental strain, enhance accessibility, and harness the therapeutic potential of drone technologies for neurodiverse populations.

Suvipra Singh, Charlotte Geary

Conference Proceedings

Assessing the Development of Professionalism in Teacher Candidates through Mixed Reality

Mixed Reality Simulations (MRS), are evolving, creating potential for improved teacher training. By creating scenarios that immerse learners in real-time teaching situations that would otherwise not be possible, such as a virtual Individualized Education Plan (IEP) meeting, the educational technology transforms teaching and learning and can improve teacher preparation for special education teacher candidates. A recent survey indicates the use of MRS was able to close the preservice to veteran teacher practice gap across several indicators of teacher professionalism.

Roberta Yeager, Colleen Duffy

Conference Proceedings

A Unified Multimodal Pipeline for Luxembourgish Language Learning: Curriculum-Grounded Retrieval and LAM-Driven Interaction

We introduce a unified multimodal system that transforms the official INL Luxembourgish textbook into an interactive, AI-driven tutoring environment. The work combines two complementary components: (1) a full pipeline for digitizing, structuring, and retrieving textbook exercises, and (2) a Large Action Model (LAM)-based interaction layer enabling an LLM tutor to surface relevant visuals dynamically during conversation.The pipeline begins with a semi-automated exercise extraction stage, where textbook pages are processed through a computer vision and GPT-4.1 vision–assisted workflow to isolate individual exercises, followed by targeted manual correction when needed. These extracted images are then passed through an OCR and cleanup stage, segmented into coherent units, enriched with metadata (chapter, theme, exercise type), and embedded into a vector store. The result is a structured and searchable curriculum-grounded knowledge base.On top of this foundation, the Image Retrieval Tool, implemented through LangGraph and OpenAI function calling, enables the tutor agent to fetch pedagogically aligned visuals based on ongoing dialogue. The system fuses text generation with image retrieval, allowing the tutor to present exercises, illustrations, and contextually relevant content directly within the learner interface. This architecture ensures that visuals appear naturally during tutoring sessions without manual selection or preloading.Evaluation demonstrates that the retrieval mechanism consistently returns accurate, relevant images aligned with the student’s topic of study. Latency analysis indicates that performance bottlenecks arise mainly from LLM generation rather than retrieval or rendering. User perception studies confirm improved clarity, engagement, and trust when multimodal elements are integrated into the learning interaction.Together, the merged system offers a practical blueprint for curriculum-grounded, multimodal language learning and highlights future directions such as automated dataset scaling, richer metadata structuring, and interactive exercise formats built on top of the existing pipeline.

Hedi Tebourbi, Sana Nouzri, Piotr Kluczynski, Yazan Mualla, Abdeljalil Abbas- Turki

Conference Proceedings

Emotional Engagement and Well-Being in Japanese Households through aibo as a Domestic Companion

Rapid population aging is reshaping household structures, and long-standing family patterns are shifting. As extended and nuclear families become less common, single-person households are steadily increasing, reducing opportunities for stable emotional support in daily life. In this changing environment, interest has grown in robot pets that offer emotional value with minimal caregiving demands. Caring for biological pets requires daily management and long-term responsibility—conditions are often challenging for individuals living alone. This study examines these dynamics within Japan, where domestic use of social robots is becoming increasingly visible.Sony’s aibo is an advanced home companion robot equipped with gaze-following, speech recognition, posture changes, and adaptive learning algorithms. These capabilities enable autonomous, development-like behaviors that support experiences of bonding and mutual responsiveness. However, little is known about how aibo supports emotional engagement and meaning-making in everyday domestic contexts, as existing Human–Robot Interaction (HRI) research has focused primarily on healthcare and institutional settings.This study investigates how Japanese aibo owners incorporate the robot into their daily routines and how they experience it as a “partner” or “virtual family member.” Semi-structured interviews and participant observation were conducted with active owners, with analytical focus on interactive behaviors, emotional responses, subjective well-being, and participation in owner communities.Findings indicate that many owners perceive aibo as an entity that “needs them” and “responds to their care,” generating a strong sense of emotional reciprocity. Growth algorithms and autonomous actions provide a tangible feeling that one’s involvement shapes the robot’s development, contributing to purpose, enjoyment, and everyday emotional stability. Aibo also functions as a mediating object that facilitates human–human connection.Based on these insights, three human-centered design implications are proposed: behavior patterns that sustain long-term emotional engagement, interaction design that integrates naturally into everyday experience while minimizing caregiving load, and social feedback structures that support family-like relational bonding. These findings highlight aibo’s potential as a domestic companion that enriches well-being in evolving family environments.

Yuka Miyazawa, Osamu Yoshie

Conference Proceedings

Interactive Driving Turing Test with Think-Aloud Protocol: How Realistic Are Behavioural Driver Models?

Driver models are essential for virtual safety assessments of automated vehicles. This study evaluates the realism of the i4Driving model, a behavioural driver model designed to emulate human-like driving, using an interactive driving Turing test combined with a think-aloud protocol in connected driving simulators. Thirty participants interacted with either a human-controlled vehicle or the i4Driving model across three motorway scenarios and rated realism, predictability, safety, and aggressiveness. Results showed that the i4Driving model was perceived as less realistic and predictable than human drivers (p < 0.001), yet participants could not reliably distinguish between the two (classification accuracy = 0.673). Think-aloud analysis revealed specific shortcomings, such as unrealistic merging and speed adaptation, alongside instances of naturalistic behaviour. These findings highlight the need for improvements in tactical decision-making and demonstrate the value of combining subjective ratings with qualitative insights for refining driver models.

Tianyu Tang, Tobias Zillmann, Johan Olstam, Christer Ahlström, Fredrik Johansson, Wouter Schakel, Klaus Bengler

Conference Proceedings

Intercultural Human-Centered AI for Automotive Systems: Bridging ASPICE Processes and Intelligent Human Systems Integration

The integration of Artificial Intelligence into safety-critical automotive systems demands approaches that combine technical rigor with cultural and human-centred sensitivity. While Automotive SPICE (ASPICE) ensures structured engineering practices, it lacks explicit guidance on integrating intercultural human factors and intelligent AI-driven support. This paper proposes a framework for Intercultural Human-Centred AI that bridges ASPICE-based practices with intelligent human systems integration, ensuring both compliance and adaptability in global engineering contexts. Three core challenges are addressed. First, AI-driven assessments can produce inconsistent outputs, which can be addressed through structured, cache-augmented generation pipelines combined with explainable decision layers, demonstrating how consistency and auditability can be achieved in large-scale assessments. Second, engineering processes are embedded in diverse cultural contexts, requiring design principles for intercultural user interface design that support inclusive AI interaction across geographically distributed teams. Third, intelligent assistant systems are positioned as partners rather than replacements for assessors through deterministic workflow architectures that enhance decision-making while maintaining human responsibility. This paper combines computational modelling with real-world deployment evidence. Developed by an experienced ASPICE assessor, the system demonstrates how process assessments can be augmented with AI-based retrieval and reasoning. A prototype was deployed to 12 domain experts who processed 424 queries over five days, generating 218,123 tokens with high perceived usefulness ratings and strong adoption intent. This work provides both methodological foundation and practical tools for organizations integrating people and intelligent systems effectively, with relevance beyond automotive to all regulated industries requiring compliance, cultural inclusivity, and human-AI collaboration.

Rüdiger Heimgärtner

Conference Proceedings

Visual Feedback for In-Car Voice Assistants

This study presents ambient visual feedback for automotive voice assistants to enhance driver interaction and safety through peripheral visual cues. A user interface prototype incorporating ambient colour feedback was evaluated through an online survey (N=151 from 28 countries) and a lab-based study (N=24, Belgium). Survey participants strongly preferred smartphone-integrated user interfaces, such as Android Auto and Apple CarPlay, over built-in manufacturer systems, indicating a desire for consistent digital ecosystems. In the lab, 18 participants favoured the ambient feedback over conventional or no visual feedback, citing improved visibility and assistance. Statistical analysis revealed that ambient feedback improved user visibility, position, and usefulness ratings. However, the need for auditory cues remained evident, confirming the importance of multimodal feedback. These findings suggest that ambient visual feedback is a promising direction for improving the usability of voice assistants and driver satisfaction while supporting safe in-vehicle interaction.

Thomas Marinissen, Pavlo Bazilinskyy

Conference Proceedings

Beyond Ridership Counts: What Trip Requests Reveal About Urban Mobility

Using data provided by public transport associations, new opportunities arise today to investigate passenger demand and user behavior in public transport. Of particular interest is information about the locations and times at which passengers use – or would like to use – public transport services. By analyzing the requests submitted to the electronic timetable information system (EFA), conclusions can be drawn regarding passenger demand and user behavior. Although electronically submitted requests represent only a portion of actual users, they can serve as an indicator for real passenger demand. In this paper, a methodology is developed for analyzing EFA request statistics and comparing them with real passenger volumes. The aim is to assess the informative value of the request data and to carry out an exemplary analysis and interpretation of these data.

Waldemar Titov, Thomas Schlegel

Conference Proceedings

AI and Automotive Design: The Ferrari Case as a Model of Human–Machine Co-Creation

Contemporary automotive design operates at the confluence of aesthetic culture, artisanal heritage, and technological innovation. The rapid evolution of digital tools and the advent of artificial intelligence (AI) have significantly reconfigured the very notion of industrial creativity, transforming the representational, simulation-based, and decision-making processes that underpin vehicular conception. In this context, design transcends its traditional aesthetic and functional dimensions to emerge as a complex cognitive activity, one that intertwines human intuition with the computational capabilities of intelligent systems.This study investigates how Ferrari—an emblematic brand within Italian design and global automotive culture—integrates AI-driven methodologies into its creative workflow while safeguarding the emotional, artisanal, and identity-defining components that constitute its distinctive design language. The Ferrari Design Center serves as a paradigmatic setting for examining the negotiation between tradition and innovation, specifically between the perceptual sensitivity of the designer and the analytical rigor of algorithmic systems.Through a qualitative analysis of the organizational and methodological structure of the Ferrari Design Center and, prospectively, through a direct interview with Chief Design Officer Flavio Manzoni, the research explores AI not as a substitute for human creativity, but as an instrument of cognitive augmentation. Rather than assessing the autonomous design capabilities of AI, the study seeks to understand how such systems can broaden the perceptual, speculative, and imaginative capacities of designers, thereby enabling the exploration of multidimensional and highly complex design scenarios.Within this framework, AI is conceptualized as a platform for human–machine co-creation, capable of processing extensive aesthetic, ergonomic, and aerodynamic datasets and translating them into formal and linguistic propositions aligned with Ferrari’s identity. The interaction between designer and algorithm becomes a heuristic dialogue in which the machine generates variations, correlations, and emergent patterns that the human agent interprets through cultural, sensory, and emotional criteria. This synergistic dynamic accelerates development processes, enhances decision-making, and fosters greater sustainability, all while preserving the emotional and symbolic qualities intrinsic to the brand.From a theoretical perspective, the paper advances an original methodological framework grounded in the principles of cognitive ergonomics, explainability, and augmented creativity. This framework aims to articulate how human–AI collaboration can be structured, evaluated, and optimized within industrial design practice. It contributes to the international discourse on Human–AI Interaction by offering a human-centered yet technologically progressive interpretation of contemporary creative processes.In conclusion, the study positions the Ferrari case as a distinctive model of AI integration within design practices characterized by strong symbolic, cultural, and aesthetic significance. It argues that when AI is conceived as a cognitive partner rather than an autonomous creative agent, it can support—and meaningfully extend—human intuition and artistic judgment without displacing their primacy. Within this perspective, the human designer remains central, guiding and interpreting algorithmic output through aesthetic sensibility, cultural competence, and emotional intelligence. AI thus emerges as a form of collaborative intelligence, capable of amplifying human design sensibility and enabling an unprecedented synthesis of emotion, function, and technology, in which the artistic dimension continues to originate from human creativity while being reinterpreted and enriched through novel cognitive and technological paradigms.

Elisabetta Benelli, Laura Giraldi, Francesca Filippi

Conference Proceedings

Designing Multidimensional Digital Purchase Journeys: CASCADE and CASMOT Conceptual Models

This discussion paper synthesizes insights from three consecutive nationwide online surveys in Japan (2022–2024) to characterize multidimensional, context adaptive digital purchase journeys that require effective human–system integration (HSI) across touchpoints. Grounded in descriptive evidence, we articulate two complementary conceptual models—CASCADE for experience design and CASMOT for behavioral measurement. We aim to clarify how value logics (e.g., assurance, economic/points, convenience/speed, empathy/story) coexist within individuals and switch by context, and to derive conceptual models that make such switching and multi track progression visible to both analysis and design. Design/methodology: From 2022 to 2024, we conducted nationwide online surveys of 2,900–4,350 respondents aged 20–69, covering 29–30 product groups across 11–13 categories. The questionnaire captured digital channels at awareness, comparison, purchase, and post purchase; payment and loyalty point usage; satisfaction and customer support experiences. Modules on webrooming/showrooming and cashless adoption were added in 2023; resale orientation in 2024. Stage specific choices were visualized as Channel Journey diagrams.Insights from the surveys: Online comparison increased from 50.0% (2022) to 55.7% (2024). Journeys bifurcated: daily goods often followed simplified one stop flows, whereas electronics and gifts showed complex cross channel switching. Value logics shifted by situation: 37.3% of marketplace users prioritized points; 12.5% of official site users emphasized security; 24.2% of electronics buyers reported assurance when purchasing on official sites. Loyalty/point activities engaged 96% of respondents—enhancing enjoyment yet adding UX complexity. Resale orientation grew (4.8% consider resale; 8.8% purchased used in 2024), extending value beyond purchase. Support quality—returns/exchanges, delivery notifications, responsive inquiry handling—strongly shaped satisfaction and trust.Conceptual models: From convergent patterns in the data, we inductively articulate two models. CASCADE formalizes a cyclical design process—Context Scan, Activation (parallel value logics), Switch & Select, Channel Diversion, Action, Dynamic Integration, Extension. CASMOT structures measurement—Context Scan, Activation, Switch & Select, Multi Channel (individual), Omni trace (aggregate), Trace. We map model elements to observed indicators (e.g., assurance logic anchored by official sites and support; economic/points on marketplaces; empathy/story on social/video; convenience/speed in rapid fulfillment).Contribution: The insights and models are intended to provide theoretical and practical guidance for service design and experience design, enabling the creation of richer and more diverse purchase experiences and informing future HSI research and practice in digital commerce.

Kyoko Kamimura

Conference Proceedings

A Framework for the Social Implementation of Visions: Integrating Design, Experimentation, and Culture

In Japan, corporations and public organizations frequently articulate ambitious visions of desirable futures. However, these visions often remain symbolic statements rather than drivers of systemic transformation. The difficulty arises from a structural gap between ideals and practice, rooted in the lack of experimental mechanisms, institutional adaptability, and cultural openness. The purpose of this study is to address this gap by proposing and examining a framework for the social implementation of visions. This framework aims to move beyond rhetorical vision-setting by offering organizations a structured approach that integrates design, experimentation, and cultural embedding.The research adopts a design-oriented methodology that synthesizes theoretical insights from innovation studies, organizational design, and cultural theory. The proposed framework integrates four interconnected elements: (1) vision design, defined as articulating a “compass” toward a desirable world rather than a fixed roadmap; (2) social experiments and experiential prototypes, which create opportunities for testing and experiencing future possibilities; (3) organizational design, encompassing structures, processes, and systems that sustain change; and (4) culture, understood as shared values and practices that enable collective action. The framework highlights two complementary pathways: a top-down approach, in which visions guide the design of experiments and prototypes, and a bottom-up approach, in which small practices evolve into broader visions. Art-thinking informs the early stage of individual imagination, while design-thinking guides the iterative prototyping and organizational embedding process. To examine applicability, two qualitative case studies were conducted: (1) Money Forward Inc., a fintech company that redesigned its mission, vision, values, and culture (MVVC) to manage rapid growth; and (2) Busshien Social Welfare Corporation, a welfare organization reimagining community through experimental social services. Data were collected through semi-structured interviews, site visits, and analysis of organizational documents.The analysis reveals several insights. First, visions require a starting point in individual imagination and passion, which transform abstract ideals into actionable orientations. At Money Forward, a leader’s personal conviction—“to create a company one can be proud of”—initiated the redefinition of MVVC. This vision was then embedded through experiential practices such as employee assemblies, evaluation systems, and public sharing of a “Culture Deck.” Second, social experiments and experiential prototypes serve as crucial bridges between visions and practice. At Busshien, unconventional initiatives such as community cafés, hot springs, and multipurpose facilities operated by people with disabilities acted as experiential prototypes that reframed welfare as a central element of local life. These experiments not only tested feasibility but also cultivated new social perceptions and cultural norms. Third, organizational design and culture proved indispensable in sustaining implementation. Money Forward established a dedicated “People Forward Division” to integrate culture with HR functions, while Busshien embedded inclusivity into daily operations through flexible roles and participatory governance. Collectively, these findings demonstrate that social implementation depends on iterative cycles of vision creation, prototyping, organizational support, and cultural reinforcement.The study highlights that innovation culminates not in technological invention alone but in long-term processes of societal embedding. For researchers, the framework provides a lens to analyze socio-technical transformation, emphasizing the interplay of individual, organizational, and cultural dimensions. It suggests that successful implementation requires patience, iterative learning, and alignment between micro-level initiatives and macro-level systems.The originality of this research lies in its integration of vision design, social experimentation, organizational design, and cultural embedding into a unified framework. By bridging art-thinking and design-thinking, it offers a systematic approach for moving from individual passion to collective societal transformation. The study contributes to the field of human intelligent systems integration by demonstrating how disruptive and innovative technologies can be enacted not only through technical breakthroughs but also through socio-cultural practices. It provides practical guidance for organizations, policymakers, and communities seeking to translate visions into sustainable societal change.

kazuhiko yamazaki, So Nishina

Conference Proceedings

Municipal revenue generation and informal settlements: The case of the Chief Albert Luthuli Local Municipality

Local Municipalities, primarily found in semi-urban and rural areas, are traditionally faced with the challenge of a very low or non-existent property rate and tax base. This is because of many informal settlements in rural villages, which disempower local municipalities to value the occupied individual land parcels for property rates and tax billing purposes. This paper aimed to assess whether the value created from the formalised properties can translate into property rates that the municipality can bill to generate revenue. The case study approach was adopted, and a case of the former Kangwane homeland and informal village areas in Chief Albert Luthuli Local Municipality was used. Data were collected over eleven months from January to November 2024 through key informant interviews and document analysis. Key informants were purposively selected from Chief Albert Luthuli Local Municipality employees from the Town Planning and Finance Departments and chosen beneficiaries. It was concluded that formalisation does not always translate into increased revenue from property rates generated from upgraded previously informal settlements. This is because most upgraded properties do not qualify to be valued and rated within the prescripts of the existing municipal property rates legislation and policies.

Lerato Motloung, Partson Paradza, Benita Zulch, Joseph Yacim, Steven Ngubeni

Conference Proceedings

Exploratory Research on the Migration of Auteurs' Cinematic Aesthetic Styles in AI-generated Short Films

This study investigates the migration of the author-director’s visual aesthetic style within the context of AI-generated short films. It observes that prominent auteurs are actively negotiating the tension between inherited cinematic traditions and their own expressive impulses, as well as the intersection between their practical filmmaking experience and the algorithmic logic of AI-generated imagery and creative inspiration. Based on the technical logic of keyword-driven creation, it explores the evolution of directors’ narrative approaches, the aesthetic framework of AI-generated visual art, and the broader implications for artistic reflection. Furthermore, it investigates the transformation of aesthetic standards, the challenges of intelligent visual representation, and the expanded expressive potential of contemporary image-making practices. The structure of this research is divided into several key sections. The first part examines the current applications and developmental challenges associated with the migration of auteurs’ visual aesthetic styles in AI-assisted filmmaking. It emphasizes the narrative efficiency and emotional expressiveness achieved through audio-visual language in the directors’ prior works, while exploring how the fictional nature of AI-generated imagery can evoke a sense of realism that resonates with the audience’s lived experiences. The second to fourth parts offer in-depth analyses of AI short film experiments conducted by Jia Zhangke, Li Shaohong, and Yu Baimei, respectively. These analyses are approached from multiple perspectives, including the logic of AI keyword generation, the construction and symbolism of audio-visual language, and the articulation of the director’s creative intentions. The discussion centers on the methods and outcomes of visual aesthetic style migration within these works, aiming to provide a comprehensive understanding of the evolving relationship between human creativity and AI-assisted artistic expression.

Yazhou Chen

Conference Proceedings

Generating Comic Instructions for Self-Explaining Ambient Systems

Dynamically connecting technical components to form Ambient Systems offers a variety of opportunities in various use cases. Particularly, the flexible integration of smart objects and applications allows for solutions adaptively tailored to the needs and daily tasks of the respective users of smart environments.However, this approach also entails some challenges as the handling of such systems can be obfuscated due to the dynamic connection. Towards this end, self-explainability of involved components and dynamically generated instructions have been proposed to counteract this issue. In this paper, we present a novel comic instruction rendering engine that can generate user instructions based on the self-descriptions of all involved components. Overall, current research on self-explainability predominantly explains system behaviour and adaptation logic but pays little attention to user–system interactions or the dynamics of interconnected adaptive ensembles.The Ambient Reflection framework instead, enables the runtime generation of instructions for users in smart environments. The foundation for the instruction generation is the Smart Object Description Language (SODL). It supports a formal, hierarchical description of Smart Objects and Ambient Applications and their interactions. The framework collects self-descriptions of all involved components and merges them into an ensemble description. Interactions in SODL are structured across the levels of the Virtual Protocol Model reaching from the abstract goal level describing the objective (e.g., “start the music”) over semantic, lexical, alphabetical level down to the physical level describing the actual physical movement (e.g., “move your hand horizontally left”). Graphical illustrative media is allowed to be linked to illustrate required user actions and system responses. To generate user-tailored instructions from the SODL self-descriptions, the framework supports different rendering engines, e.g., for text or web pages. However, the framework does not provide instructions created in comic format.There has been a lot of work published about manual or semi-automated comic generation or converting existing visual media into comics. Also, generation based on artificial intelligence has become popular. However, those approaches require significant manual intervention, problem description beforehand and iteration to produce coherent and meaningful results. In this paper, we extend the Ambient Reflection framework with a Comic Rendering Engine supporting automatically generating comic instructions based on the ensemble self-description. For this purpose, the SODL descriptions are serialized using JSON. The Comic Engine then invokes a Comic Generator as a sub-process and passes the structured JSON information. The Comic Generator first transforms the data into a Comic Book Markup Language (CBML) document. This transformation flattens the nested JSON structure while preserving the essential level information (e.g., Goal, Task), resulting in a bundled data format suitable for generation.The system accesses visual and textual representations for devices, applications and interactions, which are embedded within the self-descriptions of the respective components. The textual content is adapted to fit the special needs of comic design. The actual generation of the comic elements like characters, speech bubbles and their arrangement is delegated to a web-based, open-source software package (Comicgen) and inserted into the CBML panels. To ensure a uniform look and prevent visual obstruction, objects are scaled to not exceed a maximum size. Collision avoidance strategies are involved in placing element. The final output is rendered as a PDF file that can be displayed on devices in the environment.We conducted a user study to investigate the quality of the generated comic instructions. The study focused on the comprehensibility of the generated comic tutorials and the clarity of their textual and graphical elements. The emphasis was therefore placed on the quality of the instructions themselves, rather than on the system design or the usability of the ensembles being explained. The investigation was concluded as a quasi-experimental mixed-design study with questionnaires, observation and semi-structured interviews (N=13). The laboratory wizard-of-Oz setup included a collection of interaction devices based on gestures and voice. Tasks included light and temperature control of a smart home as well as interacting with a novel in-bed application for intensive care patients using a dedicated ball-shaped interaction device. Results indicate that automatically generated comic instructions can effectively support the operation of Ambient Systems consisting of interconnected Smart Objects and applications. Feedback showed that the tutorials’ consistent structure was positively received. Additionally, the instructions were considered clear and understandable.

Marvin Berger, Börge Kordts, Andreas Schrader

Conference Proceedings

Examining the Impact of AI on Schema and Scaffolding in Educator Preparation

Artificial Intelligence is disrupting the educational landscape and is being touted as a catalyst for enhanced learning. This article examines the use of AI as a scaffolding tool to help preservice teachers build new knowledge and skills. It explores how this use of AI impacts their schemas, the mental structures that support learning. When used as a collaborator, AI might allow developing teachers to create more sophisticated and well-structured lesson plans earlier in their training, leading to a more robust and nuanced schema. However, over-reliance on AI could lead to a less developed, or "brittle," schema, preventing the preservice teacher from fully internalizing the underlying principles of instructional design.

Colleen Duffy

Conference Proceedings

Implementing Vision in Society through Brand Experience: A Multi-layered Framework and Case Studies

Visions and purposes have become increasingly recognized as essential drivers that shape the future of organizations and society. However, visions are often articulated as abstract ideals, making them difficult for users to experience directly. While previous studies in design, marketing, and organizational theory have addressed visions, brand experiences, and culture separately, few have examined how visions are concretized as everyday experiences that influence both internal culture and external user interactions. This study aims to address this gap by proposing a multi-layered framework that enables the social implementation of visions through brand experience and by demonstrating its application through two contrasting organizational cases.This study adopted a qualitative, multi-case approach. First, an integrative framework was developed, conceptualizing the process of vision implementation as a chain: vision → brand experience → employee experience → user experience. This framework emphasizes how brand experience translates abstract visions into emotionally resonant narratives, employee experience internalizes the vision within organizational practices, and user experience manifests the vision through products and services. Second, two organizations from distinct domains were analyzed: Money Forward Inc., a fintech company in Japan, through a semi-structured interview with a key cultural leader and company documents; and Busshien, a Japanese social welfare corporation, through site visits, interviews, and literature review. The analysis examined how visions were expressed and experienced at each of the three experiential layers.The analysis revealed that both organizations successfully implemented their visions through multi-layered experiential strategies. At Money Forward, the vision of “Move money forward. Move life forward.” was translated into a brand experience of progress and optimism through design language and advertising, supported internally by employee behavior guidelines (e.g., “User Focus,” “Fairness”). Users experienced the vision through financial visualization tools that fostered security and empowerment. At Busshien, the vision of “creating an inclusive society” was embodied in open and culturally rich facilities, promoting brand experiences of inclusion and dignity. Employees internalized this vision through empathetic care practices, while users experienced respect, autonomy, and belonging in their daily interactions. Despite differences in their mediating elements—digital UX and corporate culture versus caregiving practices and community interaction—both organizations showed a shared structural pattern of translating abstract visions into concrete experiences.This study contributes a new framework for understanding how organizational visions can be socially implemented by cascading from brand experience to employee experience and finally to user experience. The framework clarifies the dynamic and cyclical nature of this process, in which user feedback and employee practices continually reshape brand experiences and visions. By highlighting the common structure underlying different domains, this study provides practical guidance for organizations seeking to embed abstract visions into everyday life and culture.

kazuhiko yamazaki

Conference Proceedings

Navigating the Artificial Intelligence Landscape in Higher Education: A Human-Centered Approach to Integrating Technology for Enhanced Learning

The emergence of Artificial Intelligence (AI) has significantly transformed the landscape of teaching and learning in higher education. As AI technologies continue to evolve, they are redefining how educators deliver content, how students engage with learning materials, and how instructors assess student performance. Educators and researchers must continue to support a human-centered pedagogical system within our institutions while incorporating AI effectively. The ongoing research in this area seeks to explore best practices for integrating AI in a way which enhances learning outcomes without compromising academic integrity or human-centered, educational settings. Recent studies have indicated that AI technologies can facilitate student engagement, support differentiated instruction and provide curriculum which positively impacts the teaching and learning environment. The current research in this area explores best practices for integrating AI in a way that improves learning outcomes without compromising academic integrity or human-centered pedagogy. However, the effectiveness of AI in education depends on the digital literacy of both students and instructors. Students may unknowingly engage in AI practices that promote dishonest academic outcomes. Institutional guidelines and policies focused on using AI tools appropriately must be created and uniformly enforced in higher education. Furthermore, professional development and on-going, consistent training are crucial to ensure educators can successfully integrate AI tools in the classroom. The rapid pace of technological change has made it difficult for universities to remain informed about best practices, often leading to a trial-and-error approach to implementation. Faculty and administrators must continue to remain current with trends and the latest developments in AI technologies while ensuring institutional goals, pedagogical frameworks, and accreditation standards are being upheld.AI has the potential to transform higher education by fostering more efficient and engaging learning experiences. However, its successful adoption requires a thoughtful, evidence-based approach that considers using AI technologies in a human-centered pedagogical system. As institutions continue to adapt to this new dynamic within the education field, continued research, training, and planning will be critical to display the full potential of AI in higher education.

Jodi Loughlin

Conference Proceedings

“The Vision Picnic”: A Metaphor-Driven Workshop Framework for Personal Vision-Making through Collaborative Self-Exploration

In a rapidly changing contemporary society saturated with diverse choices, individuals often find themselves in a "food court where they don't know what they truly want to eat." In this environment, it has become increasingly difficult for individuals to draw a clear future for themselves (to make a "handmade bento"). This study proposes and reports on the design and implementation of "The Vision Picnic," a novel workshop framework that takes a human-centered approach to this challenge. The primary objective of this workshop is to support participants in a process of self-exploration and future-self conceptualization in an enjoyable and intuitive manner by employing the familiar and creative metaphor of "making a bento for a picnic." This paper analyzes this framework and its impact on participants, and considers its effectiveness and future challenges.The workshop is designed as a journey for participants to create their own "special future bento." The process is structured into three main steps, designed to elicit fundamental abilities for vision-making: Subjective Ability (the ability to find purpose and value from a subjective and original perspective = "a tongue that trusts one's 'likes'"), Imaginative Ability (the ability to expand the image of a desirable world = "a recipe book for drawing unseen 'feasts'"), and Practical Ability (the ability to organize means to realize the formed image = "the skill to 'cook' ideas").Step 1 is Ingredient Gathering (Self-Exploration). In this step, participants open their "refrigerator of the heart" to take out "ingredients," which represent their personal "likes" and "strengths." The specific task is to freely list about 20 things they "like" or find "fun." Participants are given hints, such as using word association, and are encouraged to include simple daily pleasures as valuable ingredients. This is followed by a dialogue session where pairs "taste-test" each other's ingredients. Through questions like, "What kind of flavor (enjoyment) does that ingredient have?" and "Do you have any 'soul food' you've loved since childhood?", participants examine their ingredients (= things they like and enjoy).Step 2 is Recipe Making (Vision-Making). This step involves combining the gathered ingredients to create an exciting "original recipe," which represents a desired future self. For example, participants might combine "expanding knowledge," "beer," and "cafe" into a recipe for a "Knowledge Brewery Cafe Owner." To stimulate recipe ideas, the workshop includes an exercise called the "'Food Report' from a Future Gourmet," where participants imagine themselves at 80 years old as a "gourmet who has savored life to the fullest" and write a letter of advice to their present self.Step 3 is Packing the Lunch Box (Action Planning). Based on the completed recipe, this final step is about deciding on the "first bite" that can be taken starting from the next day. To realize their created vision, participants write down a concrete action plan of what they can do "Today," "This Week," "This Month," and "This Year." Emphasis is placed on defining an immediate, small first step, such as "Today: Find one beer bar online for reference."Qualitative feedback from participants and analysis of their work yielded several key findings. First, the effectiveness of the metaphor-based experience design was demonstrated. The friendly metaphors of a "picnic" and "bento" lowered the psychological barrier to the introspective theme of vision-making and encouraged participants to engage with the process enjoyably. Second, the importance of dialogue integrated into the process was confirmed. Through "taste-testing" with others, participants gained a higher resolution of their own values and preferences that they might not have noticed alone, with one participant noting it was "an opportunity to realize what kind of flavor I liked!" Dialogue was effective in deepening self-exploration and helping individuals find a direction for their vision. At the same time, several challenges became apparent. The "Recipe Making" step was particularly difficult, and some participants were unable to formulate a satisfactory vision within the allotted time. Feedback such as, "I thought there might be recipes that become visible by talking with various members," suggested room for improvement in how dialogue pairs are formed.

Toshiya Sasaki

Conference Proceedings

Promoting Pro-Environmental Behavior through Anticipated Emotions: A Preliminary Study Using an Episodic Recall Task to Encourage Positive Outcome Expectations

In the context of the rapidly intensifying global environmental and energy crises, promoting pro-environmental behavior (PEB) at the individual level has become a critical challenge. However, PEB often requires additional effort and time in daily life while providing few direct benefits or immediate rewards to the actor, making sustained engagement difficult. To address this challenge, previous research has explored various interventions, including the dissemination of environmental knowledge, the provision of financial incentives, and the implementation of nudges. Although these interventions have been shown to produce measurable effects, they do not directly target the inherent “burdensomeness” of PEB, and their limitations have been acknowledged.Against this background, this study focuses on “anticipated emotions” as a novel approach to overcoming the difficulties associated with PEB. Anticipated emotions are feelings generated by imagining the outcomes of one’s actions, and they are known to strongly influence decision-making. In particular, two types of anticipated emotions—expectation (anticipation of favorable outcomes) and regret (anticipation of unfavorable outcomes)—are considered to play important roles in everyday choices. Based on this facts, this study hypothesizes that these two anticipated emotions can facilitate PEB. While conventional studies have primarily emphasized externally easing or guiding PEB, this study explores the potential of using emotions to positively reframe the inherent burdensomeness of such behaviors.To test this hypothesis, we developed a novel anticipated emotion induction task. They were asked to recall and describe personal experiences in which exerting effort despite inconvenience led to a positive outcome (expectation) or in which refraining from action due to inconvenience resulted in regret (regret). Each task provided typical examples before prompting them to write about their own experiences, thereby eliciting anticipated emotions in a direct and personalized manner. An experiment was conducted where participants were randomly assigned to either the anticipated emotion group or a control group and completed the tasks individually on a computer in a laboratory setting. Baseline PEB was measured using the Pro-environmental Behavior Task (PEBT), a virtual travel task in which participants completed 24 trials choosing between an environmentally friendly but slower transportation option (SEST) and an environmentally unfriendly but faster option (TEFT). The time difference between the two options varied randomly across trials (0, 5, 10, or 15 seconds).Following the baseline measurement, the participants in the anticipated emotion group completed the emotion induction task, whereas the control group completed neutral, non-emotion-inducing tasks of the same format. After the intervention, the PEBT was administered again to assess changes in behavioral choices. In addition, a post-experiment questionnaire measured their habitual PEB, emotional states, perceived value of burdensome actions, and personality traits.The results indicated a tendency for increased SEST choices in the anticipated emotion group after the intervention, suggesting that changes in the perceived value of burdensome actions may have partially mediated behavioral change. Although exploratory, these findings suggest that anticipated emotions can facilitate pro-environmental behavior by assigning positive value to actions that are otherwise perceived as burdensome. Detailed results will be reported in the final manuscript.

Wataru Ogomori, Shunya Tanaka, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda

Conference Proceedings

From Tower to Center: Conversion Training for Remote Tower Operations

The concept of Remote Tower Operations, where Air Traffic Services are provided remotely rather than on-site, is increasingly implemented by Air Navigation Service Providers across the globe. Within Remote Tower Operations, Air Traffic Controllers and Aerodrome Flight Information Officers control the air traffic from a highly digitalized working position including a panoramic view of the airfield as well as sophisticated interfaces for the control of zoom cameras, runway lighting systems and communications. To demonstrate that safety of operations is maintained within this new operational framework, strict regulations by the Civil Aviation Authorities have to be complied with. For the opening of the Remote Tower Center Lower Saxony in Germany, the provision of a conversion training for the Air Traffic Control Officers of Braunschweig airport, as well as the Aerodrome Flight Information Officers of Emden airfield was required. This training took place at the simulation facilities of the German Aerospace Center’s Institute of Flight Guidance. The aim of the training was to familiarize the personnel with the novel working environment and to enable them to safely guide and control traffic from this environment. Throughout the training, subjective and objective metrics were recorded to evaluate the effectiveness of the conversion training. Expecting a learning effect throughout five simulation runs, it was hypothesized that despite increasing scenario complexity, more situational awareness as well as trust and thus more efficiency in handling traffic would be observed. Although not statistically significant, a descriptive overall training effect was observed for all parameters from the first run to the exam run. Especially important are the findings regarding self-reported situational awareness and trust in the system, which indicate not only successful adjustment to but also acceptance of the new working conditions, an important factor considering the transition to the new working position at Remote Tower Center Lower Saxony. The conversion training design, its framework, as well as the results of this study, can serve as guidance material for future conversion training designs.

Isabel Carole Metz, Maria Hagl, Jörn Jakobi

Conference Proceedings

Acceptance of conceptual engineering models for new technologies

Industry 5.0 and Society 5.0 initiatives represent a transformation of focus in new technology design to information and human based thinking. Change in paradigm requires conceptual engineering in design thinking when introduced with new concepts such as human or cognitive digital twin (HDT/CDT). It is important also to ask, how people accept new kinds of conceptual models related to technology design. We present an empirical investigation on how acceptance of the HDT proceeds in the minds of people who encounter a novel conceptual model of technology design for the first time. The investigation took place in two workshops. Results suggest that acceptance of HDT as a new conceptual model needs to consider at least four themes: 1. understanding possibilities for HDT application and design, 2. identifying perceived value conflicts, 3. information collection, communication, and sharing underlying HDT design, and 4. HDT’s relation to work meaningfulness, experience and learning. Thus, to fully explicate the possibilities of HDTs require understanding them as part of designing joint cognitive systems, that future technology aims to augment people, collecting and sharing high-level tacit knowledge (HTK) enables improvement of work processes, and that design of HDTs needs to follow contemporary interaction and human-centered AI (HCAI) principles. These are important aspects in maintaining worker’s sense of pride and creativity, and for designing work for future hybrid teams.

Mari Myllylä, Henrikki Salo-pöntinen, Pertti Saariluoma

Conference Proceedings

Blue Thinking: Human-Centered Design for Sustainability and the Blue Economy in Education

This paper introduces Blue Thinking, an integrative framework combining human and activity-centered design with sustainability education and the blue economy. Developed within the Blue Design Alliance (BDA) - a consortium led by College of Art and Design (ESAD) in Portugal and supported by the national Recovery and Resilience Plan (PRR) - the framework reconceptualises water as a material and epistemic medium, symbolizing adaptability, interdependence and systemic flow across human-technology-ecosystem relations. Methodologically, the study employs research-through-design and project-based learning across 36 interdisciplinary short courses (delivered from 2022 until 2025). Mixed data sources - observations, interviews and institutional metrics on enrolment, completion, satisfaction, and sustainability integration - provide our evidence base. Four representative case studies demonstrate the framework’s application: Editorial Design for Community Contexts (communication and identity), Interior Design for Nautical Environments (adaptive spatial intelligence), Food Design for Sustainability (ethical and sensory literacy), and Illustration and Digital Narratives (ecological communication). Results reveal measurable improvements in students’ systems thinking, ecological literacy, and technological self-efficacy. Findings indicate that intelligent systems augment rather than replace human judgment, enhancing decision-making in design. Blue Thinking thus operates as a model of augmented-intelligence learning, linking creativity, ethics, and technology within sustainability-oriented design pedagogy. Aligned with European Union (EU) and United Nations (UN) sustainability frameworks, Blue Thinking positions higher education as a catalyst for systemic change, preparing designers to act as agents of ecological transition, social inclusion, and circular innovation.

Ana Cardoso, Maria Rui Correia, José Simões

Conference Proceedings

Findings of a Usability Study of Family Portal in Eastern Maryland among School-going Children Caregivers

In the realm of educational innovation, family portals (online platforms for information sharing and communication between families and schools) represent a promising tool for enhancing parental engagement by providing real-time access to students' information, such as attendance records, assignments, and grades (Mac Iver et al., 2021). However, the effectiveness of these portals depends on user awareness and utilization of their features. This study investigates the awareness and frequency of use of the attendance chart feature within family portals among parents and guardians in Eastern Maryland. It assesses the extent to which these technologies are fulfilling their intended role and identifies the factors contributing to their successes and failures. Data from a structured survey of 55 participants: eight educators who are also parents in the school system and forty-seven parents/guardians of high school students in a public school in Eastern Maryland. Demographic data revealed a diverse participant group, with most respondents aged 31 to 50, identifying as female, and reporting intermediate or advanced computer proficiency. Nearly all participants (98.2%) owned a smartphone, indicating their high level of familiarity with technology. Analysis of the data revealed that 76.4% of participants were aware of the attendance chart feature, with 47.3% of participants using it, while 29.1% were aware but had not used it. Of those who were aware, 61.9% actively used the feature, indicating that awareness has a positive influence on adoption. However, barriers such as communication preferences (16.7%), lack of perceived necessity (9.5%), and usability challenges (2.4%) were identified. Additionally, irregular usage patterns were observed, with 61.6% accessing the chart at least once or 2-3 times a week, while 26.9% only checked sporadically or when prompted by specific events. These findings underscore the importance of improving portal usability, promoting consistent communication strategies, and highlighting the value of the attendance chart feature to families. By addressing barriers to adoption and usage, the study offers actionable insights for schools and developers to optimize the deployment of family portals, ensuring equitable access and engagement for all families. This research contributes to the growing literature on the role of educational technologies in fostering effective school-family partnerships. REFERENCESMac Iver, Martha Abele, Sheldon, Steven, & Clark, Emily. (2021). Widening the portal: How schools can help more families access and use the parent portal to support student success. Middle School Journal, 52(1), 14–22. https://doi.org/10.1080/00940771.2020.1840269

Miselta Tita, Joyram Chakraborty, Mona Mohamed

Conference Proceedings

Sensory and Regenerative Design in SMEs: Strategies for Environmental Restoration and Experiential Engagement

Small and medium enterprises (SMEs) play a pivotal role in local economies, yet they often face challenges in adopting innovative design practices that enhance both ecological sustainability and human experience. This study explores how regenerative and sensory design principles can be applied within the built environments of SMEs—particularly retail and exhibition spaces—to create environments that are simultaneously ecologically restorative and experientially engaging. The central research question guiding this work is: How can SMEs integrate regenerative and sensory design strategies in a cost-effective and scalable manner to enhance environmental performance and human well-being?The methodology employed a literature-based, mixed-methods approach, combining a state-of-the-art review in regenerative design, sensory design, and SME-focused research with the analysis of applied examples in retail and exhibition contexts. Key sources included foundational texts on regenerative design (Lyle, 1994; Mang & Reed, 2012; McDonough & Braungart, 2002), multisensory engagement (Pallasmaa, 2005; Malnar & Vodvarka, 2004), and empirical studies on SME spatial performance, environmental impact, and customer experience. This review was complemented by the synthesis of case studies from global brands (e.g., Aesop) to identify practical, low-budget strategies relevant to SMEs.Results reveal a set of guidelines and actionable strategies that SMEs can implement to foster regenerative and sensory-rich environments. These include: prioritizing biophilic design (plants, natural light, water features) to enhance air quality, reduce energy dependence, and engage multiple senses; incorporating natural, reclaimed, or biodegradable materials to support circular economy principles while creating tactile and visually rich experiences; designing soundscapes and ambient sensory cues to influence emotional and cognitive responses; and fostering community interaction and participatory experiences to strengthen social resilience and brand identity. Practical applications demonstrate that SMEs can achieve measurable benefits—such as improved customer engagement (up to 33%), enhanced employee productivity (10–25%), and operational savings (9–30%)—even with limited budgets, by leveraging modular, reusable, and locally sourced interventions.The discussion highlights synergies and barriers in implementing regenerative and sensory design in SMEs. Synergies include the alignment of ecological integrity with emotional engagement, operational coherence through localized sourcing and biophilic integration, and enhanced branding through sensory storytelling. Barriers include financial constraints, limited design literacy, regulatory restrictions, and cultural perceptions of design as non-essential. Policy interventions, such as grant programs, simplified regulations, capacity-building initiatives, and recognition of regenerative and sensory criteria in certification programs, are identified as crucial enablers for broader adoption.In conclusion, integrating regenerative and sensory design within SME-built environments represents a pragmatic and ethical pathway to simultaneously improve environmental outcomes, human well-being, and business performance. The findings challenge the notion that innovative, ecologically responsive, and sensory-rich design is exclusive to large corporations, demonstrating that even resource-limited SMEs can act as agents of ecological and social regeneration. Future research should explore longitudinal studies and participatory evaluations to refine these strategies and assess long-term impacts across diverse SME contexts and cultural settings. By embracing these principles, SMEs can transform everyday spaces into environments that are not merely functional but restorative, inspiring, and experientially memorable.

Paulo Eduardo Tonin, Marinella Ferrara, Elton Nickel

Conference Proceedings

Interpretable Multimodal Framework for Assessing Cognitive Load and Stress in Collaborative Robot Environments

This study presents an explainable machine learning framework for estimating cognitive load and stress from multimodal physiological and affective data collected during human–robot collaboration tasks. The proposed approach integrates electroencephalography (EEG), electrocardiography (ECG), galvanic skin response (GSR), and emotion-related features with contextual task information to model human cognitive states. Data were preprocessed, standardized, and evaluated using a leave-one-participant-out cross validation scheme to ensure subject-independent generalization. Bayesian optimization was applied to tune the hyperparameters of non–tree-based models, including support vector regression (SVR) for predicting continuous NASA-TLX scores and a multilayer perceptron (MLP) for classifying discrete stress levels. The regression model achieved an R² of 0.98 and a mean absolute error of 0.08, while the classification model obtained an accuracy and F1-score of 0.94. Model interpretability was ensured through SHapley Additive exPlanations (SHAP) analysis, which identified EEG coherence and beta-band activity, ECG LF/HF ratios, and emotion-related indicators such as sadness and confusion as dominant contributors to increased cognitive load and stress. These findings highlight the potential of combining physiological and affective modalities with explainable artificial intelligence for reliable cognitive state assessment. The developed methodology provides a foundation for adaptive robotic systems capable of monitoring and responding to human mental states, thus supporting safer and more efficient collaboration in dynamic operational environments.

Sandi Baressi Šegota, Darko Etinger, Ivan Lorencin, Nikola Tankovic, Luka Blašković, Nikola Anđelić

Conference Proceedings

Modern Technology Adoption in Property Valuation: Perceptions in South Africa

Emerging technologies such as artificial intelligence (AI), automated valuation models (AVMs), geographical information systems (GIS) and other related technologies are reshaping the global property valuation industry. Debates on readiness for the adoption of digital technologies are at the forefront particularly in municipal valuations, where concerns of valuation accuracy are prevalent. This study investigates how property valuers perceive and adopt AI and other technologies in South Africa. The study employed a quantitative research design using an online national questionnaire survey distributed to capture the opinions of property valuers. A total of 340 valid responses were received and analysed using Statistical Package for Social Sciences (SPSS) version 30. Descriptive statistics, Spearman’s rank-order correlation, Kruskal–Wallis H tests, and Pairwise Mann–Whitney U tests were applied to determine relationships and group differences. Findings indicate that AI adoption is minimal, with nearly half of property valuers reporting “never” using AI tools such as “ChatGPT” and only 1.8% reporting regular use. Statistically significant differences in adoption were observed across specialisation and registration class, with commercial and candidate valuers demonstrating higher adoption rates. Conversely, municipal and senior valuers displayed more conservative digital engagement patterns. Candidate valuers and valuers with less experience were more likely to experiment with AI tools, while property valuers specialising in municipal valuers were reported to be the most resistant to the use of AI and related emerging technologies. Confidence in GIS tools showed a high adoption rate with most respondents reporting consistent use. The findings indicate that South African property valuers are concomitantly progressive and conservative, with the use of GIS tools fully integrated in practice while AI and AVMs are yet to be adopted.

Barend Du Toit, Christopher Amoah

Conference Proceedings