Human Interaction and Emerging Technologies (IHIET 2025)

AHFE International

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

Human Interaction and Emerging Technologies (IHIET 2025)

book-cover

Editors: Tareq Z. Ahram, Renate Motschnig

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2025

ISBN: 978-1-964867-73-1

DOI: 10.54941/ahfe1006693

Articles

User experience evaluation of an AI-based decision-support tool for power grid congestion management

The electricity system is changing rapidly, due to the increasing efforts against climate change. In the control room, power grid operators are already being challenged by the changing system behaviour, and maintaining a high level of security of supply is expected to become even more challenging in the future. To cope with these challenges, new tools and functionalities, such as AI-based decision support tools (DSTs) are needed. Developers of future DSTs must consider not only technical aspects, but also whether new systems are usable by power system operators. This study presents a case study of user experience (UX) evaluation applied to a DST for power grid congestion management. The evaluation approach employs a broad range of UX metrics. More precisely, we (i) introduce entirely new UX metrics based on a cognitive analysis of the human-AI interactions, (ii) provide a questionnaire and a set of tasks that are tailor-made for the DST to assess acceptance, trust, and performance, and (iii) apply established generic questionnaires to assess usability and workload. At the same time, the employed methods are mostly simple such that the evaluation requires relatively low effort. The complete end-user population participated in the study, and the DST exhibits high scores in almost all UX metrics. The results form a baseline of summative user research which enables benchmarking of future congestion management tools (or future releases of the same tool).

Jan Viebahn, Abdullah Ayedh, Jonas Lundberg, Magnus Bång, Jeroen Keijzers

Conference Proceedings

Applying Job Design Criteria for Effective Human-AI Collaboration

Human-AI collaboration often underperforms due to a lack of motivation-supportive system design. This paper proposes a framework grounded in work design theory – specifically the Job Characteristics Model (JCM) – to guide the development and evaluation of AI systems. We introduce qualitative evaluation anchors that translate core job design criteria into assessable aspects of AI-supported work. These anchors were developed through a theory-driven process that combines work design theory with recent literature on AI’s impact on work characteristics. The goal is to foster intrinsically motivating and cognitively engaging human roles in AI collaboration, thereby enhancing overall human-AI team performance.

Samira Hamouche, Nerissa Dettling, Toni Waefler

Conference Proceedings

Exploring and Understanding Neurodiverse Sensory Experiences and Management Through Digital Intervention

Sensory processing and regulation have garnered particular focus by professionals when recommending interventions to help neurodivergent individuals. However, little research has been done into the extent that neurodiverse individuals (the general population) understand sensory management, specifically: sensory seeking; sensory avoiding; and the concept of sensory diets, despite the potential value of this to their wellbeing. This study used a mixed-methods approach to explore sensory awareness and preferences in adult respondents and to understand their sensory experiences, including sensory triggers and their management of these. The overall aim of this study was to understand whether and how a mobile application could be designed to build a user’s awareness of their own sensory needs through sensory self-assessment; and recommend a personalised sensory diet to support their sensory regulation.Twenty-seven people completed a survey asking about their understanding of sensory processing and management. Survey data highlighted a lack of participant awareness of vestibular, proprioceptive and interoceptive senses; and the use of sensory diets to help manage sensory processing and maintain an optimal sensory experience. Findings informed the design of a low-fidelity app for further evaluation. Qualitative interviews were then conducted with 14 people. The purpose of these were two-fold: to gain richer data on individuals’ sensory perceptions and experiences; and to evaluate the concept of the sensory awareness prototype. Data from the interviews were thematically analysed and affinity mapping was used to analyse the prototype concept testing, capturing participants’ views on the potential usefulness of the app. Analysis of interview data highlighted how participant experiences consisted of sensory preferences – innate or learned inclinations toward specific sensory stimuli – and sensory triggers; stimuli that cause a strong response within the individual. Behavioural responses to preferences and triggers were categorised as seeking, avoiding, or employing no structured strategy. Seeking and avoiding behaviours were classified as either a premeditated strategy to prevent stress or a coping mechanism to try and alleviate stress. The selection of these depended upon environmental opportunities or on the intensity/impact of a trigger. Participant descriptions included instances of a cycle of sensory response, leading to physical response, leading to emotional response and a consequential reduction in sensory tolerance which further impacted physical wellbeing. In cases where no proactive strategy was in place, individuals often relied on instinctive “fight or flight” reactions.A high-fidelity prototype app, “SenseHarmony”, was developed which incorporated sensory screening and mood-logging features and provided sensory diet recommendations. This was tested with a further five participants through task-based usability analysis and interviews. This evaluation suggested that digital tools can be of value as an educational resource and to help equip people with a better awareness of, and strategies for, managing their own sensory needs. Through this study, we have sought to highlight how individuals interact with and manage their day-to-day sensory experiences and the potential benefits of a mobile app to enable this. We suggest that a tool to help individuals predict and manage their sensory responses can promote a shift from coping mechanisms to strategies, and support wellbeing.

Radhika Joglekar, Gail Hopkins

Conference Proceedings

User-Centered Design and Usability Evaluation of a Floodwater Depth Estimation Mobile Application

This study presents the user-centered design (UCD) and evaluation of a mobile application prototype, named Blupix mobile, which uses artificial intelligence (AI) and crowdsourcing to estimate the depth of floodwater in a user’s surroundings. Through a three-phase mixed methods technique based on UCD principles, the functionality, design, and usability of the app prototype are tested with a sample pool of U.S. participants. Results indicate a strong demand for location-specific, real-time alerts as well as community-generated content. The findings of this study aim to contribute to the expanding body of research on mobile disaster risk communication tools that incorporate community participation and engagement.

Amir Behzadan, Renooh Sivakumar

Conference Proceedings

Designing with ‘Intelligence’? Exploring the Limits of AI-Based UX Tools

Motivation: Artificial intelligence (AI) is increasingly shaping UX practice, with numerous AI-based tools promising to streamline the UX process and improve efficiency, saving time, money, and resources for users. However, how effectively do these tools support UX professionals in UX design and research? This project explores the current limitations and possibilities of using AI-based tools within an integrated, end-to-end human-centered design process.Research Questions: - How can AI-based tools support the phases of the human-centered design process?- How much and what kind of human intervention is necessary when using AI-based tools?Methodology: To address these questions, 106 available AI-based tools for UX were identified and reviewed. The tools were evaluated according to key criteria: AI functionality, support for UX methods relevant to the case study, GDPR compliance, availability of a free trial, and positive user reviews. Based on these criteria, 23 tools were selected for further assessment, focusing on their AI capabilities and the transparency of AI-generated results. From this assessment, two tools were chosen for use in the case study. The case study utilized a draft of a university website as a test case. It included an AI-based analysis of university websites, followed by AI-moderated interviews with students. Based on the research findings, an interactive prototype was developed and subsequently tested in an AI-moderated usability study with students.Initial findings: The case study revealed gaps between the different phases of the process, rather than an integrated end-to-end workflow. Bridging these gaps required human intervention at several points, particularly when incorporating research results into the prototype. Furthermore, both the methods applied, and the quality of the results produced by the AI-based tools were found to be inferior to the work of experienced UX professionals. This underscores the current limitations of AI-based tools in fully supporting the human-centered design process.

Benedikt Salzbrunn, Saskia Huemer

Conference Proceedings

Multibody Simulation Framework for Human-Machine Interaction in Impact Wrench Fastening: Enabling Reliability and Work-Related Health Risk Assessment

Ensuring both work-related health protection and reliability in impact wrench operations requires an in-depth understanding of human-machine systems, specifically the interactions between the human operator, impact wrench, and bolt connection with the environment. However, existing studies typically focus on isolated aspects, neglecting the complex dynamics between these systems. The lack of a simulation framework hinders assessments of human load, hand-arm vibration syndrome (HAVS) risk, and the reliability of the fastening process. Without a holistic approach, it remains challenging to optimize tool design, refine tightening strategies, and mitigate risks associated with high-frequency impulsive forces.To address this gap, we present a multibody simulation framework for analyzing human-machine systems, integrating three models: a digital human model (DHM) based on a musculoskeletal human model for biomechanical and health risk assessment, a multibody impact wrench model with drivetrain dynamics to capture impulsive force transmission, and a multibody bolt connection model with fastening dynamics to assess reliability. The three models run as a co-simulation between OpenSim and MATLAB Simulink described by Molz et al. The multibody impact wrench model based on the presented workload model (ApOL) of Sänger et al. is extended by modelling the internal drivetrain dynamics of the impact wrench and the forces acting onto the human during the bolt tightening process. The bolt model integrates finite element (FE) simulations on the micro level with a multibody system (MBS) model on the macro level to capture tribological effects in tangential impact-driven bolt tightening. The micro-scale FE model incorporates real thread topographies to compute friction coefficients, which are then applied in the macro-scale MBS model that includes bolt inertia and the impact wrench’s drive system. This enables a more accurate prediction of fastening dynamics, thread deformation, and torque losses, improving the assessment of the final preload force while ensuring scalability across different bolt sizes. By leveraging these models, we establish a multibody simulation framework that links human biomechanics, tool dynamics, and the mechanics of the bolt connection. Our framework provides a structured way to assess how impulsive forces propagate through the different systems. Additionally, by integrating fastening mechanics, we can examine how variations in bolt preload, friction coefficients, and tightening sequences impact the reliability of the bolt connection. The framework can also be used to compare different impact wrench tool designs and configurations, offering insights into how to mitigate undesired tool-induced physical stresses on the human operator. It sets the stage for future developments in enabling reliability and work-related health risk assessment. The modular nature of the framework allows for extensions, such as incorporating sensor-based validation data, and adapting the approach to other fastening tools. Additionally, this framework can be applied to different industrial settings, where fastening precision and human stress are critical factors, such as construction industry. The DHM in OpenSim estimates muscle activity in response to external forces and motion; however, it is not validated for assessing vibration exposure. This remains an active research topic within the musculoskeletal modeling community. Future work will focus on validating the simulation results against experimental measurements and refining the dynamic models to capture interactions more accurately. Ultimately, this framework establishes a foundation for systematically analyzing and enhancing human-machine interaction in impact wrench fastening, effectively linking reliability with work-related health risk assessment.

Felix Leitenberger, Johannes Sänger, Jonas Hemmerich, Tobias Kretschmer, Patrick Haberkern, Niklas Frank, Albert Albers, Patric Grauberger, Markus Doellken, Sven Matthiesen

Conference Proceedings

Generative AI for Sustainable and Efficient Layout Designs

Generative Artificial Intelligence (GenAI) is emerging as a transformative tool in industrial design, offering novel pathways to optimize functionality, resource efficiency, and sustainability. This paper explores the application of generative AI in 2D layout optimization through the development and evaluation of a specialized tool: the EcoStorage Architect. EcoStorage Architect leverages a Conditional Tabular GAN (ctGAN) to generate optimized layout configurations that not only enhance spatial efficiency and accessibility but also integrate sustainability constraints from the outset. By embedding eco indicators—such as energy efficiency and resource optimization—directly into the generation process, the model ensures that environmental performance is a core driver of design outcomes. The tool is evaluated on a dedicated dataset, with results demonstrating the feasibility of integrating generative AI into early stages of the industrial design process. Quantitative and qualitative assessments highlight gains not only in layout efficiency but also in key sustainability indicators. This work showcases how generative models can drive more adaptive, sustainable, and intelligent design practices in industrial contexts, and proposes a path forward toward AI-driven optimization in facility planning aligned with circular economy principles.

Javier Fernández Troncoso, Santiago Muiños Landin, Ramon Angosto Artigues, Eero Anttila, Juha Maunula, Andrea Fernandez Martinez

Conference Proceedings

Machine Learning for User-Dependent Ankle Joint Torque Estimation: An Application of XGBoost

Powered exoskeletons are increasingly studied to reduce walking effort. Providing optimal assistance requires user gait data, particularly ankle joint torque, which must be estimated despite available sensor measurements. While precomputed estimations exist for target populations, personalized estimation is preferable. Traditional musculoskeletal models are used, but recent approaches leverage Machine Learning (ML) regressions, such as support vector machines (SVM) or Deep Learning (DL) Recurrent Neural Networks (RNN) such as LSTM-based tools. These models need extensive, high-quality data, outsourced from various sensor types for accurate and robust estimations. Studies show that ankle dynamics vary significantly, closely linked to walking speed and user anthropometrics.We utilize a dataset of 138 healthy individuals, which includes EMG, kinematic, and dynamic leg joint data, as well as walking speed (0.97–1.59 m/s), height (1.68 ± 0.10 m), weight (74 ± 15 kg), age (21–86 years), and sex (65M/73F). By employing the XGBoost ML tool, we propose that an ankle joint torque estimator that integrates angular ankle position, walking speed, and anthropometric data can achieve accurate, robust predictions without the need for muscular data. Predictions are validated against unseen torque trajectories, and the performances of the estimator are compared to recent studies on lower limb joint torque estimation.Bootstrap evaluation of the estimators compared to the calculated dynamic data shows a correlation coefficient R² = 0.981 ± 0.051 (p<0.05) and an RMSE mean square error of 0.070 ± 0.008 Nm/kg (p<0.05). Among all data characteristics, angular position (71%), stride percentage (18%), age (2.7%), walking speed (1.7%), and height (1.2%) had the greatest impact on predictions.These results acknowledge the conclusions of previous work on the non-necessity of EMG data and qualify the contribution of other previous work of taking into account the subject's walking speed and anthropomorphic data with gait kinematic and dynamic data. What's more, these results, based on a more representative and homogeneous dataset than some previous work, suggest that there may be informative redundancies between these anthropomorphic features that the model could ignore to be leaner.In the end, this joint torque estimator integrating gait speed and the subject's anthropomorphic data while dispensing with EMG data, yields customized results that are sufficiently accurate and robust to be used in ankle exoskeleton controllers to help to achieve better gait assistance than average profiles with a few mechanical sensors.

Thomas Mokadim, Franck Geffard, Aurore Lomet, Bruno Watier

Conference Proceedings

Commute time analysis using mobile location information

In this paper, authors indicate that 95% of the South Korean population owns a mobile device. Telecom providers can collect an individual's location data at short intervals by utilizing communication information from their mobile devices. By continuously tracking daily location data, it is possible to estimate an individual's residential location, employment status, and workplace location. Based on residential and workplace locations, the purposes of trips—such as commuting, work-related travel, leisure, and returning home—can be inferred.This study develops a methodology for constructing a personal trip chain database (DB) that includes trip purposes using mobile location data and analyzes commuting conditions by city in South Korea. It examines factors such as the average commuting time, standard deviation, and the proportion of individuals experiencing poor commuting conditions based on city-specific commuting time distributions. Additionally, it analyzes urban commuting self-sufficiency levels based on the consistency between residential and workplace locations.By assessing the commuting environments of those with particularly challenging commutes, this study aims to propose transportation infrastructure investment policies (SOC) to improve travel conditions.

Juyoung Kim

Conference Proceedings

Creating Safer Learning Environments Through Universal Design for Learning Framework

Ensuring the safety and security (S&S) of learning environments remains a critical concern, even in the Nordic region, including Finland, recognized as the world’s happiest country in 2024 for seventh year in a row. Scholars highlight poor psychosocial climate as a key factor contributing to unsafe school environments. This paper explores how the Universal Design for Learning (UDL) framework can enhance S&S from a psychosocial perspective. The study examines factors that contribute to unsafe learning environments, situating the analysis within existing literature and applying a UDL-based approach. Findings indicate that social atmosphere, physical space, lack of security, and cognitive challenges negatively impact the psychosocial environment, potentially leading to serious incidents. By integrating UDL principles—such as technology adoption, flexibility, accessibility, and improved spatial design—schools can foster safer and more inclusive environments. This paper offers a novel perspective by linking UDL to school S&S, demonstrating how its principles can help create more supportive educational settings that address diverse student needs.

Timo Savolainen, Terhi Kärpänen

Conference Proceedings

Integrating Model-Based Systems Engineering and Stakeholder-Driven Design Exploration: A Virtual Reality Approach for Early-Stage System Development

The integration of design, human factors engineering, and Systems Engineering (SE) is an important approach to improving the efficiency and consistency of technical development processes. In practice, these disciplines are often separated, creating challenges in the early alignment of system requirements and human factors. This study investigates the combination of Model-Based Systems Engineering (MBSE) with a Stakeholder-Driven Design Exploration to enable a closer integration of these disciplines. The development of a blind spot assistance system for vehicles is considered as a use case. Various design elements of the system are visualized as part of a virtual reality (VR) design framework. Design decisions influenced by participants are captured in an SE model representing the solution architecture of the assistant system. This enables immediate adaptation of system requirements and design elements, making the development process more iterative and recursive. The methodology described here will accelerate product development cycles, particularly in the early concept phase. By directly considering stakeholder feedback in the system model, potential weaknesses can be identified at an earlier stage and optimizations can be made in the concept phase. The study shows how the combination of MBSE with an interactive, stakeholder-driven approach in VR will increase development reliability to streamline entire engineering process.

Sarah Rudder, Michael Preutenborbeck, Paul Weiser

Conference Proceedings

Digital vulnerabilities and the oldest-old

While physical and cognitive degeneration can limit older citizens from accessing beneficial digital services (Heponiemi et al., 2023), many lead digitally active lives well into their oldest years. However, those who are more digitally active may be susceptible to fraudulent behaviour, through such life circumstances as loneliness (Liao et al., 2024). In this paper we will build upon a study undertaken with two groups of pensioners, firstly with those aged 70-79, or “Young-Old” combined with “Middle-Old” which investigated how their characteristics and the way they make decisions can increase their susceptibility to digital deception. In this new study we are concerned with understanding how vulnerable our most senior, and often frailest, citizens, or the “oldest-old” feel towards their vulnerability to digital fraud, and the potential negative effect on happiness and quality of life. According to Vincent (2023, pp. 36-37) this age group has often been “ignored” in studies, becoming “invisible”, or treated separately from younger groupings. despite the increasing numbers living to an older age, of containing many of those adopters of digital technology Wu & Gu (2021) discuss how although there is lack of consensus on the age bandings within the “fourth age”, the category “oldest-old” often refers to digital usage, those over the age of 85 in developed economies, while over 80 in developing economies. In this study, we distinguish between two age groups: Group 1 (70–79 years old) with 273 respondents, and Group 2 (80+ years old) with 111 respondents. All respondents reported whether they had experienced identity theft, credit card misuse, or a similar fraud incident. The percentages for the two groups were 23% and 22%, respectively. Has experienced fraudHas not experienced fraudAge 70-79 years old23 77Age 80+ 22 78The questionnaire included three quality-of-life questions, measured using a Likert scale ranging from 0 to 10. For the statistical analysis, responses were categorized as follows: scores of 0–5 were classified as low, 6–7 as medium, and 8–10 as high. Descriptive statistics, presented in the table below, indicate that the oldest-old respondents who had experienced fraud had a lower overall quality-of-life score compared to the middle-old respondents.Quality of life indicators Meaningful life Life satisfactionHappiness in life % reported low % reported low% reported lowAge 70-79, Has experienced fraud or misuse of information11 14 27Age 80+, Has experienced fraud or misuse of information21 17 50 In this paper, we will present a binary logistic regression analysis to identify significant predictors for experiencing fraud versus not experiencing fraud, comparing the middle-old and the oldest-old age groups.ReferencesHeponiemi, T., Kainiemi, E., Virtanen, L., Saukkonen, P., Sainio, P., Koponen, P., & Koskinen, S. (2023). Predicting Internet Use and Digital Competence Among Older Adults Using Performance Tests of Visual, Physical, and Cognitive Functioning: Longitudinal Population-Based Study. J Med Internet Res, 25, e42287. https://doi.org/10.2196/42287 Liao, S., Wang, X., & Zhang, X. (2024). Loneliness could lead to risk of fraud victimization for middle-aged and older adults. Journal of Elder Abuse & Neglect, 36(5), 508-527. Vincent, J. (2023). Life stage or Age? Reviewing perceptions of oldest digital technologies users. In Digital Ageism (pp. 36-52). Routledge. Wu, Q., & Gu, D. (2021). Oldest-Old Adults. In D. Gu & M. E. Dupre (Eds.), Encyclopedia of Gerontology and Population Aging (pp. 3637-3653). Springer International Publishing. https://doi.org/10.1007/978-3-030-22009-9_1121

Chris Wales, Ingvar Tjostheim

Conference Proceedings

Emotion-Based Memory and Decision System for Non-Humanoid AI Agents

This study proposes an emotion-driven memory and decision-making system for non-humanoid AI agents. The system models emotional perception, memory retention, and behavioral decision-making through lightweight rule-based mechanisms. Detailed system architecture and experimental results will be updated.

Zhibing Lin

Conference Proceedings

Exploring User Behavior and Validation Proficiency in Assessing Responses from a Conversational Agent

Large‐language–model (LLM) chatbots are rapidly becoming everyday information sources, yet little is known about how ordinary users verify their accuracy, especially in high-stakes domains such as health. This study investigates how and how well people validate ChatGPT’s answers when they can, or cannot, consult complementary web search results. Understanding these behaviors is essential for designing conversational systems that actively support responsible use rather than amplify misinformation.We conducted a within-subjects study with fifteen participants (7 women, 8 men, aged 22–27) recruited on a U.S. university campus. The topic space was deliberately unfamiliar but consequential: the 30-item Alzheimer’s Disease Knowledge Scale (ADKS). For each item, GPT-3.5-turbo produced a true/false response (93.33 % correct, 6.67 % intentionally incorrect). Participants completed two phases over Zoom (mean duration ≈ 67 min). Phase 1 displayed only the ChatGPT answer. Phase 2 added ten pre-collected, fully clickable Google snippets beside the same answer. Snippets were retrieved with Google Custom Search API using (a) the full question and (b) automatically extracted keywords; cosine similarity scores (BERT) were shown to signal textual overlap.Behavioral data (selection of “Correct”, “Incorrect”, or “I’m not sure”), click logs, and per-item decision times were recorded. Validation proficiency was quantified with precision, recall, F1, and the underlying counts of true/false positives and negatives. Normality was checked with Shapiro–Wilk tests; paired t tests or Wilcoxon signed-rank tests were applied accordingly. Semi-structured questionnaires before and after the task captured self-reported search habits and perceived usefulness of the two snippet types; open responses were thematically coded.Access to search results significantly improved recall from 0.70 (SD 0.10) in Phase 1 to 0.77 (SD 0.14); t₁₄ = –2.35, p = .034, d = 0.60. Participants therefore overlooked fewer correct answers (false negatives decreased from 8.40 to 6.33). F1 rose modestly from 0.80 to 0.84 (n.s.), while precision showed a non-significant downward trend because false positives increased (1.00 → 1.47; p = .052). Mean validation time per item doubled (38.7 s → 82.0 s), indicating higher cognitive effort. Link-click analysis revealed that deeper information gathering correlated positively with precision (r = .53) and true-negative detections, whereas superficial inspection fostered over-acceptance of incorrect answers. Qualitative feedback confirmed that participants prized authoritative domains (e.g., NIH, Mayo Clinic) and preferred question-based queries over keyword queries (86 % vs 20 % “very useful”). Nevertheless, two intentionally erroneous ChatGPT statements about rare recovery and tremor symptoms remained widely believed, showing that additional context does not automatically resolve misconceptions.Our findings highlight the limitations of simply adding external information sources without guidance. While users benefitted from authoritative links, they still struggled with vague expressions and misunderstood incorrect answers. Future work may explore design solutions such as more structured presentation of search results, interactive validation support, or automated detection of vague or misleading language in LLMs. Additionally, some participants found keyword queries unhelpful, suggesting that query design and information literacy training may play an important role.

Jiayin Huang, Jonggi Hong

Conference Proceedings

The influence of Chinese calligraphy on cultural and creative product design: A perspective of emotional preferences

Chinese calligraphy, inscribed in the UNESCO Intangible Cultural Heritage list, is one of China’s most significant contributions to world civilization. It is possible to uncover the emotional expressions embedded in the creator’s writing process by capturing the visual perception of calligraphy. This provides a valuable approach for understanding consumer preferences in the design of cultural and creative products. Based on these insights, designing products can not only enhance their cultural attributes but also position them as new mediums for promoting Chinese calligraphy.This research, grounded in the theories of visual perception and emotional expression, focuses on the character "永" as the central theme. It uses four visual styles from prominent Chinese calligraphers—Wang Xizhi, Su Shi, Huang Tingjian, and Mi Fu—known for their distinctive xingshu (semi-cursive script). These styles serve as prototype samples for analysis. By employing affective engineering measurement methods, the study quantifies consumer preferences and emotional responses to these calligraphic styles, providing an empirical analysis of how different calligraphic forms influence consumers’ emotional preferences.The results of this study will offer valuable insights for cultural and creative product designers, helping them understand individualised consumer preferences from the perspective of calligraphic style. This understanding will enable designers to use new technological approaches to create culturally relevant and aesthetically appealing products. By integrating these insights into product design, the study aims to advance the precise design of cultural products and promote Chinese calligraphy, thereby enhancing its cultural significance through modern design practices.

Cheng Ma, Huajie Wang

Conference Proceedings

How to Design an Operation-Specific LLM-Based Information System

The performance of large language models (LLMs) has improved significantly in recent years, with the result that they are now used in many companies in various industries. However, the design of a company-specific information system involving an LLM is associated with a large number of decisions. This leads to a high level of complexity in the design task. Against this background, companies need a structured approach that methodically supports the planning, development, implementation and long-term maintenance of LLM-based information systems so that domain- and company-specific requirements are taken into account as a result. This article therefore describes a method that supports the design, introduction and maintenance process of an LLM-based information system. The method consists of a process model and a list of design principles, which are also referred to as success factors. The process model developed is based on the proven six-stage REFA planning system. To identify and describe success factors, a systematic literature search was carried out. Based on an analysis of the contents of individual literature sources, success factors for the design of LLM-based information systems were identified. These success factors relate, for example, to the quality of the data provided, data security, user-centered system design and feedback mechanisms for improving information output.

Sven Hinrichsen, Robin Herbort, Dominik Green, Benjamin Adrian

Conference Proceedings

Propensity Matters – An Empirical Analysis on the Importance of Trust for the Intention to Use Artificial Intelligence

There is a growing need for scientific knowledge about the extent to which the results of artificial intelligence (AI) and the effects of its use can be considered trustworthy. Accordingly, user experience can lead to trust in AI being too low or too high, which could result in its misuse. Especially as trust is considered subjective and could be seen as a heuristic, which in turn would speak in favor of the importance of trust in AI, as the underlying algorithm is not transparent to the user in so-called black-box models. In this context, the call to enhance the transparency of such models to increase trust seems contradictory. There is no common theory, but Lee and See's (2004) model of trust in automation is often used as a basis for research, since automation can be seen as the foundation of AI. However, it remains unclear whether this model can be adapted to AI. Therefore, this study investigates which factors influence trust in AI in the context of ChatGPT and how this affects the intention to use. On this basis, a conceptual path model was derived and tested using path analysis. Data were collected from 105 students using validated questionnaires. The empirical path model shows the expected positive influences, with one exception. In addition, the results emphasize that the role of the propensity to trust is central. Furthermore, the significant influence of trust on intention to use is weaker than supposed. While the results largely align with existing assumptions, they simultaneously introduce new insights.

Jona Karg, Frank Ritz, Petra Maria Asprion

Conference Proceedings

Personality Traits in 12 Countries Defined by the ‘Big Five’ are Found to Have a Culture Dependency: Implications for Modeling Citizens’ Personalities

This study critically evaluates the reliability and validity of the widely used Five Factor Model (FFM) or 'Big Five' personality traits framework across 12 Latin American countries. Conventional psychometric assessments based on factor analysis have significant methodological limitations when applied to categorical data. Addressing these concerns, we employed a Bayesian statistical approach utilizing Dirichlet and Beta distributions for categorical responses obtained from 5,175 participants who completed the IPIP-R questionnaire. Our novel methodology includes Monte Carlo simulations, confusion matrices, and probability density function estimations, effectively compensating for inherent sample size imbalances. Findings demonstrate substantial cultural variations in the distribution of personality traits, contradicting the presumed universality of the FFM. Additionally, notable differences were observed between male and female respondents, influenced by nationality. Furthermore, natural language processing techniques combined with the UMAP dimensionality reduction algorithm revealed that linguistic clustering of questionnaire items does not explain cultural differences. Our results demonstrate the inadequacy of factor analysis for analyzing categorical psychometric data, necessitating instead rigorous Bayesian methods. This study significantly impacts how personality assessments should be utilized in policymaking, corporate environments, and artificial intelligence applications, emphasizing the necessity of culturally sensitive and statistically robust approaches. The outcomes are discussed in relation to creation of citizen profiles and advanced personality modelling.

Hermann Prossinger, Silvia Boschetti, Tomas Hladky, Daniel Riha, Martin Stachon, Jan Slavik, Jakub Binter

Conference Proceedings

From Paper to Pixels: Transferring Handwritten Note-Taking Into Virtual Reality

While in the past, Virtual Reality and Augmented Reality needed hardware dedicated exclusively to one or the other, newer Virtual Reality headsets like the Meta Quest 3 combine both functionalities in one. This opens up possibilities to more easily implementable applications that use a combination of VR and AR, namely Augmented Virtuality, where a mostly virtual world is augmented with parts from the real one. We explore the possibilities that Augmented Virtuality can offer to enhance VR applications both from a theoretical perspective on the example of VR in driving automation and by offering a concrete prototype for note-taking in VR. This prototype, PaperVR, uses augmented virtuality concepts to enable handwriting on real paper inside a virtual environment. For that purpose, the front-facing cameras of a Meta Quest 3 were used, together with the MetaXR plugin, to create a tracked passthrough window, revealing the physical paper inside the virtual environment. As a point of comparison, a second prototype was developed which is intended to represent the current standard in handwritten VR note-taking, namely tablet writing. A user study was conducted, to compare both prototypes with each other and their equivalent writing methods outside of VR. It shows that paper writing is superior to tablet-based writing in VR for a synthetic task in our study. Additionally, in a practical note-taking task, it was possible to reach the same objective results inside VR as using physical writing outside a virtual environment, both regarding the number of correct answers and the answering speed per question.

Paul Weiser, Sebastian Pape, Daniel Rupp, Frank Flemisch

Conference Proceedings

EchoXR: A Collaborative VR Framework for Spatial Acoustics in Architectural Design

This paper introduces EchoXR, a multiplayer Virtual Reality (VR) framework enabling real-time, collaborative exploration of architectural acoustics. By leveraging advanced tracking and spatial audio technologies, participants can co-experience how design changes—such as adding absorptive panels, altering partitions, or varying materials—impact the acoustics of a virtual environment. Although acoustic simulations often require extensive processing time, EchoXR integrates optimized algorithms with VR’s immersive capabilities to deliver a realistic acoustic performance in real time. Notably, users can hear each other’s voices auralized according to the simulated acoustic conditions, providing an immediate, immersive sense of how proposed design modifications affect speech intelligibility and influence overall noise level in the space. .The system supports multiple concurrent users, allowing designers, clients, and stakeholders to engage in synchronous, spatially coherent discussions. Through intuitive 3D user interfaces, participants can collaboratively adjust design elements and instantly perceive the resulting acoustic effects. This shared acoustic experience fosters more informed decision-making, minimizing the need for costly late-stage interventions or hastily added acoustic solutions that can disrupt the overall design concept and function of the space.The preliminary implementation demonstrates the feasibility and potential of collaborative VR auralization for architectural design workflows. By facilitating a deeper understanding of acoustics in the early design phase, EchoXR underlines the transformative role immersive technologies can play in shaping the future of built environments.

Fabio Scotto, Chia Hsuan Chao, Giacomo Montiani, Achilleas Xydis, Fabio Gramazio, Matthias Kohler

Conference Proceedings

Construction machinery work support system using mixed reality

Although the number of fatal and injured accidents in the construction industry has decreased in recent years, they are still high compared to other industries, and ensuring safety at construction sites is an important issue. Construction sites are complex and dangerous working environments, and workers from different industries often have to work together. In addition, changes in work methods and procedures may occur due to design changes, bad weather, delays in work in other trades, and shortages of equipment and labor. In order to ensure safety and resume work, it is necessary to report the change in work method to the construction supervisor and adjust and discuss the changed work method. Meanwhile, the construction industry is also promoting the digitalization of work and the use of smart devices as DX (digital transformation). One of these is to provide rapid and accurate technical support even in the event of a wide-area disaster by grasping the local situation from a remote location without having to go directly to the disaster site. In addition, in order to improve work efficiency, attempts are being made to apply remote presence to work that previously required attendance. In this study, we developed a human-machine system that visually displays instructions from a site supervisor to workers using mixed reality (MR), that is, an MR work instruction presentation system, with the aim of quickly and accurately conveying complex instructions to workers while working with construction machinery, which has been difficult to convey while working. By using this system, arrows and construction drawings can be superimposed on the worker's field of vision, making it possible to easily and accurately convey detailed instructions such as the location to crush with construction machinery, the position to grab, and the transport route of the transported items. In this study, we built a construction machinery work support system using Microsoft's HoloLens and conducted subject experiments using an actual machine.As a method of presenting work instructions using MR for the transport and stacking work of blocks by construction machinery using this system, we proposed four methods: A) work instructions using only drawing processing, B) work instructions using drawing processing and text, C) work instructions using drawing processing and voice, and D) work instructions using animation.In the experiment, block transport and assembly work was performed using the four proposed work instruction presentation methods, and the optimal instruction presentation method was examined based on the work time, mental burden using NASA-TLX, and a questionnaire survey. As a result, it was confirmed that using this system to give work instructions shortens the time required to operate construction machinery and is also effective in reducing the mental burden on NASA-TLX. In addition, it was found that of the four proposed methods of presenting work instructions, the most effective methods were the method using drawing processing and voice, and the method using animation. These results are believed to be useful for the development of a human-machine system that visually displays instructions to workers.

Hironao Yamada, Satoshi Ueki, Takahiro Ikeda

Conference Proceedings

Synesthetic Design and Intangible Heritage: Mixed Reality as a strategy for preserving and promoting endangered traditions

Intangible heritage is the name given to practices, expressions, different knowledge, and skills that several communities recognize as being part of their cultural identity. This includes aspects such as traditions, oral histories, rituals, performing arts, and craftsmanship passed down through generations. Intangible heritage, unlike its tangible counterpart, cannot be materialized. However, it plays a unique role in enhancing and deepening cultural diversity. More importantly, it fosters a sense of belonging, underlining the significance of preserving these living traditions. Intangible heritage now faces threats such as lifestyle changes, urbanization, and the decreasing interest of new generations in traditional cultural manifestations due to digital advancement and the influence of globalized companies.Intangible heritage, unlike its tangible counterpart, cannot be materialized. However, it plays a unique role in enhancing and deepening cultural diversity. More importantly, it fosters a sense of belonging, underlining the significance of preserving these living traditions.Studies state that virtual museums and platforms are effective in promoting intangible heritage and that technologies such as virtual and augmented reality provide effective experiences for its dissemination and preservation. However, limitations persist due to the predominant focus on audiovisual senses, neglecting others such as smell, taste, touch, proprioception, kinetic, vestibular, and thermal, limiting the user experience.Virtual and augmented reality are technologies that make it possible to experience a virtual world and add layers of information to the real one. Virtual reality (also known as VR) makes it possible to create an immersive digital environment where users can interact using audiovisuals such as VR goggles. Augmented reality (AR) allows digital elements to be added and superimposed to the real-world using devices such as smartphones or special glasses, providing an enriched perception of the natural environment. While VR offers users an entirely new experience, AR complements existing reality by integrating information and virtual elements in an interactive and visually appealing way, and both technologies have applications in gaming, education, training, and entertainment. However, being focused on the audiovisual senses, they leave other senses unstimulated, neglecting the ones such as smell, taste, touch, proprioception, kinetic, vestibular, and thermal, limiting the user experience.This study explores how, through synesthetic design, a multi-sensory approach can be conceived for virtual and augmented reality experiences. It uses robotics to stimulate different senses and analyse its impact on immersion and acquiring knowledge related to intangible heritage. It also aims to investigate how robotics can be used for sensory stimulation, what senses can stimulate, how they can be integrated into the immersive experience, and how this practice can be used to preserve intangible heritage.The results obtained will help to define synesthetic design practices, integrate the analyzed technologies into the preservation and dissemination of Portugal's intangible heritage and serve as a reference for future projects related to both synesthetic design and sensory stimulation practices.

Joao Dias, Ana Luisa Marques, Pedro Costa

Conference Proceedings

Evaluating a Refined Augmented Reality Eye-Gaze and Voice Control System for Electric Wheelchairs: A User Study

Self-determined mobility is fundamental for social participation, yet conventional electric wheelchair controls present significant usability challenges for individuals with severe motor impairments like tetraplegia or ALS. While alternative specialized controls exist, they may introduce issues such as fatigue or reduced intuitiveness. This paper reports on the user evaluation of a refined assistive control system, previously introduced as work-in-progress, designed to address these limitations. The system employs a combination of eye-gaze tracking and voice commands, mediated through a Magic Leap 2 Augmented Reality (AR) headset, to operate both a wheelchair simulator and a real electric wheelchair via a Raspberry Pi interface. Initial prototypes highlighted the need for enhancements focused on user experience, control stability, and intentionality, particularly for real-world deployment. The evaluated system incorporates several key refinements: (1) A robust activation mechanism requiring sustained gaze within the interface boundaries for a defined duration to enable control, complemented by a configurable grace period upon gaze exit to prevent unintended deactivation during brief glances away. (2) Advanced stability features, including Kalman filtering or iterative Slerp smoothing of gaze rotation data to mitigate input jitter, alongside head rotation handling that detects high angular velocity to trigger a brief, timed recentering of the joystick input upon cessation, preventing uncontrolled continuation of turns. (3) Fine-tuned control mapping, utilizing non-linear response curves, minimal dead zones, sensitivity scaling, and output signal rate limiting to ensure smooth command delivery, provide fine control near the center, and prevent overly sensitive physical responses. (4) Raycast-based interaction logic for axis-snapping guide cubes and focusable object detection, replacing previous methods.The primary objective of this study was to comprehensively evaluate the usability, effectiveness, perceived workload, and user acceptance of this refined control system. The evaluation was conducted with individuals with spinal cord injuries at the BG Klinikum Hamburg. We aimed to assess the system's potential as a viable supplement or alternative to existing specialized wheelchair controls.A two-phase methodology was employed: participants first engaged with the system in a VR wheelchair simulator for familiarization and baseline assessment, followed by operating a real Ottobock Juvo B5 wheelchair using the AR interface in a controlled clinical environment. Tasks included fundamental maneuvers (activation/deactivation, forward/backward driving, turning in place), navigation along a simple marked path, and precision approach tasks. Data collection utilized a mixed-methods approach, combining objective performance metrics (e.g., task time, errors), standardized subjective questionnaires (System Usability Scale - SUS; NASA Task Load Index - NASA-TLX), and qualitative feedback via semi-structured interviews and direct observation, adhering to approved ethical guidelines.This paper presents the detailed findings from these user tests, focusing on the performance differences between VR and AR conditions, the perceived usability and workload associated with the system, the effectiveness of the specific activation and stability refinements, and overall user acceptance. The results provide empirical insights into the practical application of AR-based eye-gaze and voice control for wheelchairs, identifying strengths, limitations, and crucial areas for future development to enhance autonomous mobility for individuals with severe motor impairments.

Jendrik Bulk, Benjamin Tannert

Conference Proceedings

A scalable MR-training system to prepare military and civil experts for crisis areas

The goal of the EU’s Common Security and Defence Policy (CSDP) is strengthening the civilian and military crisis management. Optimally prepared personnel are essential to efficiently meet security challenges and actively work towards conflict prevention and peace keeping. Several EU initiatives and training institutions across EU Member States help prepare personnel for these challenges. Involved stakeholders are civilian, military, and police personnel as well as representatives of government institutions and non-governmental organisations (NGOs). In crisis situations, effective collaboration among stakeholders is vital. Deployed personnel require extensive skills including monitoring, mediation, situational awareness, intercultural competence and first aid skills. Personnel deployed in crisis zones are required to make decisions under extreme stress. Currently, training programs typically combine theory with practical components such as role plays and simulation exercises. However, real-world simulations often fall short of realistically replicating crisis scenarios due to organizational and financial constraints. Additionally, especially dangerous situations cannot be safely recreated, further limiting the realism and effectiveness of such training. Virtual and mixed reality technologies offer promising new possibilities for simulating crisis areas and for training personnel in a realistic and immersive way. Such technologies allow personnel to engage in training with minimal logistical burden. They provide scalable, cost-effective, repeatable and immersive training, reducing dependency on large-scale physical simulations. SkillDrill provides an innovative MR framework, providing learning modules to develop and train essential skills such as mission planning, situational awareness, map reading and advanced first aid for self-aid and buddy care, in an immersive way. Depending on the trained skill, the system offers different layers of immersion (digital, VR, MR). Building upon the results of the end-user requirements and methodologies described in (Broneder, 2024), this paper will describe the current state of the SkillDrill system as well as the first results of the end user tests.

Elisabeth Broneder, Christoph Weiß, Jaison Puthenkalam, Youssef Ibrahim, Markus Karlseder, Daniela Weismeier-sammer, Nathan Coyle, Monika Psenner, Astrid Holzinger

Conference Proceedings

Experiences of Nursing Students from Using an Omnidirectional Pad vs Touch Controllers to Navigate a Virtual Clinical Simulation

While immersive virtual reality has improved over the years, researchers are still seeking to create more realistic experiences for healthcare and nursing students' education to enable better immersive experiences. Methods: Forty-six undergraduate nursing students were exposed to a foreign body object scenario. The students' experiences were gathered using observations and retrospective think-aloud. The qualitative data was also quantitatively summarised based on the issues (negative findings) and findings (positive findings). Results: While the touch controllers seemed superior in almost all themes identified, the cybersickness category was much higher than for the omnidirectional pad. There were also controversial experiences between students for both navigation techniques.Conclusion: While the omnidirectional pad had more issues than the touch controllers, students found it fascinating, and it seemed to have a lower onset of cybersickness than the touch controllers. Students did, however indicate that the Omnidirectional pad might need improvement to become more realistic as it still did not feel completely realistic.

Benjamin Botha, Lizette De Wet

Conference Proceedings

Virtual Reality Sensory Rooms: A Tool to Reduce Anxiety in Autistic Adults

With the current rise in autism diagnoses and the resultant strain on mental health services, it has become increasingly necessary to consider anxiety management techniques for autistic adults that are not reliant on a large amount of resources, both financial and physical. Furthermore, the current increase in availability of virtual reality headsets on the commercial market brings increased interest in applications for virtual reality for purposes beyond gaming. Previous success has been shown by other researchers in the use of virtual reality sensory rooms to reduce anxiety in patients of residential facilities, however these studies were not solely focussed on autism, and focussed on those in a residential setting. As such, it was deemed important to focus on autistic participants and examine the effectiveness of such a program for autistic adults who are not in the position to require residential care facilities. Therefore this work aims to explore the effectiveness of an emulated sensory room in virtual reality by examining the STAI data and heart rate data of a 29 person study.

Katie Potts, Phillip Smith, Mohammed Bahja

Conference Proceedings

The early detection of pressure ulcers, an optimized movement monitoring through machine learning and wearable sensor technology

This study investigates how machine-assisted motion analysis can contribute to the prevention of pressure ulcers in bedridden patients.Pressure ulcers, also known as bedsores, develop due to prolonged pressure on the skin and underlying tissues, which impairs blood circulation. Without sufficient movement and regular repositioning, affected areas may no longer receive adequate oxygen and nutrients, ultimately leading to tissue damage and open wounds. Immobile patients are particularly at risk, as their prolonged inactivity significantly increases the likelihood of developing pressure ulcers. The early detection of critical movement patterns is therefore essential to initiate preventive measures such as repositioning or targeted positioning strategies in a timely manner. The objective of this study is to define a movement threshold using machine learning algorithms that distinguishes between insufficient, adequate, and excessive movement. Both continuous and interval-based classification methods are employed to identify patterns associated with an increased risk of pressure ulcers. Additionally, skin temperature variations are incorporated into the analysis, as they may indicate reduced blood circulation—an important early warning sign for pressure ulcer formation. To capture movement data, the Pixel Watch 3 is used as a wearable sensor technology. The smartwatch is attached to the patient's body to enable a more precise detection of movement patterns. Various positions are tested to determine which placement provides the most reliable sensor data regarding patient mobility and positional changes. This analysis aims to identify the optimal smartwatch placement for achieving the most accurate classification results. Several sensors are utilized, including an accelerometer to measure movement intensity, a gyroscope to detect rotations, a posture sensor to track positional changes, a skin temperature sensor to assess blood circulation variations, and a heart rate sensor to capture physiological responses. The smartwatch is tested in three positions: chest, abdomen, and ankle. A total of 10 participants are included in the study. Five micro-movements have been identified, and for each of these movements, 20 labels are generated per participant, each lasting 10 seconds. The data collection is conducted at a sampling rate of 20 Hz. This results in a total of 14 (sensors) * 10 (participants) * 20 Hz (sampling rate) * 10 seconds (label duration) * 20 labels (number of labels) * 5 movements (micro-movements) * 3 positions (chest, abdomen, ankle) = 8,400,000 data records.The collected movement data is used to develop a machine-learning model that detects movement deficiencies at an early stage and automatically alerts caregivers before critical situations arise. The model distinguishes between sufficient, insufficient, and excessive movement, enabling targeted interventions. The study results demonstrate that the Pixel Watch 3 can be utilized as a precise monitoring tool, allowing for continuous movement tracking. Such a system could significantly contribute to reducing the workload of healthcare professionals by facilitating targeted interventions while simultaneously improving the quality of patient care. This study provides a vital foundation for the future development of intelligent care systems that not only optimize pressure ulcer prevention but also enhance the efficiency and accuracy of nursing documentation through wearable sensor technologies and machine learning. Furthermore, the system is tested in an experimental setting to evaluate its practicality and effectiveness. The goal is to obtain a realistic assessment of how well the model can be integrated into real-world nursing practice and to determine what adjustments are necessary for its optimal implementation within existing care structures.

Sergio Staab, Nadia Günter, Vincent Abt, Johannes Luderschmidt, Ludger Martin

Conference Proceedings

Enhancing trucker well-being: The role of cabin features and technology acceptance

Long-distance truck drivers face unique occupational challenges. The demanding nature of their job, characterised by extended periods of isolation, irregular schedules, and physical strain, contributes to higher levels of stress, health issues, and reduced well-being compared to other professions. This exploratory study examined drivers' perceptions of cabin features impacting well-being, as well as their acceptance of technology that measures physiological parameters to enhance well-being through an affect-adaptive system. 24 randomly selected long-distance truck drivers (23 male, 1 female) were interviewed at German motorway service stations. Participants were aged between 30 and 65 years (M = 49, SD = 10) with an average of 19 years of professional driving experience (SD = 13, range: 1.5 to 41 years). The participants drove trucks from six different brands, reflecting a diverse range of vehicle manufacturers. The interviews revealed that comfort, cooking equipment, and cabin size were the most positively highlighted factors. 38% of participants reported no negative cabin features. Among those who identified negative factors, poor truck or cabin amenities (21%) and discomfort related to seats and beds (13%) were frequently mentioned. Improvements to seating and sleeping comfort were the most commonly requested changes, alongside enhancements to entertainment, cooking, and storage features, as well as safety and driver-assistance systems. A majority of drivers (75%) were in favour of using gadgets to improve well-being, with smartwatches (80%) and driver-facing cameras (63%) being the most accepted, while chest straps were the least favoured (15%). Approval for personalised music and entertainment was high, but lower when auto-adaptive selection of content was proposed. Personalised lighting and time-based adaptive lighting were favoured, while mood-based adaptive lighting was less popular. These findings provide valuable insights into factors influencing driver well-being and are discussed with respect to leveraging tech gadgets to design improved future truck cabins.

Sebastian Pfau, Joel Rüttger, Sven Fuchs, Franziska Seifert, Cosima Von Uechtritz, Alina Schmitz-hübsch

Conference Proceedings

Evaluating Automated Gaze Mapping Across Laboratory and Field Study Settings

Eye Tracking (ET) is used in different industries to understand human visual attention, cognitive load, and decision-making processes by capturing where, and for how long a person focuses their attention. A major challenge in processing ET data is mapping gaze points to dynamic Areas of Interest (AOIs) while accounting for data variability and head movements. The purpose of this research is to compare and evaluate methods for automatic gaze-to-AOI mapping to improve efficiency and accuracy in gaze analysis. An ArUco-marker based analytical software was developed to automate gaze mapping to AOIs based on three methods for data collected in laboratory and field settings. The methods are (1) marker-based mapping, and homography-based mapping using either (2) manual-defined reference points or (3) feature detection. All three methods are compared against two baselines: manual gaze mapping and assisted mapping using a commercial software. Overall, the results show that the performance of automatic mapping methods is highly dependent on the setting and AOI configurations. Under laboratory conditions, all automated gaze mapping methods achieved accuracy (97%) and F1-scores (97%) comparable to manual mapping. In complex field study settings, the performance varied, and accuracy is reduced ranging from 14% to 77% depending on the setting due to varying conditions regarding sudden transition in lighting and real-time dynamics of the situation. The marker-based method demonstrated consistently high accuracy across all settings. Depending on the environment, the manual reference point-based homography mapping occasionally demonstrated superior accuracy. Manual mapping remained the most accurate in field study conditions but required significantly more processing time. Future work will focus on enhancing the method’s robustness in dynamic environments based on adaptive reference image selection. This will increase accuracy of gaze-to-AOI mapping and set the stage for real-time monitoring of visual attention in complex, safety-critical contexts. This advancement will foster the development of resilient, adaptive human-machine systems that dynamically respond to operator conditions, significantly reducing the likelihood of human error and enhancing overall performance.

Celina Vetter, Rebecca Nauli, Ruth Häusler Hermann, Maarten Uijt De Haag

Conference Proceedings

Intelligent Elbow Exoskeleton Control: A Neural Network-Based Framework for Optimized Performance

Elbow exoskeletons have emerged as promising technologies in the field of wearable robotics, offering assistance and support for tasks involving elbow flexion and extension. Musculoskeletal disorders associated with the elbow are prevalent in occupational environments, leading to work-related injuries and discomfort. Active elbow exoskeletons with integrated sensors, actuators, and control boards have been proposed to mitigate these issues by reducing joint strain and supporting repetitive tasks. The design and control of elbow exoskeletons are essential to ensure effective assistance, user comfort, and operational safety. Key design considerations include joint alignment, adaptability to real-world tasks, and intuitive user interaction to enhance usability and acceptance. Although current control strategies have made significant progress, they still require improvements in terms of user adaptability, feedback responsiveness, robustness, energy efficiency, and dynamic assistance. This study introduces a comprehensive methodological framework to optimise control strategies in the ExoElbow. The primary focus is on adapting assistive responses to individual user needs through real-time adjustments using advanced neural network architectures. Neural networks enable the system to learn from user inputs, adapt to feedback, model dynamic behaviours, and personalise assistance strategies. Convolutional Neural Networks are used to extract spatial features from sensor data, providing insights into user movement patterns and environmental cues while supporting energy-efficient computation. Recurrent Neural Networks are employed to capture temporal dynamics, enabling predictive assistance and smooth adaptation to varying task demands, which are key for real-time, user-centred control. Together, these models support intuitive human-machine interaction, such as brain-machine interfaces, significantly enhancing the usability and responsiveness of the system. The proposed control system dynamically adjusts assistive torque levels by continuously monitoring and analysing sensory inputs, thereby optimising user experience while reducing discomfort and strain. Validation strategies, including simulation and real-world experimentation, will be used to assess performance and user satisfaction. By addressing the limitations in adaptability, intuitive interaction, and energy efficiency found in existing approaches, this research lays the foundation for smarter, more responsive assistive technologies in active industrial exoskeletons.

Mahnaz Asgharpour, Roberto Pitzalis, Olmo Alonso Moreno Franco, Luigi Monica, Darwin Caldwell, Jesus Ortiz

Conference Proceedings

Towards the Design of Transformation: a Review of Transformative VR Experiences

Within the context applied to Virtual Reality research, the present work focuses on a literature review within the emerging field of Transformative Experience Design: a domain in interaction design that aims to create experiences fostering self-actualization and self-transcendence and which relates directly to the ideas of the sublime or awe. The methodological Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) Statement was used to conduct the current review. The scientific multidisciplinary databases used for the search were SCOPUS and Web of Science. The initial search resulted in the collection of a total of 448 articles from the two aforementioned databases, of which 408 were included after the English language criterion had been applied. After eliminating duplicate studies, 304 articles remained. Here, the initial screening phase was based on reading the respective abstracts and titles, and from this excluding noticeably irrelevant studies based on the inclusion/exclusion criteria, resulting in a total of 71 articles. Of these, and after the full-text reading, 49 papers were considered eligible for inclusion in this research context.The work focuses on studies that have adopted a strongly empirical, phenomenological and qualitative approach to the creation and evaluation of transformative experiences in VR, with the purpose of finding out not only how these are being created, but also which are the main factors that enable a transformative dimension in this type of experiences. Indeed, VR seems to be explored through it´s particular phenomenological affordances as a means to advance the two fundamental dimensions of Transformative Experience Design: perceptual vastness, on one hand, and need for accommodation, on the other.Concerning the first dimension of perceptual vastness in VR experiences, different properties stood out. Firstly, the typology of the perceptual stimuli used was found to be mainly concealed between the representation of natural scenarios, and, most importantly, Earth´s view from outer space. It was also noted that environments that present an almost exaggeratedly extensive structure and where greater horizontality prevails are those that, according to this data, appear to have the best chance of fostering awe. Rather more interestingly, it has been revealed that the design of spaces and paths that present a dynamic and dramatic structure is where the sensations of awe are most prevalent, based, above all, on a feeling of surprise.On the other hand, the more epistemic dimension of need for accommodation appears to be based upon the exploration of paradoxical, supernatural, uncanny elements, mainly founded on the violation of the laws of reality and that beg for the accommodation within our current mental schemata. Truly, VR design allows for a complete inversion of these laws, and the use of fantastic and unreal elements thus finds fertile soil to then develop an experience that is deeply transformative.These results are then systematized and discussed, and further possibilities are then suggested within this context.

Bruno Giesteira, Tiago Alves

Conference Proceedings

A Biofeedback-Driven Interaction System for Real-Time Stress Detection and Intervention

This paper presents a novel prototype for a biofeedback system that uses real-time physiological data to detect task-related stress during everyday computer use, with electrodermal activity (EDA) and photoplethysmography (PPG) sensors directly integrated into a computer mouse. By continuously monitoring stress levels with this data, the system enables immediate, adaptive responses to elevated stress levels, aimed at reducing cognitive load. These responses take the form of on-screen, evidence-based mental health exercises designed to enhance user well-being. The interventions, drawn from Cognitive Behavioral Therapy (CBT) and Dialectical Behavioral Therapy (DBT), are delivered through context-aware, discreet pop-up windows that gently prompt users toward stress-reduction behaviors. An exploratory user study found that participants responded positively to the system’s ease of use, its ability to deliver timely support, and its potential to simplify self-directed mental health care through non-intrusive measures. Early findings point to strong user receptivity and validate the concept of embedding stress-responsive interventions into routine computing workflows. While further development is needed to improve personalization, comfort, and model accuracy, this work offers a compelling foundation for future systems that aim to deliver accessible, low-effort mental health support in real time.

Sofia Vaca Narvaja, Evani Dalal, Minyuan Dong, Yuxin Ni, Ian gonsher

Conference Proceedings

Improving the Accuracy for Biometrics using External Auditory Canal

The use of biometrics authentication technology has become widespread such as the face recognition is increasingly being used in the airport, hospital. If a technology with the same level of accuracy and convenience is developed in the future, it is expected to be used in a variety of fields. The purpose of this study is to improve the convenience of biometrics authentication. We are focusing on external auditory canal, which is less susceptible to the effects of the outside environment. We are conducting research and development into a personal authentication system using images of external auditory canal, and our findings underscore the fact that have the features of individual differences inside the ear canal. In the proposed method, images taken using a light source were processed to artificially enhance the red color, and the accuracy of personal identification using VGG16 was evaluated on images of both ears of 13 people. Specifically, as a preprocessing step, we created a thermography-like image from the original image and extracted the red regions from it. Using a trained model with processed image data, we evaluated the accuracy of classification, and the accuracy improved from 0.989 to 0.999. The results of this study suggest that slightly higher accuracy can be achieved than with conventional methods. The multiple image data were extracted from video data in the ear canal, and the images were classified using the representative CNN algorithm VGG16, and it was confirmed that a high level of accuracy could be achieved. In the future, we plan to verify the shortening of the learning time.

Takeshi Hamasaki, Jo Kawabata, Yujie Li, Yoshihisa Nakatoh

Conference Proceedings

Technologies for safety helmet detection on motorcycles

Motorcycle-related accidents are a major contributor to road traffic fatalities worldwide. Wearing helmets significantly reduces the risk of severe injuries and fatalities, yet compliance remains low in many regions. Helmets serve as a critical safety device, mitigating head injuries and saving lives in the event of accidents. Despite strict helmet laws in many countries, enforcement remains challenging, particularly in densely populated or rural areas where manual monitoring is difficult to sustain.The detection of inappropriate helmet use, such as wearing non-standard helmets or improperly fastened helmets, is equally critical. These issues compromise the protective benefits of helmets, underscoring the need for reliable detection systems. Traditional manual monitoring is labor-intensive and prone to human error, necessitating the adoption of automated systems. Such systems not only enhance enforcement efficiency but also act as a deterrent, promoting safer riding practices. Moreover, real-time detection of helmet usage can provide actionable data for policymakers to identify high-risk areas and devise targeted interventions.Numerous technologies and methodologies have been developed in recent years to automate helmet detection, leveraging advances in computer vision, artificial intelligence, and embedded systems. Image processing techniques have laid the groundwork for helmet detection by identifying color, shape, and texture features. Machine learning and deep learning approaches have further revolutionized this domain by enabling high-accuracy detection under varying conditions, such as different lighting, occlusions, and diverse helmet designs. These advancements have paved the way for scalable, real-time systems capable of integration with existing traffic monitoring infrastructure. This review explores the technological advancements in this domain, focusing on their technical underpinnings and real-world applications. It presents a comprehensive overview of existing technologies, emphasizing their underlying principles, advantages, limitations, and potential future directions.

María Del Carmen Rey Merchán, Antonio Lopez Arquillos, Jesús Gómez De Gabriel, Juan Antonio Fernández Madrigal

Conference Proceedings

Using the Wearable Acceptability Range (WEAR) Scale to Rate Social Acceptability of Mixed Reality and AI Enabled Head-Mounted Wearables

As head-mounted wearable technologies, including those featuring augmented reality (AR) capabilities and other integrated technologies, gain popularity, social acceptability emerges as a critical factor for their adoption. Unlike less visible tech products such as smart phones, tablets, laptops, and smart home devices, head-mounted wearables are also considered to be fashion accessories, serving as an extension of personal style and identity. Furthermore, head-mounted wearable technologies, such as AR devices, are often perceived to pose privacy and security concerns for both users and bystanders due to their ability to record, track, or display information in real-time. If a wearable device is perceived to be intrusive, unsecure, or unappealing, widespread adoption of the technology could be hindered despite its technical utility as demonstrated by several product failures ranging from earlier attempts at AR hardware to personal transportation devices.Quantifying social acceptance presents significant challenges. Unlike technical performance, social acceptability is a very subjective and nuanced metric that is influenced by factors including social norms and individual preferences. To address this challenge, the Wearable Acceptability Range (WEAR) Scale was utilized for this study to assess the social acceptability of different commercially available AR devices. Originally developed by Gilbert and Kelly (2016), the WEAR Scale measures four key factors: Design and Aesthetics, Self Expression, Consequence, and Reflection by Others. The original 50-item WEAR Scale has since been revised by Nam and Lee (2020) to a 15-item version focusing specifically on smart technology, streamlining the assessment process while maintaining comprehensive coverage of both aesthetic and functional wear across a broader range of products including wearable technology.For this study, a group of 29 participants were each introduced to four of six popular AR devices: Ray-Ban Meta, Engo 2, Xreal Air2, TCL Rayneo X2, Even Realities G1 and Apple Vision Pro. For each device, participants were walked through key device features and tasks followed by a survey using the WEAR scale to gauge their perceptions on social acceptability. Overall, the results indicated varying levels of social acceptability across the devices. The Ray-Ban Meta glasses received the highest ratings across all factors, despite being the only device that did not feature a digital display, due to its compact size and resemblance to traditional eyewear. Bulkier devices such as the Apple Vision Pro and the Xreal Air2 received lower social acceptability scores, particularly in areas related to design and their perceived impact on social interactions.The WEAR Scale proved to be an effective tool for quantitatively evaluating the social acceptability of popular head-mounted wearables. The scores for each device were highly correlated with the product size, weight, and its resemblance to traditional prescription glasses. Further research opportunities include using the WEAR Scale to evaluate products and prototypes with more subtle differences in form factor, to better understand its applicability in contexts where variations between devices are less pronounced.

Mohammad Jeelani, Michael Prieto

Conference Proceedings

Towards a Technology-Enhanced Team Coaching Framework for Higher Education

In the landscape of computer science education, there is an increasing emphasis on collaborative problem-solving and adaptability. The incorporation of coaching methodologies into computer science courses holds the potential to foster students’ teamwork and professional competencies. In this paper a coaching framework which was piloted in a bachelor-level, course on project management and developed for a Human-Computer Interaction course at a European university will be presented. The framework combines person-centered coaching approaches, agile practices, visualizations, and support via interactions with generative AI tools to support team collaboration.The Person-Centered Approach focuses on the needs of an individual through transparency, active listening, and fostering the self-directed growth thus motivation while progressing in the project. Agile practices focus on collaboration, iterative progress and adaptive feedback cycles thus leveraging constructive communication within the team. Visualizations support transparency and understanding, and generative AI helps suggesting responses whenever technical, linguistic, or other support or ideas are needed. The integration of these four complementary assets into a unified framework aims to leverage the cultivation of key professional competencies, including communication, problem-solving, and adaptability in a time effective and inclusive way. A core component of the proposed coaching framework is the integration of emerging technologies like digital tools, smart online whiteboards and generative AI to facilitate collaboration. While whiteboards and visualization tools support keeping an overview, organization, brainstorming and task management, generative AI tools take on new roles in activities such as ideation, coding, and refinement of content. These tools allow students to engage more deeply with agile methodologies and the quality of their interaction and teamwork, in particular if supported by a mindful, person-centered coach. The outlook is that gradually course instructors who utilize the coaching framework would take on the role of coaches to accompany student teams in their self-determined, digitally empowered tasks.This paper presents the design and architecture of the framework, characteristic use cases in the context of the course on Human-Computer Interaction, the benefits as well as challenges of this innovative approach for students’ engagement, their project outcomes, their professional competencies development, and the potential implications for higher education. Preliminary findings suggest that integrating these coaching methods into computer science education not only improves teamwork but also prepares students for dynamic professional settings.

Vanessa Tudor, Renate Motschnig

Conference Proceedings

Multifactorial Measurement of Mental Strain for Developing Adaptive Assistance Systems in Control Rooms

This study investigates the mental strain among control room workers, as a requisite for developing adaptive assistance systems, specifically for the energy sector. Through preliminary interviews with personnel of a German energy supply company, we identified mental workload, attention, emotional states, and mental fatigue as relevant user states. Twenty male dispatchers from the same company participated in the study, completing validated questionnaires including the Workload Profile, Activation-Deactivation Adjective Check List, Flow-Experience Questionnaire, and Self-Assessment Manikin during normal shifts. Results revealed moderate workload demands with high variability, stable tension and activation levels, moderate concentration, and positive emotional states during shifts. These findings provide valuable insights for designing adaptive assistance systems that can respond dynamically to operators' needs, potentially enhancing job satisfaction, performance and efficiency in control room settings.

Estefany Rey-becerra, Matthias Hartwig, Sascha Wischniewski

Conference Proceedings

A Comparison of Four Sensor-based Input Methods for Scanning Keyboards

Four sensor-based methods for computer input were compared. The methods were button, accelerometer, flex sensor, and pressure sensor. The sensors were held in the user's hand in a grip position (button, pressure) or attached via a Velcro band either to the index finger (flex) or on the back of the hand (accelerometer). The methods were used for the select operation with a single-switch scanning keyboard using a Qwerty letter arrangement. The setup used a 700 ms scanning interval, a 200 ms scanning delay (after each selection), and auditory feedback for switch activations. Twelve participants completed five text-entry tasks with each sensor. The text entry rates were slow, but in the expected range for single-switch input. Button selection was the fastest at 2.35 words per minute (wpm) and had the highest efficiency with 82%. The flex sensor followed at 2.26 wpm with 77% efficiency, followed by the pressure sensor at 2.07 wpm with 74% efficiency. The accelerometer was the slowest at 1.89 wpm and had the lowest efficiency at 68%. Statistical tests indicated a significant effect of sensor type on entry speed and efficiency, though post hoc comparisons revealed no pairwise significance, potentially due to the limited sample size. Qualitative results supported the findings: The button sensor received the most favourable user ratings across comfort, fatigue, and preference, with six of twelve participants selecting it as their preferred choice. Four participants selected the flex sensor as their preferred choice

Haobin Alturo Chen Liu, Sarika Patel, Scott Mackenzie, Aakanksha Verma, Kerthana Ramesh

Conference Proceedings

An examination of the influence of visual perception of 3D LED billboards on viewer emotions: based on environmental psychology

The advent of 3D LED billboards in consumer and public display sectors necessitates a comprehensive understanding of their visual effects and the mechanisms underlying users' emotional responses. Environmental psychology suggests that environments can evoke feelings of happiness and relaxation, yet they may also induce anxiety and depression. Consequently, this study seeks to employ the PAD model (pleasure, arousal, dominance) alongside environmental psychology to investigate the impact of 3D LED billboard visual effects on audience emotions. It aims to analyze the emotional characteristics observed in experiments and case studies to inform the optimization of design strategies. Traditional research in this area is constrained by physical influences and regulatory policies, presenting challenges such as imprecise experimental parameter adjustments (e.g., environmental daylight, on-site human traffic) and legal restrictions that prevent the display of experimental content on screens. This study introduces an innovative approach by developing a VR virtual experimental platform, offering new methodological insights for future research on 3D LED billboards.Methods: This study employed a questionnaire survey and a quantitative experiment. Initially, a questionnaire featuring various photographs of 3D LED billboard cases was distributed, and participants were asked to evaluate these cases based on visual quality elements. The aim was to identify differences in the design elements of 3D LED billboards across different visual levels. Subsequently, on-site measurements of the 3D LED billboard scenes were conducted for modeling purposes, and a naked-eye 3D video was produced. The emotions elicited by various screen parameters were quantitatively assessed using the PAD (Pleasure, Arousal, Dominance) model. Following the experiment, emotional calculations and design factor evaluations were performed for different design scenarios to investigate the emotional design strategies of the environment. In this experiment, screen parameters served as independent variables, while pleasure, arousal, and dominance in the PAD model functioned as mediating variables, and emotional tendency was the dependent variable.Conclusion: The analysis of questionnaire survey data reveals that the visual quality of 3D LED billboards is influenced by factors such as brightness, size, color saturation, viewing angle, and distance. Furthermore, the examination of quantitative experimental data indicates an absence of linear correlation between screen parameters (specifically brightness) and the audience's PAD (Pleasure-Arousal-Dominance) emotional values when the same content is displayed. Optimal screen parameters can elicit feelings of surprise or pleasure in viewers, whereas extreme parameters may provoke anxiety or hostility. The visual perception of the screen significantly impacts the audience's sense of pleasure and dominance, suggesting that varying screen parameters predominantly affect the audience's positive or negative attitudes and their active or passive willingness to engage with the screen. Additionally, we conducted emotional evaluations and design analyses of various cases and experiments, proposing emotional design strategies aimed at enhancing positive emotional responses. These strategies are intended to guide future designs towards being more scientifically grounded and human-centered, thereby improving the visual image quality of 3D LED billboards.

Jinghao Jiang, Kaizhong Cao

Conference Proceedings

Impact of Road Event Recognition Reliability in Autonomous Vehicles on Driver Trust and Takeover Performance

The reliability of an autonomous vehicle's (AV) event recognition is vital for building driver trust. Drivers' responses to AV event alerts directly influence driving safety. Therefore, understanding how AV recognition reliability affects driver trust and subsequent takeover behavior is crucial for designing safer and more effective autonomous driving systems.This study used a driving simulator to examine the effects of AV’s event recognition reliability on driver trust and takeover performance. Sixty volunteers without prior autonomous vehicle experience were divided into two groups: one performed a non-driving-related task (NDRT) in autonomous mode, while the other passively observed the roadside. The experiment utilized a mixed factorial design with three levels of recognition reliability (93%, 80%, 60%) and two error types (false alarm vs. miss), alongside a secondary task condition (NDRT required vs. not required). Six similar road scenarios were created to minimize environmental variability, and participants drove for about 18 minutes at 70 km/h. During the drive, 15 autonomous vehicle recognition events were randomly introduced, prompting the vehicle to issue or withhold takeover requests based on reliability. Participants could decide whether to assume manual control in response to these alerts.The experimental data collection comprised two parts: (1) objective data, including takeover performance (takeover time, control duration), driving behavior (accidents, steering wheel angle variation, lateral acceleration variation, lane position variation), and NDRT performance (total score, completion time, number of questions answered, and errors); and (2) subjective data, assessing participants' initial trust in the autonomous vehicle, their trust and acceptance levels after each event, and overall acceptance following the driving session.The study revealed that miss errors significantly impacted driver confidence, which declined sharply with increased error frequency and decreased system reliability. Miss errors also prolonged takeover time, hindering drivers' ability to respond effectively to sudden road incidents. Conversely, false alarms increased reaction time by about 0.14 seconds, while miss errors reduced takeover time by approximately 0.41 seconds, risking premature responses. Additionally, miss errors increased cognitive load due to unexpected incidents, leading to greater steering variability and impulsive lane changes, which caused more significant deviations from the intended path. After encountering multiple errors—especially at 80% and 60% reliability—drivers remained skeptical of system alerts. Although trust improved slightly with accurate warnings, it did not return to the initial levels seen with high reliability. These findings underscore the challenge of restoring driver trust in autonomous vehicles and highlight the importance of human factors design in maintaining user confidence.

Shan-chih Chen, Yung-ching Liu

Conference Proceedings

Optimizing Augmented Reality Displays for Culinary Guidance: Investigating High-Contrast Effects in Human-Machine Interface

As AR technology advances, it is transforming user interaction by providing hands-free, real-time guidance. In culinary settings, AR enhances cooking efficiency, particularly for individuals with limited experience. This study investigates AR text displays in high-contrast environments for synchronous recipe teaching, focusing on novice users. A quantitative study with 20 participants compared two groups: one using AR glasses for real-time recipe guidance and the other using a tablet-based digital recipe. AR users benefited from hands-free guidance, seamlessly following instructions while handling ingredients, whereas tablet users frequently shifted attention between the screen and their cooking. Usability, user experience, and visual strain were assessed using the System Usability Scale (SUS) and Near Point Accommodation (NPA) tests. Results showed that AR significantly improved cooking performance, efficiency, and confidence. The hands-free interface minimized disruptions, and high-contrast text did not induce visual fatigue. These findings highlight AR’s potential in interactive cooking and learning, benefiting both amateur and professional chefs. Integrating AR into culinary education and professional kitchens could enhance training and skill development. Future advancements, including AI-driven personalization and gesture-based controls, could further optimize AR’s role in digital culinary assistance and immersive learning.

Yuchen Yeh, Yucheng Lin

Conference Proceedings

Trusting the Machine – The Role of Gender and Personality in Shaping the Propensity to Trust Artificial Intelligence

With the growing significance of Digital Trust in the context of Artificial Intelligence (AI), it is essential to identify the factors that shape individuals' propensity to place trust in AI. This study examines whether gender differences exist in the propensity to trust AI and explores the extent to which personality traits serve as significant predictors of trust. Data from N = 114 students was collected using validated psychometric questionnaires. A one-way analysis of variance (ANOVA) was used to analyze gender differences, while a multiple linear regression analysis was used to examine the influence of personality traits. The results revealed no significant gender difference. However, the personality traits conscientiousness and neuroticism were significant negative predictors of the propensity to trust AI. Overall, the Big Five personality traits explained a moderate amount of the variance in the propensity to trust AI. The findings underscore the multifaceted nature of psychological factors influencing trust in AI and contribute to the expanding body of interdisciplinary research aimed at systematically understanding this complex phenomenon.

Jona Karg, Janine Jäger, Petra Maria Asprion

Conference Proceedings

On Integrating Digital Competencies into German Teacher Training: An Interdisciplinary Approach

Digital competencies are essential for German teacher training students to design contemporary German lessons. The acquisition of media literacy and the integration of digital tools into lessons are crucial factors for successfully preparing students for digital participation in society. Additionally, digital tools offer significant benefits for subject-specific didactic use in German lessons: planning and support, linguistic analysis and reflection, collaborative environments, visualization techniques, multimodal applications, and more. This potential is only limitedly utilized in Austrian schools.The current study investigates the possibilities and potentials of incorporating digital competencies into German teacher training with a focus on subject-specific didactic implementation. It proceeded under the framework of the funded nationwide project "Teaching Digital Thinking" (TDT), an initiative of the Institute of Computer Science at the University of Vienna, to promote digital competencies. Two years ago participatory action research (PAR) was started to study the explicit inclusion of learning objectives that address pre-service teachers’ acquisition of digital competences in the context of their initial experiences in teaching German to secondary level students (age 10-18). In this context the focus of the current study is on the most recent group of a practically oriented seminar in German (Bachelor) in the winter term 2024/25.The investigation is based on the following research question: What support do pre-service teachers need to expand their digital competencies and actively incorporate them into German lessons?To respond to this research question from the perspective of students as well as instructors, a Participatory Action Research Approach was taken, following Baskerville’s (1999) five phases: diagnosing, action planning, action taking, evaluating, and specifying learning. In the paper the authors are going to describe the phases and their outcomes in detail. To generate data for the evaluation phase, pre- and post-test questionnaires were used. The seminar design included the introduction of digital tools in a subject-specific didactic context. At the same time the participating students observed and taught at schools as part of the general school internship, where they were requested to observe the integration of digital elements at the practice schools. Reflective portfolios served to document and analyze students´ observations and experiences, with digital competencies creating a focus of reflection.The results of the first cycle of action showed that active confrontation with digital skills in the accompanying seminar had a positive impact on the use of digital tools. The majority of students reported back that the exchange with peers in the seminar contributed to the expansion of their own competencies and that they felt it was part of their task to support pupils with the acquisition of digital competencies. Based on the insights gained, the following measures are planned for the subsequent cycle of action to optimize the integration of digital competencies: systematic involvement of mentors in the project, invitation of external experts to the accompanying seminars and the creation of a digital resource collection with practice-relevant examples of application for German lessons.

Martina Turecek, Roland Ambros, Renate Motschnig

Conference Proceedings

Advancing Occupational Exoskeletons: Usability Assessment of a Minimalist Calibration Interface

Research on ergonomics for work-related musculoskeletal disorders (MSDs) remains a significant challenge for affected individuals, businesses, and society. As the most costly category of occupational health issues, MSDs affect more than one in three European workers, making them the most common work-related illness across all industries. A common occupational task in various industries is manual materials handling (MMH), which refers to the process of manually moving, lifting, lowering, pushing, pulling, or carrying materials, goods, or products. Nevertheless, it also poses a risk of injuries and MSDs due to different factors, such as the physical strain involved, repetitive motion, poor ergonomics, and environmental factors, such as uneven floors, cluttered workspaces, slippery surfaces, or poor lighting. A promising approach to address MSDs in the workplace is the use of an occupational back-support exoskeleton. This is a wearable technology designed to reduce lumbar spine physical strain during lifting tasks. Research has demonstrated that these wearable devices can decrease back-muscle activity by up to 40%, effectively reducing spinal loading during MMH tasks. According to the actuation principle, an active exoskeleton (with sensors, controller and actuators) can be more versatile in terms of configuration than a passive exoskeleton. A specific characteristic of active exoskeletons is the possibility of modifying the control strategy to provide appropriate assistive forces according to the task. This control strategy is modulated through a human–machine interface (HMI), which is the cornerstone of user interaction and the basis of cognition to modify and adjust parameters in a system. In an active occupational exoskeleton, more functions can be adjusted, such as calibration, user information (weight and height), and control gains.Purpose: This study presents the usability assessment of the motor calibration function in the novel User Command Interface Round (UCI-R), a minimally adaptable setup system for occupational exoskeletons. Calibration is the first step to set up the exoskeleton XoTrunk before starting the MMH task. A user study was conducted with 10 participants by comparing the original user interface with a newly designed, minimised version. The experiment assessed improvements in user experience and efficiency between the two interfaces.Methods: To systematically evaluate user interaction with the interface, we applied the GOMS (Goals, Operators, Methods, and Selection rules) model, which is a well-established cognitive modelling technique in HCI. In this study, the GOMS was used to compare user actions between the two interface versions with a focus on task flow related to motor calibration. The analysis aimed to estimate the cognitive load, execution time, and operational complexity, providing quantitative and qualitative insights into user experience. The goal of this study was exoskeleton calibration; the operators are interactive cards from the exoskeleton calibration section of the User Command Interface (UCI) and the UCI-R visual interface. The methods are the sequence functions to be performed (to achieve motor calibration) in both interfaces, and the calibration action has a specific rule, which is to remain still during the calibration.Results: Ten subjects participated in the assessment showing differences in usability attributes such as efficiency, satisfaction and time on ask favorable for the UCI-R visual interface.Conclusions: Usability attributes such as effectiveness, efficiency, ease of task, time on task, documentation organisation and satisfaction can lead to the acceptance of a new technology as an occupational exoskeleton. A well-designed user interface improves user experience and satisfaction. The minimised UCI-R yielded higher ASQ and SUM results than the standard version of the UCI.

Olmo Alonso Moreno Franco, Christian Di Natali, Luigi Monica, Darwin Caldwell, Jesus Ortiz

Conference Proceedings

Emerging Disruptive Technologies focused strategy: a constraint management approach

Businesses across all industries are facing increasing challenges, which put their competitiveness at stake. Challenges range from disruptions driven by world conflicts and global politics to a perceived increase in socioeconomic risks. With the increased competition, businesses make a considerable effort to sustain a competitive edge in their arenas. A factor ever impacting business performance is technology—a major driver of competitiveness, accelerating innovation and new product development. All these factors together are putting pressure on business leaders and top management teams across any industry. They have to manage finite resources and funds, while at the same time dealing with tough choices on how to react to technological threats, which may affect their businesses, sometimes with catastrophic consequences, as has happened by the effect of technological change along history. At times, an apparent technological advantage may prompt business leaders to consider alternative technological paths. Such decision-makers oftentimes lack a framing and pragmatic approach to assess such potentially emerging technologies. The purpose of this paper is to suggest a strategy to deal with the danger posed by Emerging Disruptive Technologies (EDTs). It suggests businesses how to design a well-thought-out plan that will help them be more resilient and competitive when faced with the threat of possible EDTs. The methodological approach is based on causal logic and a constraints management approach. Taking the defining dimensions of EDTs (strategic, operational, tactical, technical, and organisational), the methodological approach starts by identifying and making problem symptoms visible, together with the chains of cause and effects, which typically originate and drive such symptoms. Oftentimes strategy design imply solving dilemmas and making suboptimal choices, however, by using some tools such as the Categories of Legitimate Reservation, as well as the concept of Conflict Resolution Diagram, both tools from the Theory of Constraint framework, apparent dilemmas, aka dichotomies, are broken allowing for the design of optimal solutions. The results are shown as logic trees, which help through all the strategy development stages, from problem characterisation to strategy design and planning for implementation. This paper also intends to provide academics as well as practitioners with a strategic problem solving framework, which can be further customised for any organisation or strategic situation where the threat of EDTs is a real concern. Overall, and moreover an EDT-influenced strategy is critical for supporting decisions concerning technology investment, capability development, and other strategic initiatives.

Pedro Água, Anacleto Correia, José Bartolomeu

Conference Proceedings

Evaluating Silicon Sampling: LLM Accuracy in Simulating Public Opinion on Facial Recognition Technology

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like responses, prompting exploration into their potential for social science research. "Silicon sampling," a method where LLMs are queried after being prompted with personas, has emerged as a possible alternative to traditional survey methods, especially given the increasing challenges associated with declining survey participation rates and rising costs. However, the accuracy of silicon sampling remains a subject of debate.This study examines the effectiveness of silicon sampling in replicating survey results on public acceptance toward facial recognition technology (FRT). The research builds upon the work of Kostka et al. (2021), who conducted a multinational survey across Germany, China, the United Kingdom, and the United States, analyzing public opinion on FRT alongside socio-demographic data and key contextual factors, including perceived consequences, utility, and reliability of the technology.The study addresses two research questions: (1) Can LLMs simulate an individual's surveyed opinions on FRT when prompted with a persona using only demographic information? (2) Can LLMs simulate an individual's surveyed opinions on FRT when prompted with a persona using both demographic and relevant contextual information?The research employs three LLMs: GPT-4o, Claude 3.5, and the open-source DeepSeek V3. It compares the LLM-generated responses to the original survey data, assessing the degree of alignment under three prompting conditions: demographic-only, contextual information-only, and demographic-plus-contextual information. To initially evaluate alignment, the differences between the percentages of each level of FRT acceptance were calculated. Additional metrics such as accuracy, mean absolute error, and F1-Scores are included in the extended paper. Preliminary results from GPT-4o and Claude 3.5 suggest that prompts incorporating both demographic and contextual information yield simulated responses that closely align with the original survey data. Consistent with prior findings, prompts based solely on demographics produce significantly less accurate results. By comparing closed-source models (GPT and Claude) with an open-source alternative (DeepSeek), the study also examines potential differences in reliability between these types of models. Multiple runs for each model are included to assess output variability and reproducibility within and between models.By demonstrating the importance of incorporating relevant contextual information into prompts, the study provides valuable insights into optimizing the silicon sampling technique and the accuracy of LLM-generated responses in survey simulations. Ultimately, this investigation advances the understanding of the capabilities and limitations of LLMs as tools for studying public opinion, particularly in the context of technology acceptance, and informs the development of best practices for utilizing silicon sampling in future research. The results suggest that, with careful prompting, silicon sampling can offer a viable and cost-effective alternative to traditional survey methods, potentially mitigating challenges related to declining response rates and increasing costs.Kostka, G., Steinacker, L., & Meckel, M. (2021). Between security and convenience: Facial recognition technology in the eyes of citizens in China, Germany, the United Kingdom, and the United States. Public Understanding of Science, 30(6), 671–690. https://doi.org/10.1177/09636625211001555

Charles Ma

Conference Proceedings

Design and development of a student-initiated automated delivery system for potential use in e-commerce

The growth of e-commerce business – and the consequent faster delivery times – has demanded better services by overcoming problems such as high labor dependence and inefficiency at sorting and routes. This paper describes a student-initiated independent research and development project in which an automated system for the said delivery service involving a sorting mechanism enabled by Raspberry Pi and artificial intelligence-driven route optimization was designed and prototyped. The proposed system identified parcel destinations, efficiently sorted items, and calculated optimal delivery routes considering traffic, weather, and road conditions.In Singapore, e-commerce sales are expected to reach US$14 billion by 2027. This growth has increased the pressure on logistics providers to meet the rising customer expectations, especially in urban areas where same-day or next-day deliveries had been expected by the users. Late deliveries are one of the most common delivery problems. The traditional delivery services that rely on manpower slowly lose the ability to meet such criteria, causing more delay in deliveries and increase in operational costs. In manual sorting, it is exhausting and time-consuming to decode the packages and match them with information in the address database, increasing time taken in the sorting process and causing delay in deliveries.Our objective was to research and develop a prototype for an automated operations chain that spanned from inventory sorting to dispatching and final delivery. This involved:•designing an automated operations chain and evaluating the practical feasibility and logistics of achieving each stage of operation;•setting up an image-text algorithm using a web camera as an input device, capable of identifying the destination of the package and formatting it into a spreadsheet (xlsx). This allows for future reference by the management for further tracking or the product; and•comparing and evaluating wayfinding algorithms to plan an efficient route from the recorded destinations in the excel sheet.Key findings suggested that automation minimizes human error, enhances operational efficiency, and reduces environmental impact through optimized fuel consumption. Additionally, the data-driven approach taken by the system enhanced traceability and transparency, thus potentially building trust in customers. While there were still some challenges to be faced – for instance, restricted data access for validation – this project underlined the potential of AI and robotics in improving delivery logistics, hence providing a scalable and sustainable framework that might meet the increasing demands within the e-commerce landscape.

Jun Yit Ong, Aaron Y C Wong, Kenneth Y T Lim

Conference Proceedings

Quantum Computing Circle – a Descriptive Case Study on Teaching Quantum Computing in a Business School

Quantum computing holds immense disruptive potential impacting technology, business, and society. Despite its significance, its complexity poses accessibility challenges. Consequently, diverse teaching approaches are being explored by educational institutions. While tech-savvy audiences are addressed, offerings for business-oriented individuals are scarce. In 2023, the authors of this publication secured funding for the 'Quantum Computing Circle', an educational initiative aimed at familiarizing business managers/students with quantum computing. This program, comprising twelve teaching hours including hybrid lectures and lab exercises, supplemented with self-study and an online test, was piloted with a cohort of approximately 50 bachelor-level students across two universities in spring 2024. This paper delineates the course's design, implementation, and outcomes, including student and lecturer feedback as well as learning achievements. It provides didactic recommendations and insights for educators in emerging technologies like quantum computing, serving as a starting point for further research in quantum computing education.

Bettina Schneider, Carmen Winter, Bernd Hänsch-Rosenberger, Gerhard Hellstern, Franka Ebob Ebai, Clément Javerzac-galy

Conference Proceedings

Automated 3D Ergonomic Assessment from a Single Standard Camera for Confirmation of Work Overload of Lumbar Spine

Chronic lumbar spine disease is a new item on the list of occupational diseases in the Czech Republic from January 1, 2023. This disease is defined by clear clinical characteristics and necessary exposure criteria at work. The diseases arise during heavy physical work, during which the relevant structures are overloaded for a long time to such an extent that, according to current medical knowledge, overloading is the cause of the disease.The essential exposure criterion is the determination and confirmation of work tasks, work activities and work shifts in which the hygienic limits set by Government Decree No. 361/2007 Coll., as amended, for handling loads, taking into account the working position, are exceeded. To meet the hygienic exposure criteria, it must be confirmed that the compression force on the L4/L5 disc exceeds the value based on the NIOSH US 3400 N limit and taking into account the relevant anthropometric characteristics of the person and the ergonomic, time and frequency parameters of work, for at least 3 years and at least 60 shifts per year. At the present time is used traditional certified method for work risk assessment which is based partly on the subjective assessment by a specialist in the field of occupational physiology. To replace this method a new ErgoVison, full-stack web-based application designed to automate ergonomic evaluations in industrial settings is tested. This system leverages advanced computer vision techniques to reconstruct a 3D representation of human posture from videos recorded with a single standard camera. By extracting key body joint angles—including spine angle and the distance to a handled weight—ErgoVision provides objective, quantifiable assessments that help ergonomists make rapid and reliable decisions. The ErgoVision web application streamlines video uploads, data processing, and reporting. The system designed to align with the ergonomic and legislative standards as defined by the Czech health government directives. Previous research in camera-based ergonomic assessments has largely focused on multi-camera setups. In contrast, this work is motivated by the need for a more accessible solution. By employing a single-camera approach combined with specialized reconstruction algorithms and a user-friendly web interface, ErgoVision seeks to democratize ergonomic assessments and offer a certified, objective evaluation tool for a broader audience. In the initial step, video footage is captured of a subject performing physical labor using a standard, single camera. The objective is to record high-quality visual data that accurately represents the subject's posture and movements during various tasks. This approach is designed to simplify the ergonomic evaluation process by leveraging readily available hardware, thereby reducing both cost and complexity in comparison to multi-camera setups. The accuracy of ergonomic assessment and its availability for industry is crucial in safeguarding worker´s health and optimizing productivity in industrial environments. Challenges such as the accurate reconstruction of extreme postures remain, highlighting avenues for future research. Ongoing developments will focus on refining the 3D reconstruction algorithms and expanding the system’s capabilities to accommodate a wider range of ergonomic scenarios. Ultimately, ErgoVision represents a significant step forward in automating ergonomic evaluations, with the promise of supporting informed interventions to improve worker safety and productivity. Future work will further explore integrating advanced sensor data and machine learning models to overcome current limitations, ensuring that the system remains adaptable to evolving ergonomic standards and industrial demands.ACKNOWLEDGMENT: Supported by Ministry of Health, Czech rep. - RVO (NIPH, 75010330).

Vladimira Lipsova

Conference Proceedings

Delivery service and omni-channel online-and-offline for retail collaborative recommendations

From the perspective of e-commerce, delivery and retail operators can join in discovering valuable data on the platform through interactive data on consumer preferences for delivery service and online-and-offline purchasing. These operators can then summarize the information to make collaborative recommendations more accurately, thus increasing consumer purchasing. The delivery service business model is the final link in logistics for both online-and-offline business. An omni-channel, the online-and-offline business model, provides a complete and uninterrupted consumption experience by combining data and marketing content, acting as an offline physical channel and online with consistent services and information. Online-and-offline business models combine e-commerce and physical commerce. A recommendation system filters information to recommend information, services, or products that users may need based on their preferences, interests, behaviors or needs. Recommendation systems include collaborative filtering, content-oriented recommendation, and knowledge-oriented recommendation. Regarding retail collaborative recommendation, that is, a recommendation mechanism involves two or more parties, such as logistics, retail firms and e-commerce operators, working together to obtain necessary consumer information and knowledge, such as profiles and preferences, as the basis for personalized product recommendations. For example, when consumer A purchases mountaineering equipment on a website, the shipping fee is included after discounts, and A then chooses the transaction method of electronic payment and home delivery service. This transaction record involves three-party operators of products, logistics, and cash flows. Through this transaction, the multi-party platform not only understands consumers' purchasing behavior, but also specifically understands consumers' intentions, including outdoor sports, mountain climbing, online discount preference, electronic payments, home delivery, etc. Through collaborative recommendation, multi-party operators can analyze the specific profile of consumer A and further promote information that may interest the customer. This information is not just about specific products, but also includes information related to backpacks, such as weather, map routes, sports news, blog articles, etc. Thus, collaborative recommendation is an approach that seeks to understand consumers' lives and context. In these regards, this study investigates Vietnamese consumer behaviors with delivery services and omni-channel online-and-offline (n=2,354). Data mining analytics, including clustering analysis and association rules, reveal knowledge clusters/patterns/rules for investigating delivery service and omni-channel online-and-offline for retail collaborative recommendations. Finally, with information technologies and business applications developments, such as artificial intelligence, data computation, business intelligence and machine learning, the theoretical and practical applications of retail collaborative recommendations can be more completely developed for human interaction and emerging technologies.

Shu-hsien Liao, Jian-ming Huang

Conference Proceedings

A Multi-Perspective AI Framework for Mitigating Disinformation Through Contextual Analysis and Socratic Dialogue

The proliferation of digital information channels has created an unprecedented challenge in discerning credible information from sophisticated disinformation campaigns. Traditional fact-checking methods, often relying on binary true/false classifications, struggle to address the complexity, context-dependency, and nuanced nature of many claims circulating online. This limitation underscores the urgent need for advanced tools that empower individuals to critically evaluate information from multiple angles. Our AI-driven framework combines persistent contextual memory with Socratic dialogue and a three-lens analytical pipeline to foster deeper understanding and resilience against manipulation.As users interact, each input is segmented into atomic claims and stored, alongside the evolving dialogue history, in a contextual memory to ensure consistency. Each claim is then evaluated in parallel by three specialized LLM arbiters: the Empirical Arbiter, which verifies data against curated repositories and assesses observational consistency; the Logical Arbiter, which uncovers hidden fallacies and assesses argument coherence; and the Pragmatic Arbiter, which weighs potential outcomes, utility, and situational fit. An Analysis Integrator synthesizes these into interpretable metrics: Verifact Score (evidence strength), Model Diversity Quotient (inter-arbiter agreement), Contextual Sensitivity Index (scenario appropriateness) and Reflective Index (exposed assumptions). Additionally, a Perspective Generator crafts counter-arguments and alternative viewpoints, encouraging users to consider different interpretations and promoting epistemic humility.We hypothesize (H₁) that our arbiters' feedback will reduce user endorsement of unsupported claims more effectively than conventional fact-checking while mitigating backfire effects through Socratic dialogue. Our research questions ask how Empirical, Logical and Pragmatic scores influence confidence revision (RQ₁); whether MDQ reliably signals claim controversy and predicts evidence volatility (RQ₂); how users perceive transparency, fairness and cognitive load when receiving multi-perspective feedback versus a simple true/false label (RQ₃); and to what extent the persistent contextual memory system improves belief updating by maintaining coherent reasoning chains across extended dialogues (RQ₄).By providing a multi-faceted presentation that moves beyond simple verification, the system is designed to encourage engagement in higher-order critical thinking. The proposed framework represents a significant advancement over traditional fact-checking by integrating empirical validation, logical scrutiny, and pragmatic assessment through an AI-driven system. The full paper will detail the system architecture, formal metric definitions, experimental protocol, and proposed evaluation methodology to assess its efficacy in educational settings, media literacy programs, and as a personal tool for navigating the complexities of the modern information ecosystem.

Manuel Delaflor, Carlos Toxtli

Conference Proceedings

Learning to Repair Through AI-Driven Geometry Reconstruction for Sustainable Manufacturing

Remanufacturing plays a vital role in advancing circular economy strategies by extending product lifecycles and reducing energy consumption. However, the variability in part condition and lack of predictive tools often hinder efficient repair planning and sustainable decision-making. This paper presents the EcoRemanufacturing Architect, an AI-driven solution designed to reconstruct degraded geometries and support informed decision-making in additive remanufacturing processes. The tool integrates edge-based contour extraction and Fourier descriptor encoding to capture degraded component geometries, which are then predicted from process parameters using a pair of Random Forest Regressors. To enhance generalization across diverse repair scenarios, the training dataset is augmented using a Variational Autoencoder. The reconstructed curves are evaluated using both descriptor-based and spatial metrics, confirming the model's ability to capture both global shape and local detail with high accuracy. Beyond geometric feasibility, the system estimates key environmental indicators—such as energy consumption, material use, and carbon footprint—enabling multi-criteria evaluation of repair strategies. The proposed pipeline demonstrates how digital intelligence can empower more sustainable and cost-effective remanufacturing workflows by enabling accurate part assessment and resource-aware repair planning.

Sondos Jaziri, Andrea Fernandez Martinez, Johan Vallhagen, Santiago Muiños Landin

Conference Proceedings

The Influence of Culture on Typeface Perception and Design

This study aims to explore the impact of culture on typeface design and its communicative effectiveness, particularly in a multicultural city like Hong Kong. The research will employ a mixed-methods approach, combining surveys and semi-structured interviews to gather data from a diverse sample of individuals from various cultural backgrounds. The aim is to provide empirical insights into the relationship between cultural dimensions and preferences for typefaces, as well as practical guidelines for designers to create culturally sensitive typefaces. The study will contribute to the field of design psychology by establishing a foundation for understanding the relationship between culture, typography, and user experience. The findings will be presented to design practitioners in multicultural contexts, while also addressing limitations and suggesting potential directions for future research. The study will also explore the impact of emerging technologies on cross-culturally relevant typography.

Amic Ho, Ruth Chau

Conference Proceedings

Enhancing the management of nuclear information systems through graph theory-based methods and human-centered modeling

The integration of digital technologies is crucial for enhancing the efficiency and performance of nuclear facilities throughout their entire lifecycle. However, the nuclear industry faces significant challenges due to its intricate supply chain, resulting in fragmented data exchanges and inefficiencies. The expansion of complex information systems has introduced considerable challenges to data management, leading to inconsistencies and inaccuracies that adversely affect operational performance.To address these challenges, this study proposes an integrated analytical approach that combines graph theory with the Technology-Organization-People (TOP) Model for Human-System Integration (HSI). By incorporating the TOP model, we consider the technological, organizational, and human dimensions of complex sociotechnical systems. In addition, a method is introduced to weight edges in data flow graphs, applied to measure the effect of cognitive load of human tasks.A synthetically generated dataset was used to simulate real-world operations, allowing the application of two graph theory methods: Betweenness Centrality to identify critical nodes and Spectral Clustering to group nodes with similar dataflow characteristics, providing insight into the underlying structure and dynamics of the nuclear dataflow. This approach facilitates a more sophisticated analysis and comparison of results, distinguishing between outcomes with and without cognitive load and supports then more informed data management and flow optimization decisions.The results of this study underscore the effectiveness of combining graph theory methods with human-centered models and also highlight the critical role of human factors in data management strategies that subsequently contribute to improved efficiency, reliability, and performance of nuclear facilities throughout their life cycle.

Olivier Malhomme, Luigui Salazar, Xianyun Zhuang, Robert Plana, Nicolas Bureau

Conference Proceedings

Mapping Human-Centred Design in innovation-driven Projects: an HRL assessment of an autonomous ferry and remote operations centre concept

The rapid pace of technological development in the maritime sector is driving transformative changes across sociotechnical systems,as autonomous vessel, remote operations, and control infrastructures are developed. However, innovation efforts often focus on the technology itself, leaving critical human factors (HF) aspects underdeveloped. This extended abstract presents a case study from the development of an autonomous urban passenger ferry and its associated remote operations center (ROC), in which the Human Readiness Level (HRL) framework (HFES/ANSI 400-2021) was applied to assess human-system readiness, consolidate earlier Human-Centered Design (HCD) efforts, and guide future development.Although the ferry system had reached Technology Readiness Level (TRL) 4–5, our HRL assessment revealed that human readiness had not kept pace. HRL 1 and 2 activities—such as defining user needs, human roles, operational contexts, and early interaction concepts—had been partially addressed across various HCD efforts. However, HRL 3 activities are intended to establish validated human-system interaction concepts through structured analyses of tasks, cognitive demands, operational scenarios, and human performance metrics. In this case, HRL 3 was not fully met: key gaps included the absence of formal task and cognitive task analyses, limited definition of supervisory roles and transitions between automation modes, and a lack of traceable performance measures related to operator workload, situation awareness, and risk-critical scenarios.Extensive HCD and HF activities had been carried out throughout the project, often by different contributors at different times, with a certain fragmentation as a result. The HRL framework, even though it was in part used as a retrospective checklist, provided a structured mechanism to consolidate insights, identify latent risks, and re-establish a baseline for continued HCD and human-system integration work. Its staged exit criteria helped the team see where human readiness had failed to keep pace with system development, and where further work was needed in usability, safety, and regulatory compliance.To build on HRL 1–2 progress, structured HF methods, including CRIOP scenario analysis, operator workload mapping, scenario desciptions, and documentation of design assumptions were conducted to begin fulfilling HRL 3 requirements. These activities clarified cognitive demands, roles, and safety-critical transitions, and created a compiled evidence base that can support continued validation efforts toward HRL 4 and beyond.As part of this work, a preliminary set of human factors design guidelines was derived from the HRL mapping process. These address safety, efficiency, and user acceptance concerns, and aim to support future iterations through clear principles for interface design, operator training, situational awareness, emergency protocols, accessibility. The guidelines are intended as a living reference for designers and engineers working on remote and autonomous maritime systems. Even in projects with strong HCD ambition, the absence of structured integration and traceability mechanisms can make it difficult to maintain continuity, especially in innovation-driven or academic environments where project goals evolve and team members may change over time. In this case, the HRL framework helped tie fragmented contributions together and provided a foundation for planned, traceable HF integration. It also supported cross-team alignment, and a form of quality assurance , capabilities that can be increasingly valuable in AI-enabled, high-tech development settings such as maritime autonomy, where there are also eveloving regulations. Our findings reinforce the growing view that HRL is not only a diagnostic tool but also a forward-looking framework that makes human-system integration more visible, traceable, and auditable throughout complex development processes.

Hedvig Aminoff

Conference Proceedings

Leveraging Generative AI for Expanding Strategic Thinking: An Integrative Framework for Scenario Analysis, Strategy Formulation, and Collaboration

Generative artificial intelligence presents a novel approach to expanding managerial strategic thinking by integrating scenario-based analysis with algorithmic exploration. The objective of this proposed presentation is to demonstrate how such an approach can help managers address emerging uncertainties, transcend siloed decision-making, and accelerate strategic insights in rapidly changing business environments. The significance lies in moving beyond traditional, historically focused analytical tools and toward a forward-looking perspective that combines human intuition with AI-driven insights. By leveraging generative capabilities, organizations can more comprehensively identify threats and opportunities, thus enhancing resilience and adaptability in volatile markets.The methods involve a multistage process that begins with identifying a focal strategic challenge, such as confronting new technologies, shifting consumer preferences, or unforeseen regulatory changes. Managers then collect relevant contextual information, including historical data, consumer trends, and market reports, which they feed into the AI system. Next, iterative prompts guide the AI to generate plausible future scenarios, each reflecting distinct combinations of factors such as economic shifts, competitor innovations, and policy alterations. Throughout this process, human expertise remains critical: managers filter AI outputs by applying domain knowledge, refining scenarios, and validating or discarding speculative elements. This dialogue between human judgment and AI generation ensures that the resulting scenarios balance creative exploration with practical relevance. The final stage involves deriving strategic options that are robust across multiple plausible futures. Teams examine these options by testing whether they can withstand differing assumptions about regulation, resource constraints, or consumer behaviors. By adopting a cyclical approach, the organization revisits scenarios regularly, updating them with new data and insights to ensure that strategic planning remains dynamic and responsive.Early results from pilot applications indicate that participants benefit from an expanded perspective, uncovering hidden interdependencies and second-order effects that traditional methods often overlook. In particular, managers report that when AI surfaces unconventional predictions, it prompts more nuanced discussions about risk mitigation and opportunity exploitation. This enriched strategic discourse can foster greater alignment among cross-functional teams, as it encourages them to reflect on the broader business ecosystem rather than focus solely on short-term, department-specific metrics. Over time, organizations that embed this AI-based scenario process show signs of enhanced agility: they can pivot more rapidly when external signals suggest a particular scenario is becoming more likely. While not a definitive forecast tool, generative AI serves as a stimulus for collective sense-making, helping decision-makers continuously probe their underlying assumptions and embrace a wider range of strategic possibilities. By adopting this method, firms can refine their readiness for disruptive forces, position themselves proactively against emerging challenges, and cultivate a culture of adaptive learning that is essential for long-term competitiveness.

Sonic Wu

Conference Proceedings

Design and Evaluation of a Social AI Bot for Empathetic Support in Online Dementia Healthcare Community

Dementia caregiving exerts heavy emotional, psychological, and social challenges on caregivers, leading caregivers to feel isolated and overwhelmed. Online health communities have become vital platforms for dementia caregivers to seek support, advice, and empathy from others. However, many help-seeking posts go unanswered or receive responses lacking sufficient emotional support. Because of advances from Artificial Intelligence (AI) and large language models (LLMs), there are some academic literatures that have examined solutions for healthcare backgrounds previously. However, very few scientific investigations explored social AI bot's functionality for providing emotional support replies on dementia caregiver online communities. For this current investigation, we aim to develop and introduce a LLM-based social AI bot for dementia online healthcare communities and explore its efficacy for providing supportive and empathy replies towards help-seeking post submissions from dementia caregivers. Empathy scores and sentiments scores were calculated for comparisons between actual user replying post and social AI bot replying post. It was portrayed from analysis results that replying post generated from social AI bot have considerably high empathy scores and sentiments scores than actual user replying post. The scientific investigation findings enhanced our understanding on how social AI bot can be effective for providing proper empathy support for dementia caregivers.

Yanzhen Jason Yue, Yi Chen, Chee Seng Chong, Xiangming Landy Lan

Conference Proceedings

Enhancing Creativity in Design Education through Emotional Engagement: A Study on Junior Designers

Emotional Design Principles are increasingly incorporated into the curriculum for junior design students, recognised as essential for fostering innovation and enhancing user-centred solutions. This study identifies a pathway to address the misalignment between the plurality of art and junior designers in the design course. The study employs a mixed-methods approach, utilising action research, surveys, and focus groups to evaluate the impact of emotional design on students' creativity, empathy, and decision-making. Throughout three terms, workshops will present concepts associated with emotional design via hands-on projects that promote experiential learning and collaboration among participants. The assessment of alterations in the understanding and implementation of emotional design principles will be conducted statistically using a pre-and post-workshop questionnaire. Focus group talks will be used to gather qualitative data on students' experiences and perspectives. Preliminary findings indicate that incorporating emotional design into the students' learning environment may enhance creativity and sympathetic comprehension. Participants are expected to gain a deeper understanding of the impact of their emotional connections on their design work and user-centred solutions. This research aims to construct a theoretical formal model of emotional design principles in creative curricula, taking into account the significant influence of cultural settings on students' perceptions of emotional design. These findings will assist educators in determining which strategies might improve design education by enhancing the emotional engagement of younger designers, thereby better equipping them to navigate the complexities of the developing world. To achieve this, it is essential to train not just technically adept designers but also those with cultural sensitivity and emotional intelligence, emphasising the significance of emotion in innovation and user experience.

Amic Ho

Conference Proceedings

Digital Personas: Exploring the Impact of AI Influencers on Social Engagement and Brand Authenticity

The rise of AI influencers has significantly influenced visual communication, necessitating a comprehensive understanding of emotional elements and essential principles of data visualisation for proper interpretation. This research examines the challenges AI-generated images have in effectively condensing complicated information while maintaining aesthetic appeal and clarity. A unique research employing a mixed-methods methodology subjected volunteers to various urban landscapes in virtual reality to analyse their physiological reactions (heartbeat, electrodermal activity) and subjective emotional responses (via questionnaires). The investigation examined colour schemes, font, and layout configurations to identify best practices in visual communication that enhance audience emotional engagement. The results indicated that specific frame designs elicited varying emotional responses, demonstrating a significant correlation between colour choice and viewer emotions. The study emphasised the necessity of maintaining emotional sensitivity in AI-driven communication strategies, asserting that impactful graphic and material forms of communication foster creativity and responsibility in communication design messaging. This study enhances the knowledge of the association between various maps with different colour schemes and the feelings they evoke, therefore revealing the numerous ways urban design and architecture influence psychological well-being. The final result underscores the significance of including emotive elements in designs, ensuring that AI-generated creations resonate emotionally with consumers. The research advocates for a paradigm shift in visual communication design to enhance aesthetics, ethics, and emotional engagement.

Amic Ho, Ruth Chau

Conference Proceedings