Human Systems Engineering and Design (IHSED2025): Future Trends and Applications

AHFE International

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

Human Systems Engineering and Design (IHSED2025): Future Trends and Applications

book-cover

Editors: Tareq Ahram, Waldemar Karwowski, Darko Etinger

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2025

ISBN: 978-1-964867-74-8

DOI: 10.54941/ahfe1006755

Articles

Disaster Situation Understanding and Management by Using Common Ontology and Semantics

This research examines the creation of common ontology and semantics aspects during nature disaster identification and management. The common ontological definition is important for various stakeholders and expert groups to understand disaster during its different stages for controlling and managing salvation and recovery. During this study has been used as case study environment, the MobiJOPA™ system created recently by the Start-up company Husqtec Corp., which is concentrating on situation and operational management. As the use case has been selected water flow disaster, which is quite common type of disaster because of the influence of climate change. During the research has been answered to the following research questions: - How is the common ontology and related semantics formed on the use case of water flow disaster? - How is human-based understanding and management of situation analysis, resource control, and operation command organized according to the common ontology and related semantics? - How could generative AI and AI Agent- technology be used in a common semantic infrastructure? This article introduces the problematics of common ontology to be configurable according to the variety of local, regional, and geographical stakeholders and experts based on characteristics of demographic population, nationality, culture, organization structure, weather conditions, and the diversity of nature and infrastructure. The study highlights the critical role of user-centered design, AI-driven decision support, and team cohesion in fostering effective emergency response. A case study prioritizes user-centred design to address the needs of diverse user groups, ensuring inclusivity and accessibility in disaster scenarios. Advanced technology integration by using Generative AI and AI Agent technologies improves decision-making and teamwork during crises. The study also introduces the need of cohesion within the team, managing the disaster situation and decision making. Modular and customizable features enhance the system's adaptability and user experience of various experts and groups involved.

Vesa Salminen, Matti Pyykkönen, Ari Saarinen

Conference Proceedings

Layer Model for the Design of Data-driven Business Models – AI Integration and Industrial Data Fusion Across Hierarchical Levels

This paper presents a structured framework for analyzing the role of intelligent sensor systems in enabling data-driven and potentially disruptive business models in manufacturing. Building on a five-level layer model − comprising sensor, machine, shopfloor, plant, and value chain − the study systematically examines each level along five analytical dimensions: data, processes, IT systems, interfaces, and standards. For each level, the current state and expected future developments are exemplarily assessed through literature analysis and industrial case examples. This multi-dimensional approach reveals digitalization potentials and integration barriers at each stage of the value creation process. The findings are then synthesized to explore cross-level fusion strategies, enabling new forms of vertical and horizontal integration. The methodology follows the Zachman framework logic, ensuring structured coverage of each layer and aspect. Real-world use cases − ranging from pay-per-part offerings to cross-company data spaces − illustrate how sensor-based integration supports novel business logics such as Equipment-as-a-Service, predictive quality management, or audit-ready digital twins. The paper contributes to Industry 4.0 discourse by linking sensor fusion architectures with value creation mechanisms, demonstrating how technical infrastructures and business models must co-evolve. The proposed model serves as both a diagnostic tool for digital maturity and a design template for future-ready industrial service models.

Holger Kett, Robin Kurth, Sandra Frings

Conference Proceedings

Tracking Human Factor Recognition in Occupational Accident Investigations: A 10-Year Review from the Quarrying and Aggregates Sector

Occupational accident investigations are a critical component of safety management systems, particularly in high-risk industries such as quarrying and aggregates. Human factors are widely recognized in academic and applied safety literature as major contributors to workplace incidents. Yet, their explicit recognition within organization-led investigations in high-risk operational environments remains limited. Despite growing awareness, many investigations still lean toward identifying technical, procedural, or rule-based failures, leaving behavioural and cognitive contributors underexplored. This study assesses how human factors are recognized, addressed and interpreted in internal accident investigation reports produced over a ten-year period within a single high-risk industrial company operating in the quarrying and aggregates sector. It examines whether the visibility, frequency, and analytical depth of human factor mentions have developed over time, and evaluates the extent to which investigation practices reflect evolving awareness of cognitive and systemic contributors, beyond general attributions like “human error.” A retrospective review was conducted on 150 formal accident investigation reports generated between 2014 and 2024 by a company operating in the quarrying and aggregates sector. Reports were examined to determine whether human factors were referenced - explicitly (e.g., “fatigue,” “communication failure”) or implicitly through behavioural descriptions. Reports that included human factor references were further examined to identify whether specific categories were cited and whether the analysis extended beyond general terms like “human error” to explore underlying causes. A structured checklist was used to ensure consistency in data collection, recording binary presence/absence data and brief explanatory notes. No qualitative coding was applied. Frequency counts were then compiled by year to observe trends in the visibility and analytical depth of HF mentions across the ten-year period. The analysis showed that human factors were mentioned in 60% of reports across the 10-year period. Of these, only 24% offered any detail beyond vague labels such as “human error” or “personal issue”. There, a range of human factor categories was identified, indicating that multiple behavioural and cognitive aspects were recognized to some extent. However, most of these references focused on the actions or decisions of frontline operators, with significantly fewer mentions of supervisory oversight, team-level interaction, or broader organizational influences. Report frequency varied slightly by year, but the proportion of reports recognizing HF remained largely static. This study highlights that, within the examined company, human factors remain underrepresented in formal accident investigations. Over a ten-year period, there was no notable progress in the depth or frequency of HF inclusion, despite increasing attention to the topic in industry discourse. These findings suggest that changes in safety culture and investigative practices require more than awareness and interventions. While limited to a single company, the results may reflect broader patterns within the sector and warrant further comparative research.

Jelena Lezdkalne

Conference Proceedings

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach to Optimized Human Performance

This paper presents a bifurcated model of EEG-based human–system integration, delineating two functionally distinct pathways: clinical recovery and neuroadaptive performance. The clinical recovery pathway targets persistent trait-level impairments from psychiatric, neurological, or developmental conditions using advanced signal processing techniques—including source-localized EEG, joint component ICA (JC-ICA)—to improve diagnostic accuracy and guide personalized interventions. In contrast, the neuroadaptive performance pathway addresses transient state-level fluctuations in healthy individuals, embedding real-time EEG metrics into dynamic environments such as aviation and adaptive gaming to sustain cognitive control and optimize performance under high workload and uncertainty. Together, these approaches support both adaptive responsiveness and proactive augmentation—marking a paradigm shift in cognitive engineering and human–machine teaming. Though methodologically aligned, they differ in goals, operational contexts, and populations. Maintaining this distinction enables more precise system design, ethical deployment, and scientific validation. The dual-pathway model thus provides a foundation for next-generation EEG-integrated technologies across clinical neuroscience and applied neuroergonomics.

Curtis Cripe

Conference Proceedings

A quantitative assessment approach for user operation performance grounded in cognitive models

User task performance is the most crucial indicator reflecting the effectiveness of human-computer interaction design in information systems. The evaluation results of user task performance can directly reflect the design effectiveness of information systems. However, there is currently no quantitative evaluation method for task performance. This research paper focuses on the evaluation of user task performance in information systems. By conducting ergonomic experiments based on the trackball operation method, the meta-operation time in the GOMS model is revised and supplemented. Based on the revised results of the GOMS model, a quantitative evaluation method for task performance is studied. The results show that this method can obtain quantitative evaluation results of user task performance, which can support the improvement of human-computer interaction design in information systems.

Kaili Yin, Zhangshuo Zhang, Ziang Chen

Conference Proceedings

Usability Issues in BPMN Models Analyzed Using Eye-Tracking Technology

EEye-tracking technology is a powerful tool in human-computer interaction (HCI), capturing users’ visual attention and tracking their eye movements. This technique helps determine where a person is looking at any given moment and the sequence of their gaze. It, therefore, provides information about their visual and cognitive functions. Data collected in this way can be objectively processed, leading to the design of more efficient and user-friendly interfaces. Business Process Model and Notation (BPMN) is widely recognized for its clear and understandable representation of business processes. It is generally used to manage organizations. This study aims to describe eye-tracking technology in the context of BPMN. In this study, we worked with BPMN and used an eye tracker to generate visual heatmaps to represent the focus areas of the participants under study. The experiments were conducted using the web-based tool GazeRecorder, which is free and available online. Participants walked through business process models demonstrating actions, choices, and potential interactions within systems such as booking a flight, ordering food online, or purchasing electronic devices (e.g., TV, PC, smartphone). The study determined which BPMN symbols are challenging to interpret and how the overall quality of the BPMN can be improved.

Josef Pavlicek, Martin Molhanec, Petra Pavlíčková, Matěj Brnka

Conference Proceedings

CoBotCraftLab – Approaching Human-Robot Collaboration in Digital Craft

This paper intends to depict the specific research approach established through the CoBotCraftLab portal - a robot cell for automated collaborative manufacturing in the construction industry - that is currently being installed at Bochum University of Applied Sciences (HSBO). This manufacturing cell consists of 6 collaborative robots (cobots) with individual load capacities of 20-25 kg each, which are movably mounted on linear axes and equipped with application-specific or generalist manipulators via tool changing systems. The overall system has 42 degrees of freedom of movement and will thus be able to perform a wide range of automatable tasks from the field of building construction. These include additive manufacturing of complex components, automated and collaborative prefabrication of component parts, automated application of tools such as drills and milling machines in regard to joints in lightweight structures, and applications from the field of non-destructive testing of building materials. The large-scale equipment, once installed, will present a significant contribution to the establishment of an interdisciplinary laboratory environment for research into working methods for collaborative manufacturing with craftsmen and robots in building construction. The innovative approach is to enable simultaneous and collaborative manufacturing between humans and robots by setting up the large-scale device using small-scale collaborative robots, allowing the precise and rapid production of a variety of prototypes from different materials at 1:1 scale. In this work environment, collaborative workflows involving robots and humans, both in separate and shared workspaces, will be able to be tested. Using the robotic manufacturing cell, a prototypical fabrication of demonstrators is intended to help find answers to research questions in the fields of "Digitalization of construction and craft", "Demographic change and safety" and "New methods for circular building". The cell will be used to develop workflows and record process data, which will form the basis for dealing with the following major research questions:To what extent are robotic processes capable of replicating traditional crafts, reanimating traditional techniques and transferring and scaling them to match the realm of construction? Can joint workspaces that are simultaneous in terms of space and time, involving craftsmen and robots, be developed that efficiently enable the fabrication of building components, such as for example built-in elements in housing construction? How do requirements for work safety and ergonomics change in the context of digital craft and demographic change? How can the existing gap between the experiential knowledge of humans and the precision and speed of robotics be closed in the context of construction processes? Can collaborative human-robot interactions go beyond the synthesizing function to also cater to disassembling and analytically sorting processes, as we encounter an emerging circular construction industry?

Daniel Schilberg, Erhard An-he Kinzelbach, Sven Pfeiffer

Conference Proceedings

Business Analytics Strategies in Port Economics from a Systems-Theory Perspective: A Bibliometric Analysis and Future Research Directions

Business analytics in the context of port economics encompasses data-driven insights to optimize port operations, streamline logistics, inform infrastructure planning, and enhance stakeholder coordination. Contemporary research in business analytics strategies in port economics from a systems – theory perspective is fragmented, as varied approaches and themes make it challenging for scholars and industry practitioners to form a clear vision of current integrated business analytics strategies. To address this gap, this study conducts a bibliometric analysis of 142 articles regarding business analytics strategies in port economics. The articles were published in 98 academic journals and authored by 498 scholars. The application of the bibliographic coupling methodology in the VOSviewer software enabled the identification of four clusters: (1) Contemporary Maritime Transport Systems; (2) Port Systems Analysis; (3) Performance Optimization; (4) Data – Driven Decision Support. Content analysis of the identified clusters indicates future research directions regarding business analytics strategies that contemporary ports should incorporate: (1) Improved efficiency and resource allocation via utilization of predictive analytics, real – time monitoring and performance measurement; (2) Cost optimization via reduced waiting times, improved equipment utilization, and predictive maintenance; and (3) Enhanced decision – making via data – driven insights, risk management, and sustainability goals. The findings offer a scientifically robust foundation for scholars and industry practitioners aiming to improve their understanding of how systems – theory informed business analytics strategies can be utilized to optimize the port as a system.

Alen Jugović, Miljen Sirotic

Conference Proceedings

Customer Experience and Social Robots - an experiment in a grocery store

We can expect the field of robot end-user applications to grow, and with time, we will also see more advanced and skilled humanoid robots. To ensure that this happens in a relevant, human-friendly, and sustainable way, we need to study robots and the way they can interact with humans. We need to study both the evolving technology and human behavior, i.e., the end users (customers, clients). Understanding the usefulness and potential of social and service robots requires studying them in specific real-world contexts. This paper we disucss an experiment where we investigate the deployment of a social service robot in a retail setting. More specifically we focus on customer interactions and experiences with humanoid robots in a grocery store. By investigating real-world retail contexts, the research aims to understand the practical utility and potential of social and service robots.We used structured observation top collect data and preliminary findings reveal a range of customer reactions, from joy to fear, and highlights the novelty effect, where customers take photos and follow the robot. Findings suggest that all types of users are likely to interact with the robot, though many observe it with curiosity. The paper contributes to Human-Robot Interaction (HRI) theory and suggests further long-term and also quantitative studies to enhance understanding of trust and social-emotional reactions in real-world contexts.

Christa Tigerstedt

Conference Proceedings

Strategic Transformation towards Advanced Mechanical Engineering: A Systematic Review and Taxonomy of Trends and Enabling Factors

The field of Advanced Mechanical Engineering (AME) is undergoing a profound transformation, driven by technological innovation, digitalization, sustainability imperatives, and shifting customer expectations. Despite the strategic relevance of these developments, a coherent and comprehensive understanding of strategic readiness in this domain remains fragmented. This paper addresses this gap by developing and validating a holistic conceptual framework — a taxonomy — using a design research approach. Based on a systematic literature review (from 2023 onward, Web of Science Core Collection), an inductively derived framework was refined to synthesize current scientific knowledge while offering practical utility for industrial application. The aim is twofold: to consolidate state-of-the-art academic insights and to provide a practice-oriented evaluation matrix that companies can apply to assess their strategic positioning and identify key areas for future investment. The resulting taxonomy structures the strategic landscape of AME along two axes: five strategically relevant trends (dimensions of strategic transformation) and four overarching enabling factors (transversal trends), which act as critical levers enabling and influencing the five strategically relevant trends. The findings illustrate how the interplay between these trends and enablers reshapes engineering design and manufacturing systems — highlighting, for instance, modular and flexible design approaches, digital twins, and data-driven decision-making as central to achieving excellence and sustainability. Ultimately, this validated taxonomy provides a robust foundation for future research and serves as a pragmatic tool for practitioners. It supports organizations in systematically organizing and aligning their strategic initiatives and offers actionable insights for academics, engineers, and decision-makers aiming to foster innovation in engineering design and manufacturing in response to emerging challenges.

Julia Berner, Holger Kett

Conference Proceedings

Securing Interfaces of a Multinational Standard with Technical Specifications for Data Sharing: Challenges of Authentication and Authorization

Standards are helpful to establish interoperability within multinational coalitions. In a military context the NATO standard STANAG 4559 outlines models and processes for the sharing of Intelligence, Surveillance and Reconnaissance (ISR) data. This paper explores the intricate challenges of securing such data dissemination processes, particularly focusing on authentication and authorization mechanisms. As security requirements evolve from a "System High" to a "Zero Trust" approach, the need for stringent identity verification and privilege management becomes paramount, especially in untrusted network environments. We analyze various authentication and authorization technologies, from Basic Auth to OpenID Connect (OIDC), to identify their applicability within the constraints of a multinational data sharing standard. We highlight key challenges, including compatibility with legacy systems, coordination for common (that is, compatible) configurations, and the implications of integration within a broader network context. Through empirical case studies and participation in exercises, we provide insights into effective strategies for overcoming these obstacles, thereby contributing to the development of robust security frameworks in coalition operations.

Lorraine Hagemann, Simon Schwarz, Barbara Essendorfer

Conference Proceedings

Impact of Pedal Design Parameters on Operational Efficiency and Usability in Foot Interaction Systems

Foot-based interaction offers a valuable hands-free input method in complex multitasking environments. This study used a Halstead-Reitan tapping task to evaluate how pedal resistance (5.8N–28N), force method (forefoot and rearfoot), and angle (0° and 30°) affect interaction efficiency. Results showed pedal type significantly impacted performance, with 5.8N and 20N pedals yielding the highest tap rates and best user experience. While angle and force method had no significant main effects, their interaction with pedal type was notable. Findings provide ergonomic guidance for optimizing foot-controlled interface design.

Yafeng Niu, Yiyan Wang, Hongyang Zhang, Shatong Yang

Conference Proceedings

Calibration of Illuminance in Virtual Engine Light Rendering Based on Lighting Simulation Values

With the continuous improvement of computers' ability to recreate real environments, when immersive virtual reality devices are used for lighting design, approximate models are often adopted due to real - time rendering performance limitations. This leads to designs relying on subjective perception, making it difficult to achieve precise quantitative verification. Professional lighting design software can perform physically accurate lighting calculations, and virtual engines can conduct efficient real - time rendering. Combining the advantages of the two makes it possible to achieve correct calculation and visual verification of light distribution in the engine. This paper proposes a new method of using Unity HDRP as a lighting design tool. Through in - depth research on the rendering pipeline and setting key parameters, correct light distribution and calculation can be carried out in the game engine. By creating the same virtual environment, the brightness distributions on the same surface calculated by Unity and Dialux are compared. The results show that after external parameter calibration, Unity is reliable in reproducing light distribution, and combined with real - time rendering, it can conduct correct and visual lighting design.

Chen Cheng, Xiaozhou Zhou

Conference Proceedings

Software-supported decision support for the foresighted planning of digital business models

To remain competitive, companies must continuously adapt their value proposition, especially in response to increasing demands for sustainability and digitalisation. Small and medium-sized enterprises often struggle to implement future-oriented digital business models. The aim is to develop decision support to help companies plan ahead and assess their value proposition, with a focus on foresighted planning. Based on literature research, expert interviews and the analysis of existing solutions, an understanding of “sustainable value” and requirements of decision support are defined. Decision support is implemented in a software. The main contribution is the setup of functions and content such as a list of influence factors, analysing influences and evaluating ideas, control questions and support for the implementation of digital business models. Validation through expert interviews and workshops in mechanical and plant engineering shows that the software supports enterprises in foresighted planning of value proposition and the selection of a concept for digital business models. It makes them robust towards the variety of future scenarios.

Iris Graessler, Alena Tusek

Conference Proceedings

A Hand-Tracked Rotational Interface for Parameter Input in Mixed Reality CAD

Mixed Reality (MR) offers opportunities to enhance early-stage Computer-Aided Design (CAD) by enabling immersive, spatially integrated workflows. However, current MR CAD systems struggle with precision, efficiency, and intuitive interaction, limiting their professional adoption. This study introduces and evaluates a novel, hand-tracked rotary input system that allows designers to manipulate CAD parameters by twisting, pushing, or pulling a virtual knob, enabling direct interaction without controllers or external menus. The rotary knob was compared with a virtual numpad in an A/B test involving 12 CAD-experienced participants. Tasks assessed speed and accuracy under time constraints and were complemented by subjective workload (NASA TLX), intuitive interaction (INTUI), and observational data. Results show that while the numpad achieved faster and more precise input, the rotary knob encouraged sustained focus on the 3D model and demonstrated rapid learning effects. Participants rated it higher on engagement (“magical experience”) and saw potential for iterative design workflows, though reliability concerns and gesture discomfort highlighted areas for refinement. The findings suggest that, with further optimization, spatially layered input techniques like the rotary knob could complement traditional CAD tools, supporting more human-centered and immersive MR design environments.

Gavin Kerrremans, Lucas Van Dorpe, Jelle Saldien

Conference Proceedings

Towards the Future of Air Travel: Public Perceptions on eVTOL Aircraft and Service Design

Commercial interest in Electric Vertical Take-off and Landing (eVTOL) aircraft is accelerating, yet user perspectives on aircraft design and service models remain underexplored. Early integration of these insights is critical to ensuring successful implementation and public acceptance of this emerging transport mode. An interview study was conducted with 33 participants who attended the Farnborough International Airshow 2022, UK. Uniquely, participants had physical access to a production-size model of Supernal LLC’s SA-1 eVTOL aircraft during the interviews. Given the novelty of eVTOLs, this was of significant methodological benefit to the study. Thematic coding and analysis of the interviews using two independent researchers was conducted, resulting in two distinct thematic groupings of participants: 1) eVTOLs as a service, and 2) eVTOLs on demand. Importantly, across the two groups, there were significant differences in the perceptions towards the physical design of the eVTOL and its purpose, impacting scheduling, seat capacity, set layout, and pilot interactions. These significant findings around the design of the aircraft and service should be used in conjunction with the growing body of literature on eVTOL implementation to ensure the successful implementation of future eVTOLs and wider shared mobility services.

Arun Ulahannan, Charlotte Collins, Michael Lombardo, Christina Kang, Stewart Birrell

Conference Proceedings

Reliable Information Retrieval with LLMs: Automated Analysis and Comparison of large PDF Documents

In high-stakes professional settings like the insurance industry, extracting information from complex PDF documents is critical yet challenging due to document length and technical language. While large language models (LLMs) offer new opportunities for automating document understanding, their usefulness depends on output accuracy, transparency, and verifiability. In critical contexts, users must be able to trace information back to credible sources to reduce risks from hallucinations or misinterpretation. This research explores how LLMs can support reliable, transparent information retrieval (IR) from complex documents. We introduce five IR system variants designed to iteratively improve LLM outputs through better context preservation and fine-grained source attribution. These systems incorporate enhancements such as Markdown-based parsing, retrieval-augmented generation (RAG), and advanced document preprocessing. The final iteration integrates Multi-view Content-aware (MC) indexing, which supports semantically targeted retrieval using keyword, summary, and raw-text views. To evaluate performance, we develop a domain-specific benchmark with curated insurance documents, ground-truth answers, as well as performance metrics for assessment of the answer accuracy, hallucination rate, and source attribution precision. Results show that systems with content-aware chunking or MC-Indexing outperform earlier versions in accuracy and attribution, though with added complexity. Our findings highlight the value of structure-preserving preprocessing, targeted retrieval, and source transparency in developing trustworthy AI tools for document analysis. Future work may explore automated verification loops and user-guided retrieval to improve interpretability and reliability further.

Lara Noe, Sebastian Breier, Ruben Nuredini

Conference Proceedings

State Based HMI Prototyping for Designing Adaptive HMIs

The growing use of autonomous systems is leading to a significant change in the role of humans in technical processes. Instead of being directly involved in control and interaction, humans are more and more responsible for supervising and monitoring automated operations. This transformation is particularly evident in safety-critical domains such as maritime transport, where remote operation technologies are being implemented. Ships are no longer steered directly from the ship itself, rather they are monitored remotely by operators located in dedicated Remote Operation Centres [1].However, this new form of human–system interaction brings several challenges. As human operators are only required to intervene in special cases, they may become cognitively underloaded. Combined with monotony and potential night shifts, this can result in classic human factors issues such as fatigue, reduced attention and poor situational awareness. These factors can have serious consequences in safety-critical contexts.To minimize the risk of human errors, it is it is essential to keep the human "in the loop" and to provide specific support by designing adaptive HMIs. HMIs that adapt to task demands and user states can ensure that operators receive the appropriate information for their current workload. This requires a well-designed dialogue between humans and technology that can adapt dynamically to changing operational conditions.Against this background, the present study investigates how existing HMI design methods can be extended to incorporate different user and system states during the design phase. Current tools, such as Figma and the “KnOwledge eNrichEd CreaTive” HMI design Method (KONECT-Method) [2], do not systematically address the varying states of systems and users in the design process.This paper presents the conceptualization, development and prototypical integration of a user state framework into the KONECT HMI design tool. The first part of the paper outlines the motivation and problem definition, using workload as an example of a user state. This is followed by a review of current HMI design methods supporting adaptivity. The paper then details the selection and analysis of the KONECT method, presenting the extension that was implemented to enable user state modelling. Following this, the usability of the extended tool is evaluated in relation to common challenges such as overload and underload, and their implications for HMI design.Finally, the results are discussed and future research directions are outlined.[1] Seafar, „Operating vessels from shore control center,“ https://seafar.eu/services/, Date 16.06.2025.[2] M. Saager, A. Steinmetz, J-P. Osterloh, A. Naumann, A. Hahn, „Ensuring Fast Interaction with HMI´ s for Safety Critical Systems-An Extension of the Human-Machine Interface Design Method KONECT”, Intelligent Human Systems Integration (IHSI 2024)

Alexander Steinmetz, Marcel Saager, Jan Patrick Osterloh

Conference Proceedings

Scaffolding Autonomy: AI-Augmented Self-Paced Learning Environments for Sustainable Learning Outcomes

This paper presents the design and implementation of a digital self-paced learning format that scaffolds both knowledge acquisition and time management. While self-paced environments offer flexibility and learner autonomy, they also pose challenges in sustaining motivation, managing cognitive load, and regulating study behaviour. The learning environment supports learners through two key scaffolding layers: content-level guidance and temporal regulation.Knowledge scaffolding is achieved through structured content design, semantic navigation tools, and Retrieval-Augmented Generation (RAG) that provides personalized summaries based on learner performance. These features help learners build conceptual understanding and reinforce key concepts. Temporal scaffolding includes time-aware notifications, visual progress dashboards, and learning caps to encourage regular engagement and reduce last-minute cramming.Empirical data from over 600 learners demonstrate improved study behaviour and performance with structured guidance. While artificial intelligence plays a vital role in personalization and feedback, it must maintain transparency and trust. The system is designed to act as a supportive companion, not a controlling presence—preserving learner autonomy and ownership.This work highlights the potential of AI-augmented scaffolding to create human-centred, effective self-paced learning environments.

Kurt Englmeier

Conference Proceedings

Benefits of integrating resource management into an enterprise architecture

This paper extends previous research on the integration of model-based systems engineering (MBSE) with the Unified Architecture Framework (UAF). Building upon the author’s earlier work that established the value of the UAF's Personnel and Resource domains, this study expands the implementation to include the Projects and Operational domains, creating a more comprehensive enterprise architecture (EA) model. This research demonstrates how the UAF can be applied to a manufacturing company to improve collaboration across disciplines and enable informed decision-making throughout the organization. Key outcomes include integrated viewpoints across UAF domains and aspects, automatic verification of requirements through parametric modeling, and dependency matrices that illustrate cross-domain relationships of the organization. Results show that this methodology successfully maintains traceability between enterprise domains by considering aspects such as requirements, taxonomies, structure, and processes. This work establishes a foundation for EA modeling and demonstrates the UAF’s capability to bridge traditional systems engineering (SE) practices with human factors (HF) considerations. By integrating various stakeholder concerns of the enterprise, transparency across disciplines is accomplished within a model environment. Future research will explore the Services and Security domains to complete the UAF implementation.

Sarah Rudder

Conference Proceedings

A Predictive Model of Human Trust Evolution Over Time in AI-based Recommendations

Understanding the dynamics of human trust in AI-based recommendations is an important challenge for the design of decision support systems and human-machine teams. This study aims to advance quantitative modeling of reported trust levels evolving over successive trials across several weeks. Data from 53 participants was collected in a visual search experiment with AI system recommendations. The Feedback-based Dynamic Trust Model (F-DTM) proposed herein is based on ten predictors, focusing on variables linked to different types of delayed feedback. Six different types of machine learning regression models were compared, with the decision tree model demonstrating the best predictive performance (R² = 64.9%, RMSE = 0.72) on held-out data. Some variables were then converted into cumulative sums to capture more effectively the sequential nature of the data with a memory of past outcomes. These modifications significantly improved the performance of the new 12-variable decision tree model (R² = 69.92%, RMSE = 0.66). A subsequent analysis on this revised F-DTM model assessed the impact of eliminating variables one at a time, reaching an R² of 70.41% and an RMSE of 0.65. These findings help address the current lack of quantitative models of trust evolution in AI. However, the present cumulative sum memory approach of the F-DTM, employing supervised machine learning, may be improved on by using more complex models designed for time-series forecasting. Directions for future research include investigating temporal models, such as long short-term memory (LSTM), hidden Markov model (HMM), ARIMA or autoregressive models to predict trust evolution in AI-based recommendations.

Vincent Fer, Daniel Lafond, Gilles Coppin, Olivier Grisvard

Conference Proceedings

Visual Complexity and Aesthetic Value in Design: Between Hedonomics, Emotional Experience, and Ergonomic Aesthetics

This article proposes a methodology for analyzing morphological load in the design of seating objects, with a focus on the relationship between aesthetics and functionality. Drawing on recent theoretical concepts such as embodied aesthetics and affective ergonomics, a semi-quantitative evaluation grid is developed to quantify the degree of formal elaboration of a chair based on six key criteria: complexity, functional justification, expressiveness, adaptability, sensory interaction, and affective function. The grid is applied to eight iconic chairs from modern and postmodern design, resulting in a tripartite typology: chairs with predominantly functional load, predominantly aesthetic load, and balanced load. Through comparative analysis and graphical representation of these models, the decisive role of morphology in communicating the aesthetic and ergonomic values of the product is highlighted. The article contributes to the development of an evaluation method applicable in design research, education, and professional practice.

Maria Moga

Conference Proceedings

Mixed reality glasses in remote R&D collaboration

The digitalisation and the emergence of metaverse technologies are revolutionising the way we work, particularly in office tasks, where remote work has become increasingly prevalent. However, the implementation of interactive and illustrative tools to support location-independent collaboration during research and development (R&D) is still an area that requires further exploration. This study examines the application of two mixed reality (MR) glasses for remote collaboration in R&D, specifically focusing on dynamic 3D models of engines. Two human factors experts experimented the MR glasses and conducted a SWOT analysis. Findings revealed that MR glasses can enhance interactivity, user interfaces, sound, and imagery quality compared to traditional online tools. Challenges included time-consuming setup and initial stability issues, indicating a need for user expertise. The study highlights the potential of MR glasses in R&D collaboration while emphasising the importance of user experience and simplified system initialisation.

Susanna Aromaa, Antti Väätänen

Conference Proceedings

Reviving Lost Heritage Through AI: A Hybrid Design Approach in Downtown El Paso

Urban development in historically significant areas often results in the loss of buildings with cultural and architectural value. While full reconstruction is rarely practical, emerging artificial intelligence (AI) tools offer new ways to reinterpret demolished heritage and symbolically reintegrate it into the urban landscape. This research explores how AI can assist in creating design interventions that evoke the memory of lost buildings within existing structures. The study focuses on a case in downtown El Paso, Texas: the former site of the Union Bank and Trust Company, now a parking structure. The research applies a hybrid methodology that blends archival research, AI tools, and simulated oral histories. Resident Identification: Names of historical residents are obtained from El Paso city directories to ground the narrative in historical context. Narrative Generation: With assistance from ChatGPT, simulated oral histories are created based on known architectural features and urban memory of the demolished building.Prompt Engineering: Extracted descriptive elements are converted into detailed prompts. AI-Based Visualization: Tools including Adobe, Midjourney, Vizcom, and ChatGPT’s visual capabilities generate design concepts inspired by the historic building. Design Intervention: Proposed changes to the existing parking structure focus on minimal physical alterations that visually reference the Union Bank building’s original form and style.The outcome will include conceptual visual designs for adapting the existing structure to reflect lost architectural heritage. Rather than attempting full reconstruction, the proposal introduces subtle elements—such as stylistic façade motifs and material textures—to bridge past and present. The designs aim to reconnect community identity with the built environment in a feasible, contemporary way.This research presents a replicable framework for using AI to reinterpret lost heritage, especially in sites where rebuilding is not possible. By combining digital tools with historical resources and community-based narratives, it demonstrates how symbolic architectural revival can be both respectful to the past and responsive to current urban needs. The methodology also offers potential applications in other cities where architectural heritage has been lost or neglected.

Seyed Damoun Pezeshki, Mahyar Hadighi

Conference Proceedings

Evaluation of Technostress Creators among Healthcare Workers in Saudi Arabia

Technostress is a new form of stress that affects several people, including healthcare workers. Technostress may increase because of the increasing responsibilities and demands that this digitization places on health care workers (HCWs).Technostress has been defined as the negative aspect of technology use. Both individuals and organizations suffer from technostress, which has been linked to negative health outcomes, reduced job performance, increased job discontent, and disruptions in work settings. Addressing technostress among healthcare professionals has received little attention, despite the increasing adoption of technological advances in healthcare facilities. The aim of this study was to investigate the technostress creators among healthcare workers in Family Medicine Centers (FMCs).Methods: A cross-sectional study was conducted in one of the family medicine centres in Saudi Arabia and included healthcare workers working there. The data were collected through an online questionnaire sent through email from February to March 2024. All the participants took a two-part questionnaire that asked about demographic data and ‎technostress creators (complexity, overload, invasion, uncertainty, multitasking, and work interruption). Informed consent was obtained from all healthcare staff who agreed to participate in the study. The study was approved by the Institutional Research Board (IRB) of the Royal Commission health service program in ‎Jubail.‎Results: In total, 101 participants were enrolled in this study, with a response rate of 79.2%, the result calculated the mean and standard deviation of participants, agreement for ‎technostress. Among all the technostress creators, the highest mean of participants, agreement recorded for techno-complexity (There are always new developments in the digital technologies we use in our organization), showed 4.34±3.23. However, work interruption had a low level in the total mean (2.01± 1.18); the total mean was (3.04±0.70) at level (neutral). Correlations with demographic factors were not discovered in this investigation, which indicates that technostress is a widespread problem that affects practitioners from every category. This generality emphasizes how vital it is to investigate the root origins of this occurrence.Conclusion: This study showed a significant level of technostress among HCWs, especially in techno-complexity, which concurs with other studies. Other creators are still favourable regarding technostress. To achieve a useful and long-lasting level of utilization, decision-makers should take into account the cognitive and social components of digitalization. Additional investigation is required to develop causal and practical models for workable action plans.

Marwan Babiker, Eda Merisalu, Zenija Roja, Henrijs Kalkis

Conference Proceedings

Dynamic adjustments of Correlated Color Temperature (CCT) in urban waterfront night lighting: effects on subjective aesthetic preferences

As urbanization accelerates, urban waterfront nightscape lighting is essential for shaping a city's image and improving residents' well-being. However, the impact of dynamic color temperature changes on residents’ aesthetic preferences in urban nightscape lighting remains underexplored. This study utilizes the Unity platform to simulate the waterfront nightscape of Xuanwu Lake in Nanjing, Jiangsu Province, aiming to investigate the influence of dynamic lighting parameters—including Initial Correlated Color Temperature (CCT), CCT Gradient, Number of CCT Levels, and Frequency of Dynamic Effects—on residents’ subjective aesthetic preferences. Additionally, demographic factors such as age, region, and education level are analyzed. A total of 42 participants evaluated 135 waterfront nightscape lighting scenarios based on three dimensions: Overall Aesthetic Perception, Perceived Comfort of Speed, and Range of Color Perception.The results indicate that: (1) Initial CCT and CCT Gradient significantly affect Overall Aesthetic Perception, Perceived Comfort of Speed, and Range of Color Perception (p < 0.05). The highest rating for Overall Aesthetic Perception (M = 4.15) was observed when the Initial CCT was 3000K and the CCT Gradient was 1000K. (2) When the Initial CCT was 3000K, Perceived Comfort of Speed was rated highest (M = 4.16). Younger participants (aged 18–24) were more sensitive to changes in Frequency of Dynamic Effects, with excessively high frequencies leading to decreased comfort. (3) Initial CCT, Number of CCT Levels, and CCT Gradient significantly influenced Range of Color Perception (p < 0.001, p < 0.05, p < 0.05). A lower Initial CCT expanded the Range of Color Perception, with the highest value (M = 4.56) observed at an Initial CCT of 1000K. The Range of Color Perception was maximized when the Number of CCT Levels was 3 (M = 3.44) and when the CCT Gradient was 3000K (M = 3.45). (4) The 25–39 age group and residents from southern regions exhibited significantly stronger aesthetic preferences for dynamic lighting (p < 0.001). Gender had no significant effect on Overall Aesthetic Perception (p > 0.05). This study provides theoretical foundations and practical guidance for urban waterfront nightscape lighting design. We recommend that core waterfront buildings adopt an Initial CCT of 3000K, a CCT Gradient of 1000K, and a Frequency of Dynamic Effects of 2 seconds to accommodate diverse demographic preferences.

Zi Yi Zhang, Jing Li, Yu Zhang, Xiaoxiao Wang, Ying Luo, Chengqi Xue

Conference Proceedings

Timing Matters - The Role of Timing in Explanation Delivery

With the rapid advancements of autonomous systems and their integration into everyday life, explainability has become essential for fostering user trust and promoting effective human–system collaboration. However, the utility of explanations depends not only on content but also on timing. Prior research shows that pre-action explanations improve trust and understanding, yet the optimal timing remains unclear—especially under varying cognitive workloads.Building on our earlier theoretical framework based on the SEEV (Salience, Effort, Expectancy, Value) attention model, we empirically tested optimal timing through a two-phase interactive game. In Phase 1, participants completed a Reaction Time Determination task, responding to colour–word cues to establish a baseline for processing minimal instructions. In Phase 2, the Reactive Game, participants collected coins of a target colour indicated by a brief cue, requiring quick interpretation amid distractions.Seventeen participants (mean age 44.7 years, SD = 16.4) completed the study. Analysis of the gameplay data revealed an average reaction time of 2.58s to act on explanations—closely matching the 3s window predicted by our prior model. Subjective workload was evaluated using the NASA-TLX, which indicated moderate mental and temporal, low physical strain, and significant correlations between mental demand, effort, and frustration—highlighting the impact of timing on cognitive load.This study contributes to human-centred system design by providing evidence-based insights into optimising explanation timing for improved user comprehension and performance. The approach shows how explanation strategies can be informed by cognitive models and validated in interactive, user-centred settings. Future work will explore adaptive, context-aware explanations tailored to individual cognitive states.

Akhila Bairy, Mehrnoush Hajnorouzi, Astrid Rakow, Martin Fränzle, Maike Schwammberger

Conference Proceedings

Product Innovation In Sustainable Design: Internal Partition System For Improving Indoor Well-Being

The authors was designed and developed a subsystem of vertical interior partitions for renovations and new constructions, ensuring the adaptability of spaces to changing user needs, as part of the PON doctoral research project entitled “Health, Environment, and Architecture. Materials and Components for Product Innovation in Sustainable Design”. It consists in a prefabricated and modular subsystem designed to create, acccording to the Circular Economy, bio- and eco-friendly partitions that can be quickly assembled and disassembled, with high levels of recyclability and reusability, based on the principles of Life Cycle Thinking and Design for Disassembly. These prerogatives were complemented by the goal of using materials that naturally improve living comfort, starting from a previous environmental impact assessment conducted by the authors on hemp-based products: a raw material capable of creating an environmentally, economically, and socially sustainable system, realizing local development prospects and responding to the development and well-being needs of humanity and the planet. Therefore, a prefabricated system was developed to be constructed by assembling hemp panels on wooden grids. The new system's development was divided into four phases: design, off-site production, on-site assembly, and on-site disassembly, which led to the creation of the system's prototyping drawings. The work process followed the steps of the Bill of Materials, analyzing materials, system subcomponents, and their quantities, as well as assembly anchoring systems, concluding with the identification of disposal scenarios. Finally, the design process led to the development of a technology that represents an evolution of traditional systems already in use. The goal was to create a set of elements that are easy to transport and assemble (design of a kit ready for on-site assembly), highly versatile in construction (modular system), and easily disassembled, reusable, and/or recyclable.

Maria Chiara Capasso, Donatella Radogna

Conference Proceedings

Enhancing Programming Task Performance with LLMs: The Role of Query Formulation and Task-Technology Fit

This study investigates the effectiveness of large language models (LLMs) in solving programming tasks, with a particular focus on how query formulation influences response quality. Using the Task-Technology Fit (TTF) framework, the research explores the alignment between task requirements and LLM capabilities, and how this alignment impacts student performance.An experiment was conducted with 60 students from the Faculty of Informatics and the Faculty of Engineering at the Juraj Dobrila University of Pula. Participants were asked to solve the “8 Queens” problem in two 30-minute phases: first independently, and then with assistance from the ChatGPT-4 model, during which they could issue 5–10 iterative queries. This setup enabled a comparative analysis of student performance in traditional versus LLM-assisted conditions. Data collection included a structured questionnaire aligned with TTF constructs. The data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM), which modeled the relationships between task characteristics (TASK), technology characteristics (TECH), task-technology fit (TTF), and user performance (PERF). The results indicate that both task complexity and technology capabilities significantly contribute to TTF. In turn, TTF strongly influences user performance with the model explaining 47.3% of the variance in TTF and 33.2% in performance.Statistical analysis confirmed a significant improvement in solution accuracy when tasks were completed with LLM support. Furthermore, qualitative analysis showed that well-structured, context-rich queries led to more accurate and relevant model responses. The findings underscore the pivotal role of query formulation in optimizing the use of LLMs for programming tasks. Developing effective query strategies enhances task-technology alignment and ultimately improves performance. This study contributes to a growing understanding of human–AI interaction and highlights the importance of integrating query design skills into educational and professional programming contexts.

Darko Etinger, Lucija Josipović Deranja

Conference Proceedings

Graphical AI workflow modelling: Identifying relevant competencies in AI-based automation of business processes

This research investigates how Artificial Intelligence (AI) can be systematically integrated into existing business processes by combining suitable competencies with graphical AI workflow modelling. While AI offers a high potential for automation and increased efficiency, its implementation often fails due to a lack of interdisciplinary competencies that bridge the gap between domain expertise and IT know-how. Low-code platforms and visual modelling tools are increasingly recognised as enablers, empowering non-programmers to intuitively create graphical AI- based workflows. Nevertheless, specific competencies are required to realise the full potential of AI, the domain specific knowledge and align technical understanding with AI capabilities. The paper reviews the state of the art in AI-driven business process automation and competencies for visual low-code approaches. It then presents a practical solution to identify and systematise essential competence areas. Based on this, a practical competence model is developed to support the design of user-friendly, AI-enabled workflows. This is tested in a practical application context — emergency management — where it supports critical decision-making processes and is validated through expert feedback. The study concludes by offering actionable recommendations to help organisations foster the necessary competencies and methods for competently integrating AI into their digital processes.

Iris Graessler, Deniz Oezcan

Conference Proceedings

Context-aware Product Recommendations Using Weather Data and AI Models

Traditional recommender systems generate product suggestions based on user purchase history or collaborative filtering techniques. Although effective under static conditions, dynamic contextual factors, such as weather conditions and geographic location, are frequently overlooked despite their clear influence on consumer behavior. To overcome these limitations, context-aware recommender systems integrate real-time situational data, including ambient temperature, precipitation, and demographic attributes, into the recommendation process, therefore providing more precise and relevant suggestions.An author-developed framework employs OpenAI’s GPT-3.5 Turbo and GPT-4 variants to produce personalized order recommendations. Upon receiving a user-provided location (e.g., “Pula”), current weather data are retrieved from an external API and combined with user profile information to construct contextualized prompts. These prompts are sent directly to the OpenAI API, which returns context-aware recommendations based on the provided inputs. By merging environmental context and user preferences with advanced generative AI, alongside a given product database, recommendations are demonstrated to be substantially more relevant than those produced using traditional methods.

Alma Smajić, Mia Rovis, Ivan Lorencin

Conference Proceedings

Large language models as Retail Cart Assistants: A Prompt-Based Evaluation

Large language models (LLMs) offer promising capabilities for interpreting user input in natural language and translating it into structured formats for downstream processing. This study investigates the use of LLMs as shopping-cart assistants, limited to the task of parsing natural-language commands into a predefined JSON schema containing three fields: action, product, and quantity. The objective is to evaluate the models’ ability to perform accurate semantic parsing under consistent conditions. To examine the impact of prompt design, three distinct prompting strategies were developed: a minimal instruction specifying the target fields, an extended prompt including synonym guidance and formatting rules; and a few-shot learning approach incorporating multiple examples with strict output requirements. Each prompt variant was applied identically across all selected LLMs to ensure comparability. The evaluation was conducted using a dataset of 1,000 synthetic shopping-cart commands generated via a large generative AI model. Each command was paired with a known ground truth, structured into the same target schema. Model-generated outputs were transformed into CSV format and compared against these references to assess parsing performance. By systematically varying prompt complexity and controlling for model input, this study provides a controlled comparison framework for assessing prompt effectiveness in narrow, structured tasks. The results contribute to a deeper understanding of prompt design as a determinant of LLM utility in applied, goal-oriented scenarios.

Ratomir Karlović, Ivan Lorencin

Conference Proceedings

Certifying unmanned systems

The paper presents a review that summarizes and importantly synthesizes the status of the certification for the time being a Norwegian drone system. Focus is on how this certification process generates new insights or creates an integrated analytic approach (critical view on) the activity of certifying based on feedback from Norwegian military end users. Main question to be discussed when planning and implementing a test set-up for the certification i.e., a course syllabus, is how to facilitate a course syllabus and activities that most efficiently qualify and certify an unmanned system. The test bed, developed by the Norwegian Defense Research Establishment (FFI), are supported by a framework of various software configurations adapted for behaviors in various military applications across different domains (underwater, ground, air). We investigate how operators and instructor trigger dialogue in observational tasks during tutored physical flying session certifying an air drone system and how do debriefing and learning create cognitive comprehension that is the competency developed in a team during certifying a military unmanned system.

Rune Stensrud, Ina Berby, Aleksander Simonsen, Olav Rune Nummedal, Mathias Minos-stensrud, Sigmund Valaker

Conference Proceedings

Reflective practice in primary physical education: developing context-specific tools and design considerations to support physical education teachers

Primary school physical education (PE) plays a pivotal role in fostering active lifestyles by promoting enjoyment of physical activity and supporting the development of skills, knowledge, and attitudes essential for lifelong engagement. However, delivering enjoyable PE lessons to all children remains complex, given the varying abilities, interests, and needs among children. One way to address these challenges is through reflective practice, wherein teachers critically evaluate their lessons, using feedback from their pupils, identifying areas for improvement, exploring alternative teaching strategies, testing them and reflecting on the outcomes. Despite its benefits, consistent and systematic reflection remains uncommon among primary school PE teachers.Technological tools are promising for supporting teachers in reflective practices. While applications like lesson recording software, feedback tools, and e-portfolios have gained traction in secondary and tertiary education, they often fail to meet the specific needs of primary school PE teachers and children. This paper addresses this gap by exploring design considerations for tools that support context-sensitive reflective practice of primary school PE teachers, aiming to improve teaching quality and better align lessons with children’s needs for PE enjoyment. A user-centered, iterative research-through-design approach was applied to develop a tangible feedback device for children and a digital mock-up reflection tool for teachers. We combined PE lesson observations, focus groups, reflective questionnaires, user-testing, and evaluation. Stakeholders, including primary school PE teachers, pre-service PE teachers, children and design researchers, collaboratively explored the challenges and practical needs surrounding feedback and reflective practices in primary school PE settings. Findings indicated a preference for a tangible, portable, battery-powered feedback device for children capable of offline operation to ensure usability during PE lessons. The device should facilitate easy and anonymous data collection, secure data storage and reliable data transfer. Iterative design cycles enhanced usability, resulting in an intuitive, robust and child-friendly device incorporating press buttons and smiley-face indicators as response labels. Feedback questions were adapted to children’s linguistic levels, ensuring alignment with teaching practices that foster children’s PE enjoyment. In parallel, teachers expressed a preference for a digital, web-based reflection platform to facilitate systematic reflection. A mock-up was developed in Figma, guiding teachers through structured reflection phases using prompts and templates. It supported accessible and time-efficient activities, including PE lesson evaluation, searching PE teaching resources, collaborating with peers via an online community platform, and creating action plans for future lessons. The reflection prototype was also integrated with the tangible feedback tool, facilitating seamless data transfer and enabling teachers to configure feedback. Visualizations of children feedback data were presented in an accessible format, and the tool allowed teachers to store, and archive resources such as recorded lessons, peer-assessments, self-assessments and articles, while ensuring efficient documentation, security, privacy, and easy navigation. The findings led to design consideration for primary school PE-specific feedback and reflection tools, highlighting their potential to improve children’s PE experiences and support teachers’ professional development. The study emphasizes the importance of understanding the PE context and collaborating with teachers and children when designing such tools.

Anoek Adank, Rosanne Bloemraad, Dave Van Kann, Steven Vos

Conference Proceedings

The importance of structure in transformation chaos: A Transformation Framework

Dynamic market conditions, technological disruption and social change require organizations to continuously adapt and evolve. However, studies on organizational change show that the majority of transformations undertaken fail because they are characterized by a lack of clarity, overload and ineffective measures. This paper shows how a clear structure as a critical success factor can make the chaos and challenges of a transformation manageable. The focus here is on a practice-oriented framework that divides a transformation into nine essential building blocks with activities that are critical to success. The structure of the framework is understood as a flexible organizing principle for a transformation without hindering creativity and dynamics. Case studies show the adaptability and applicability of the framework to different characteristics and dimensions of transformation. The transformation framework provides an operative structure and enables transformation managers for transparent orchestration and implementation of transformation.

Iris Graessler, Benedikt Grewe, Marc Fritzen

Conference Proceedings

Taking Perspective: Broadening Acceptance of a Serious Game Framework

Educators often face challenges or avoid incorporating digital learning content into theirclasses due to the limited availability of content that meets specific course requirements.In previous research, a vision was presented for developing and deploying serious gamesthat leverage Digital Game-Based Learning (DGBL) and domain-agnostic frameworks toenhance educational experiences across diverse fields of knowledge. Evaluating thisconcept, a central insight was that the fundamental game loop should remain intact acrossdifferent knowledge domains - rather than requiring educators to rebuild a game for eachsubject, a core game loop was maintained, where progression depended on missioncompletion, enabling easy alteration of visual setting, storytelling components, orgamification features for extra motivational impact. Studies confirmed that a domain-agnostic serious game framework, combined with robust interoperability standards, couldsignificantly improve accessibility for educators seeking to delve into DGBL environmentswithout in depth game development knowledge. The presented body of work intends toshow how modular designs, centralized maintenance, and flexible mission structuressupport a wide range of instructional goals, ultimately fostering deeper learnerengagement and more sustainable knowledge acquisition. However, a key limitation is thecurrent 4X-style (explore, expand, exploit, exterminate) game loop, which fails to engageevery learner profile equally. Consequently, in its next iteration the concept is broadenedto additional game play styles, presenting an approach for integrating a role-playingmechanic with shifting perspectives. By examining a serious game developed for theGerman Weather Service (DWD), it is demonstrated how perspective-taking within a role-playing context can enrich the narrative, deepen learner immersion, and ultimatelyimprove understanding of the diverse roles embedded in complex processes.

Ehm Kannegieser, Sergius Dyck, Andreas Lambert, Stefan Wolff, Andy Philipp

Conference Proceedings

Understanding generative AI's role in higher education: a teacher perspective on responsible integration of AI in business education

This publication explores the potential and actual use of generative AI (GAI) in business education at Arcada University of Applied Sciences, with a particular focus on the teacher’s role in integrating GAI into course modules. Research suggests that GAI can enhance teaching and student learning by offering personalized and engaging experiences. The aim of the study is to contribute to a deeper understanding of AI in education and to promote knowledge about the responsible integration of AI into business education. A further objective is to develop teaching practices that prepare students to engage with the technology responsible in their future professional lives.We investigate teachers’ perceptions of AI and their reflections on working with it. Additionally, we describe our collaborative work on these issues over the course of a year. During spring and autumn 2024, we conducted research into our own teaching practices in relation to AI within our teaching team. In parallel, we collected data from workshops where current AI practices, tools, challenges, and educational needs were discussed.The project also provides insights into how AI can be integrated across various areas of business education and lays the foundation for future research on optimizing AI use in educational contexts.We identify challenges related to safety, bias, and academic integrity. Finally, we discuss future trends and the evolving role of teachers in an educational landscape where AI is embedded in the learning environment. A balanced use of AI is recommended, and continued work is needed to ensure responsible, reliability, and ethical integration.The publication aligns with strategic goals concerning sustainable digital solutions and responsible AI. We argue that the publication contributes to the broader discourse on high-quality, sustainable, and responsible education. Our project supports Sustainable Development Goals 4 and 11, and peer learning has been central throughout our process.

Christa Tigerstedt, Susanna Fabricius

Conference Proceedings

Exploring Barriers in Cybersecurity Training: A Socio-Technical Perspective on Cross-Organizational Portability and Inclusion

Cybersecurity training and practical exercises such as cyber-range and Capture-The-Flag (CTF) events are increasingly used to build organisational resilience. However, challenges remain in reusing and adapting these exercises across organisational and national boundaries. This paper explores two key aspects that affect the long-term sustainability and impact of cybersecurity training: cross-organisational portability and inclusivity. Drawing on a cross-border workshop with participants from Sweden and Norway, we identify technical, organisational, and pedagogical barriers that hinder the reuse of cybersecurity training and exercises, including the lack of shared packaging standards, mismatched legal frameworks, hidden infrastructure dependencies, and divergent learning objectives. We argue that portability is not only a technical issue but also a socio-technical challenge requiring clearer communication and aligned expectations. The paper also investigates how inclusivity is understood and implemented in cybersecurity education, highlighting promising practices, such as diverse learner pathways, multilingual materials, and community-led efforts, alongside persistent structural limitations. Based on these findings, we propose the use of lightweight, machine-readable manifests to improve scenario portability and call for more structured institutional support for inclusive training environments.

Ala Sarah Alaqra, Farzaneh Karegar

Conference Proceedings

Enhancing Community Care Through Digital Coordination: A User-Centered Approach to Expanding the Helferportal

Demographic changes are pushing communities of all sizes in Germany, as well as other ageing societies, towards a critical care crisis. Integrative, cross-sectoral care structures that combine the strengths of volunteers and commercial service providers are essential to meet the growing demand for care services and reduce the financial and emotional strain on family carers. For these care structures to be effective, they must be efficiently coordinated to maximize care capacity. A centralized digital coordination tool can transparently connect individuals in need with care providers and volunteers. Ensuring its acceptance and seamless integration into existing community advisory and coordination processes, however, requires careful consideration of the needs of the different actors involved in caring communities. We adopted a user-centered design approach to expand the existing Helferportal application. As a first step in this participatory research project, we focused on identifying opportunities for digitization in community care processes as well as defining software requirements and key features.Method: We conducted semi-structured interviews with (N = 23) care advisors, community coordinators, and social service providers in a district town in Germany to gain a detailed overview of community care processes and identify digitization opportunities. Audio recordings of the interviews were literally transcribed and analyzed in MAXQDA by structured qualitative content analysis.Results: Participants identified significant potential in a software application for the coordination of integrated care structures that include volunteers. A centralized digital booking and coordination system to schedule appointments or recurring services was recognized as essential for improving cross-sectoral care management and reducing phone-based communication in daily work processes. A privacy-compliant communication platform was also recommended to facilitate the spontaneous distribution of support needs among volunteers and professionals. Additional requests included digitizing documents for documenting advisory work and to streamline billing processes. Barriers to adoption included the need to build trust through in-person interactions and high usability requirements, underscoring the importance of a participatory approach in evaluating the future application. The findings underscore the potential of digitization to enhance care structures and to help mitigate the impending care crisis by fostering stronger, more connected communities.

Tim Kuball, Thomas Oeben, Luise Look, Georg Jahn

Conference Proceedings

Investigation of research gaps and needs with regard to the use of model-based systems engineering for the development of barrier-free vehicles

Systems Engineering (SE) and in particular Model-Based Systems Engineering (MBSE) are disciplines that are particularly suitable for the development of complex systems. MBSE is therefore often used for developments in the fields of vehicle technology and mobility systems, as these systems are highly complex. In these areas, there is a clear trend in research and development towards innovative and sustainable public mobility systems. For this purpose, vehicles are being developed that are specially adapted for use in the respective mobility systems and are designed to meet the needs of customers. An important feature of vehicles used in such a mobility system, which is intended for the general public, is that the vehicles should be as accessible and barrier-free as possible.The integration of systems that can be used for the barrier-free design of vehicles is also characterised by a high degree of complexity. This is due to the very different requirements that different types of mobility restrictions entail, the technical design of the systems themselves, the interaction of the individual systems and the limitations imposed by the vehicles in terms of payload and installation space. By adding the high degree of complexity of the vehicles themselves, an accessible or barrier-free vehicle therefore represents a system with a high degree of complexity. However, the integration of accessibility elements into an existing vehicle is also associated with a high degree of complexity for the reasons mentioned above.Due to the complexity associated with the barrier-free vehicle system, the use of MBSE to develop vehicles that are as barrier-free as possible seems very sensible. Due to the relatively large proportion of people with mobility impairments, ethical aspects and the legal framework in various countries that prioritise inclusion, the topic of barrier-free mobility is also highly relevant. For these reasons, a closer look at the use of MBSE for the development of accessible vehicles is justified. For the reasons explained above, this article will first analyse the extent to which MBSE is already being used for the development of accessible vehicles. In particular, the methods and tools of MBSE that have been designed specifically for the development of accessible vehicles or that support them are analysed. For this purpose, a systematic literature review is carried out, which shows that there are large research gaps with regard to the use of MBSE for the development of barrier-free vehicles. The next step of the article examines and justifies why there is a need to close the identified research gaps, so that a need for research is identified. Furthermore, the article looks at which approaches exist in the literature that could be used to design MBSE methods and tools that address the development of accessible vehicles. This step also includes an analysis that identifies the gaps and needs in the area of tools for the development of accessible vehicles beyond the MBSE.

Luca Lanz, Eva Maria Knoch, Matthias Vollat, Albert Albers

Conference Proceedings

Identifying practices in the safety observation process in Finnish organisations

Safety observations constitute a crucial tool for enhancing safety management and culture, thereby supporting the implementation of safety strategies. Safety observations include unsafe conditions and actions, while near-miss incidents are typically defined as unplanned adverse events that could have resulted, but did not, in injury or damage to people, property, equipment, materials or the environment. Although there are no established guidelines for the safety observation process, various practices for collecting and utilising safety observations in the workplace have emerged. While collecting safety observations has become more common across different sectors, the practices vary among organisations. These practices’ effectiveness has not been evaluated, and some implementation issues may not have been addressed. This article tackles identifying practices in Finnish companies’ safety observation process. The data for this paper were collected from an online survey (n = 21) and interviews (n = 40). The survey targeted safety experts and occupational safety managers in different Finnish organisations. The semi-structured interviews were conducted in five case organisations. In total, 64 people were interviewed. The focus was on questions related to the kinds of practices employed in the safety observation process. In this study, the practices were highlighted in, reporting system, handling of observation and communication about observation.

Johanna Pulkkinen, Noora Nenonen, Maria Lindholm

Conference Proceedings

Building an assurance case for assessing novel maritime border surveillance system

An assurance case is a documented body of evidence providing a convincing and valid argument that a system is adequately built for a given application in a given environment. It is a requirements-based approach, in which requirements provide a reference for the assessment of determined features of the target system. System adequacy is demonstrated by presenting evidence and by justifying why the evidence supports particular requirement-based claims. As follows, a systems assurance case is a conceptual procedure within which reasoning about system validity takes place. It is a hierarchical ordering of system-related data extending from an abstract understanding of system performance to a concrete proof of the validity system. In this paper, we discuss the development of an assurance case for a maritime border surveillance system which aims at enhancing the situational awareness of border authorities at external maritime borders of the European Union and third countries. This paper discusses the benefits of the assurance case in the context of applied civil security research, considering among others the suitability and comprehensiveness of the approach compared to other methods, such as checklists and compliance matrices. The strength of the approach in organizing information associated with complex systems is also addressed.

Laura Salmela, Jaana Keränen, Jari Laarni, Sirra Toivonen, Antti Väätänen

Conference Proceedings

The Effect of Rear-lighting system Design on Preventing Rear-end Collisions in a Simulated Distracted Driving

Rear-end collisions account for approximately 29% of all vehicular accidents. While various cues can inform drivers of a lead vehicle’s stopping behavior, brake lights remain the primary and most critical signal for indicating deceleration. The concept of redundant signaling—well-supported by both basic and applied research—suggests that additional visual cues can enhance driver response times. This study examined the effect of incorporating a redundant pictorial stop cue into rear brake light configurations on driver reaction times during a cognitively distracted, simulated car-following task. Forty-eight drivers participated, responding to three rear light configurations which depicted three different taillight-to-brake lights transitions—Traditional without additional pictorial stop cue, the 2023 Jeep Renegade model with an “X”-shaped motif, and a Redundant Pictorial Signal—while concurrently performing a math-based cognitive distraction task. Results showed that the redundant rear light configuration significantly reduced braking reaction times compared to the traditional setup and demonstrated potential for reorienting driver attention back to the driving task. These findings suggest that integrating redundant visual stop cues into rear light designs may help prevent rear-end collisions or reduce their severity and associated fatalities.

Dongyuan Wang, Pingying Zhang, Vamsi Sai Kalasapudi

Conference Proceedings

Monitoring the adoption of e-mail security standards in selected healthcare entities in Poland

Since 25 September 2023 configuration of DMARC protocol is mandatory for public entities in Poland. The article presents the status of implementation of the DMARC, SPF and DKIM security protocols in domains used by healthcare entities in Poland. Selected domains were analyzed using EasyDMARC online software. Out of 302 domains, the DMARC protocol was somehow configured in 232, including 181 in secure way, and was missing in 70. Other protocols are used with varying degrees of success. The SPF protocol is properly implemented in most examined domains, while vast majority of domains is missing the implementation of DKIM protocol.

Patryk Morawiec

Conference Proceedings

Transfer and Lifting Technologies in Long-Term Care Facilities: A Scoping Review of Assistive Solutions for Older Adults Care

The practice of caring in long-term care institutions for older adults often involves the lifting and transferring of residents, tasks that, when performed manually, expose professionals to biomechanical overload and musculoskeletal injury risks. To minimise these risks, the use of assistive devices has been recommended as an ergonomic strategy. Despite the relevance of such technologies, their adoption in long-term care facilities (LTCFs) faces significant challenges, including financial constraints, the need for continuous staff training, and the adaptation of existing infrastructure. Additionally, there is a limited number of studies exploring the use of these devices in institutional settings. In this context, the present scoping review aimed to map the scientific literature on the use of lifting and transfer devices used in LTCFs, considering aspects such as the geographical and temporal distribution of publications, methodological designs, technologies analysed, sample characteristics, and main findings reported. The search was conducted in the Scopus and PubMed databases using combinations of terms related to patient transfer, long-term care institutions, and assistive devices. Following the application of inclusion criteria (language, full-text availability, and focus on LTCFs), 16 articles published between 2004 and 2025 were selected, originating from different countries, notably the United States, Sweden, and Denmark. The studies employed various methodological approaches, including observational, cross-sectional, longitudinal, and quasi-experimental designs, contributing to a comprehensive understanding of the factors involved in the use of these technologies. The most frequently investigated devices were ceiling lifts, floor lifts, mobile lifts, sliding sheets, and transfer belts, often investigated in combination. Most articles focused on healthcare professionals, emphasising the prevention of musculoskeletal disorders, while only one study directly addressed the perspective of older adult users. Evaluation methods predominantly included questionnaires, field observations, and interviews. In terms of outcomes, key ergonomic benefits were highlighted, such as the reduction of physical symptoms and improvements in carers' posture, as well as increased perceptions of safety and comfort among older adult users in some contexts. However, significant limitations were also identified, including low adherence among staff, improper use of equipment, increased task execution time, and structural barriers such as lack of maintenance and institutional support. The current findings indicate that successful implementation of these technologies depends on the interplay of technical, organisational, and human factors. As a contribution, this review organises and systematises the available knowledge on the topic, highlighting ergonomics as a fundamental axis of occupational health in LTCFs and pointing to the need for integrated public policies and management strategies that encourage the safe and effective use of these technologies in the care of institutionalised older adults.

Mariana Anjos De Almeida, Milene De Almeida Ribeiro Checoni, Ana Beatriz Ferreira Cardim, Erica Pereira Das Neves, Carla Da Silva Santana Castro, Fausto Medola

Conference Proceedings

Data Synthetization and Feature Analysis: A Study in Bladder Cancer Recurrence Data

The application of synthetic data within the biomedical domain is rapidly gaining momentum, driven by the growing need for robust datasets suitable for machine learning (ML) and statistical modeling. In scenarios where access to real patient data is limited due to privacy concerns or scarcity, synthetic data offers an attractive alternative. These artificially generated datasets aim to mimic the statistical characteristics of original data, enabling researchers to conduct exploratory analysis, develop predictive models, or validate findings without compromising patient confidentiality. However, the increasing use of synthetic data raises several methodological and interpretative challenges, particularly regarding the correct sequence and context for applying statistical analyses. One of the central issues identified in contemporary literature concerns the timing of data analysis relative to the synthetic data generation process. Some studies conduct statistical or ML analyses directly on real datasets and use synthetic data for validation or augmentation. Others, conversely, perform all stages of analysis including feature importance estimation, correlation assessment, and model training on synthetic data. This inconsistency raises the question of whether statistical analysis conducted solely on synthetic datasets yields reliable insights, or whether it constitutes a methodological flaw. The prevailing assumption is that analysis should ideally be performed on real data to preserve statistical integrity, but empirical evaluation of this notion remains limited. In the current study, the authors address this issue by applying a synthetic data generation method specifically, the Tabular Variational Auto encoder (TVAE) to a biomedical dataset focused on bladder cancer recurrence. This dataset includes various diagnostic variables, and the primary goal is to assess how well synthetic data replicates analytical insights drawn from the original data. To achieve this, the authors conduct both correlational analysis and machine learning-based feature importance estimation. The results derived from synthetic datasets of varying sizes are then compared to those obtained from the original data. The findings indicate that while synthetic data can approximate general trends observed in the original dataset, there are notable differences depending on the analytical technique employed. In particular, models such as Random Forest appear more sensitive to variations introduced during the synthetization process. This sensitivity manifests as shifts in feature importance rankings and variability in predictive performance, especially when working with smaller synthetic datasets. On the other hand, simpler statistical methods such as correlation coefficients display more stability, suggesting that some analytical approaches may be more robust to data generation artifacts than others. These observations underscore the importance of methodological caution when interpreting results based on synthetic biomedical data. While synthetic datasets hold considerable promise for advancing data-driven research in biomedicine, they are not a one-size-fits-all solution. The sequence in which synthetic data is introduced into the research pipeline whether before or after statistical analysis—can significantly influence the validity of the findings. As such, researchers must critically assess the suitability of synthetic data for specific analytical tasks and ensure transparency in reporting their methodological choices. Future work should further explore the impact of different generative models and dataset properties on the reliability of synthetic-data-driven insights.

Sandi Baressi Šegota, Ivan Lorencin, Nikola Anđelić, Vedran Mrzljak, Antun Gršković, Juraj Ahel, Klara Smolić, Dean Markić

Conference Proceedings

Toward Intelligent Homecare for Older Adults: Deep Learning-Based Activity and Routine Deviation Detection Using SDHAR-HOME Data

The global growth of the older adult’s population highlights the urgent need for intelligent privacy-preserving homecare systems that can monitor daily activities and detect behavioral deviations. We propose a comprehensive framework that combines a Transformer-based deep learning model for human activity recognition with a rule-based, interpretable routine deviation detection system. Leveraging the SDHAR-HOME dataset, which contains multi-sensor time series data from two users, the framework first classifies daily activities using a transformer encoder and then constructs a personalized behavioral baseline to identify deviations such as missed meals, sleep disturbances, and unusual hygiene habits. Results demonstrate high classification accuracy (up to 98.5%) and validate the effectiveness of conventional monitoring methods through detailed visualization and semantic deviation labeling. This dual-strategy framework is particularly suitable for assistive monitoring applications in homecare settings.

Raja Omman Zafar, Yves Rybarczyk

Conference Proceedings

Technology and environmental design for the safety of people with autism

People with autism need a safe environment, free from potential risks and that facilitates movement so that they can continue to perform their tasks and maximize their abilities (FLEMING; ZEISEL; BENNETT, 2020). This study aimed to explore the safety measures implemented by family members of people with autism in the home environment. An exploratory, descriptive, and qualitative study, approved by the Research Ethics Committee of the Hospital das Clínicas of the Ribeirão Preto Medical School of the University of São Paulo, in which 26 caregivers of people with autism participated. Data were collected through in-depth interviews. The study questions were based on environmental adaptations for well-being and safety measures adopted. The main thematic categories identified were: Modifications in environmental design and Technology resources. The category "Modifications in environmental design" generated the subcategories "Access Control Strategies" and "Modification of structure and rearrangement of furniture." Access control modifications included the installation of gates and keyed doors to isolate rooms and control access to medicines, plants, and animal feed. Regarding structural strategies, accessibility features were adopted, such as leveling the floor and removing steps, installing ramps, handrails, corner guards, and grab bars, removing shower stalls, widening doorways and passageways, installing non-slip flooring, and installing safety screens and nets, among others. Furniture and rugs were removed to increase free space and reduce environmental risks. Technology features included the installation of surveillance cameras, assistive devices such as shower chairs, bed safety rails, motion sensors, furniture corner guards, and floor signage, as well as increased supervision and surveillance. The main changes are based on the fact that 20 of these subjects were children living with autism and had no perception of the potential risk of the environment. Safety is the most frequently adopted measure for environments in which neurotypical individuals live, taking into account their cognitive, sensory, experiential, and sociodemographic specificities (Lee, 2022). Conclusion: Knowledge about the specific needs of a group of individuals should inform design and technology choices that can contribute to a full life in a safe and functional environment.

Emilin Odilia Rossi De Carvalho Goulart, Fausto Medola, Rita Cristina Sadako Kuroishi, Karla Beatriz Agostinho, Carla Da Silva Santana Castro

Conference Proceedings

Students' perceptions about the aging effects of using simulators

The use of simulation technologies in teaching and learning contributes to the preparation of healthcare professionals, by supporting the experience of changing places, providing better future professional practice. Objective: To understand university students' perceptions of the use of the "Advanced Simulator of the Effects of Aging," which seeks to simulate musculoskeletal, auditory, visual, and tactile changes in previously programmed activities of daily living. Method: This is an exploratory, observational, qualitative and quantitative study. Data were analyzed using content analysis. Results: Eighteen university students from a public university in the state of São Paulo, Brazil, participated in the study. The average age of the participants was 25.6 years, 17 female and 2 male. The data generated the thematic categories: "Limitations of the Simulator" and "Effects of Simulator Use." Regarding the limitations of the simulator, the size of the equipment's components made it difficult to fit bodies with different biotypes, influencing movement control and task completion. Stands out that overloading wrist and/or ankle weights seemed to worsen task performance, especially after a few minutes of use, which could compromise the performance evaluation if considering the beginning and end of the activity. Discomfort in performing tasks with equipment attached to the body was reported, which in itself would affect performance. Regarding the effects of the simulator, limitations on vision and mobility were the most frequently described. The change in the visual field influenced balance and other components of neuromuscular performance, task planning, and perception of safety. Cognitively, participants reported that they needed to recruit more attention, causing greater fatigue, slowness and consequently, limited overall performance. Discussion: From the perspective of the technology development process, simulation practice represents an opportunity to raise the project team's awareness of users' potential difficulties, thus contributing to the development of solutions that better meet their needs. Empathy strategies implemented in the design process can benefit students' creative process and promote the development of better-performing solutions (YESILTEPE; DEMIRKAN, 2025). Conclusion: The experience of raising awareness about the difficulties arising from the aging process brought students closer to the functional changes experienced by older adults, sometimes highlighting negative aspects of functional losses and describing the experience as frustrating, and sometimes fostering empathy with older adults when they identified the important changes of aging. Awareness-raising initiatives can benefit the training of students in the healthcare field and those working on projects and technology development focused on older adults. They highlight the need for a simulator that has items of varying sizes to be used with different biotypes and that the visual changes proposed by the simulator are more realistic compared to those experienced by older adults. The results point to the need to adapt the use of this aging simulation system to teaching purposes, associated with participant feedback to minimize anxiety and the development of ageist attitudes towards aging.

Karla Beatriz Agostinho, Leonardo Martins Kebbe, Emilin Odilia Rossi De Carvalho Goulart, Rita Cristina Sadako Kuroishi, Vitoria Camilli Pereira Ramos, Maria Eduarda Harumi Eizo, Livia Karla Roque, Geovana Cristine Agostinho, Fausto Medola, Carla Da Silva Santana Castro

Conference Proceedings

Daily Stress Detection Using Artificial Neural Network Based on Acoustic and Semantic Information from Speech

Cumulative daily stress is harmful to the health of people and leads to productivity loss. Hence, timely detection of daily stress is of vital importance. Natural speech from real life is the recommended information to detect stress as a non-invasive way. This study aims to improve stress detection accuracy by combing the acoustic and semantic information from speech. Based on the speech database with real daily stress, we fused the acoustic and semantic features and developed a daily stress detection model using artificial neural network. The results showed that the model accuracy using acoustic information is 65.50% with a F1-score of 60.21%. The model accuracy using semantic information is 80.00% with a F1-score of 76.65%. By combining the acoustic information and semantic information, the model accuracy was improved to 90.75% with a F1-score of 89.25%. These results indicated the complementary effect of acoustic and semantic information on the daily stress detection. This study validated the effectiveness of detecting daily stress based on the combination of acoustic and semantic information from real speech. The model developed in this study can be applied to daily stress monitoring in daily life, offering valuable insights for stress management intervention to mitigate adverse health impacts.

Peixian Lu, Xingwei Jiang, Shiguang Deng

Conference Proceedings

Quantum Cats: Generative AI 3D-enabled Interactive Experience in Mixed Reality

Humans love cats, at least half of humans. Quantum cats are even nicer to our minds. Thus, Generative AI (Gen AI) created and animated 3D cats of Schrödinger in mixed reality, which are close to infinite fun. In this project, we bring Schrödinger’s famous thought experiment to life by combining the power of Gen AI, Quantum Computing concepts, and Mixed Reality (MR). The result is an Interactive 3D experience that enables users to observe, influence, and explore the behaviors of AI-generated quantum cats within an immersive environment, promoting education, entertainment, and engagement.The goal is both playful and provocative: to offer a hands-on metaphor for quantum uncertainty and superposition through intuitive interactions. The project also highlights how generative AI accelerates 3D content creation, enabling rapid iteration and rich visual storytelling. By integrating these technologies, we aim to demonstrate a new kind of experiential interface – one that is scientific, artistic, and, unsurprisingly, fun.The demo includes a Gen AI-powered parts with 3D and Animation, Interactivity, Quantum and Spatial computing components. More details are presented below; the system architecture and implementation details will also be included in the final paper. Recent developments in Generative AI promise to accelerate the production speed of nearly everything, including interactive 3D experiences. Practically, Text-to-3D, Image-to-3D, and Multiview Image-to-3D provide production-ready results at least in terms of an edge Mixed Reality device. Furthermore, one can achieve not only the models but also the characters, rig them, and animate them. With the acceptable results in generation and animation, characters can be created faster than achievable by human artists, initially, and then even quicker, with better quality.We conducted a state-of-the-art literature review for 3D character generation. We performed experiments with the most promising tools and models, including Meshy 4 and 5 preview, Luma Genie, Tripo 2.5, Trellis, and Hunyuan 2.0. The generation results were visually acceptable with all the selected 3D models and tools. We identified two models that returned visually acceptable results compatible with the rig and animation pipelines. The models from Meshy and Tripo appeared to be compatible with Mixamo and Animate Anything, respectively. Our Interactive MR-enhanced demo offers a fresh perspective on the foundations of quantum computing, making them easy to grasp and even “touch”. The core idea derives from the iconic Schrödinger’s cat thought experiment with a twist. While the original setup focuses on the principle of superposition and involves a single cat to illustrate the behavior of a quantum system, which can exist in a superposition of multiple states simultaneously, we introduce additional cats to illustrate the concept of quantum entanglement. This phenomenon manifests itself in peculiar long-range correlations that cannot be accounted for classically and results in states of composite quantum systems, which cannot be factored into individual states of the constituting subsystems. The key premise of the experiment remains - the cats are placed into the box with poison vials triggered via a spontaneous mechanism of radioactive decay, introducing a true uncertainty element. As long as the box is closed to the observer, the cats can be viewed as both alive and dead at the same time. Within our virtual environment, additional separating walls can be shifted inside the box, allowing us to “entangle” the cats. Namely, if the cats are located in the same box compartment impacted by the same poison vial, upon inspection, they will both be found either alive or dead. The inspection itself is performed by opening the box and illustrates the measurement in quantum mechanics, which results in the collapse of the superposition to a single definitive state. In the light of quantum computing, cats in the proposed demo represent a system of qubits, while user interaction with cats’ results in unitary transformations applied to the state of this system. This is visualized using a dedicated widget containing a quantum circuit for state preparation. Therein, superposition is generated utilizing Hadamard gates, and the entanglement is introduced through the action of two-qubit CNOT gates. The state evaluation procedure is performed in a simulated manner. To implement the human-computer interaction system, we utilized the Magic Leap Unreal Engine SDK. During the development phase, we experimented with various input methods — both controller-based and hand-tracking — and ultimately chose hand-tracking for its ability to deliver a more intuitive, natural, and immersive user experience.We briefly presented our research and experimental work in Gen AI 3D and the HCI domain, incorporating the flavor of quantum physics.

Sam Frish, Vadym Chernyshov, Ihor Romanovych, Nataliia Susulovska

Conference Proceedings

TAC-Twin: A Rapid Framework for Personalized Doppelgänger Avatar Creation Using a Modular Virtual Human Pipeline

We present an end-to-end framework for rapidly creating interactive, personalized avatars for scalable training and simulation applications. Built as an extension of the Virtual Human Toolkit, the framework integrates technologies for audio-visual sensing, speech recognition, natural language processing, nonverbal behavior generation, and high-fidelity text-to-speech synthesis. A personalized avatar is defined here as a real-time, embodied digital representation of an actual individual rather than a generic character. The creation pipeline requires only a single facial photograph, processed through a photorealistic character generation workflow, then refined, customized, and deployed in a real-time 3D environment for integration with conversational AI and synthetic voice generation. The system also supports rapid generation of generic avatars from high-quality synthetic headshots produced by generative AI, enabling the creation of diverse, realistic or stylized cohorts within minutes. Our initial use case examines whether personalized avatars enhance engagement, motivation, and performance compared to generic avatars, with the hypothesis that personalization increases relevance, identification, and learning outcomes. We describe the architecture, avatar creation pipeline, and role of generative AI in accelerating development, and share early implementation insights.

Arno Hartholt, Ed Fast, Kevin Kim, Edwin Sookiassian, Andrew Leeds

Conference Proceedings

Automated Procedural Error Detection in Human-Robot Collaborative Assembly Using Vision-Based Template Matching

In collaborative human-robot assembly, robust error identification is paramount for ensuring process integrity and safety, particularly in the post task phase where a comprehensive analysis provides an opportunity to identify subtle and cumulative errors that may have been missed in real-time. Traditional manual verification is often tedious and prone to human error, including oversight and fatigue, which can compromise quality. This paper evaluates the efficacy of an automated, vision-based error detection system using OpenCV template matching as a more reliable alternative. Our method identifies procedural errors, such as missed components or out-of-sequence operations, by comparing real-time images of the assembly state against a library of reference templates that depict correctly completed procedural steps. Visual dissimilarity metrics are used to automatically flag deviations from the expected sequence. Experimental results demonstrate that the automated system significantly outperforms manual verification in the consistent and rapid identification of both missing and mis-sequenced assembly steps. Whilst its performance can be influenced by challenges such as variable lighting and low-contrast features, the vision-based approach proved substantially more dependable than human inspection especially for structured and defined tasks where the objects consistent and predicted visual features. We conclude that template matching provides a robust and scalable solution for quality control in collaborative assembly tasks. This automated approach enhances operational efficiency and safety, though further tuning may be required to optimise performance in visually complex environments.

Isaiah Nassiuma, Ella-mae Hubbard, Mey Goh

Conference Proceedings

The Adoption of Artificial Intelligence Tools in Education: A Case Study of Primary and Secondary School Teachers in Pula, Croatia

The integration of Artificial Intelligence (AI) into education offers numerous opportunities to enhance teaching effectiveness, personalize learning, and increase student engagement. Simultaneously, it raises many questions regarding teachers' digital competencies, ethical challenges, institutional readiness, and the general acceptance of AI-based tools. This paper presents the results of a case study conducted among primary and secondary school teachers in the city of Pula, Croatia, with the aim of examining their attitudes, readiness, and perceived challenges concerning the use of AI in teaching practice. \nData were collected through a structured questionnaire that covered digital habits, self-assessed skills, prior experience with AI tools, and the perception of usefulness and potential risks. The research results show that most respondents recognize AI's potential to improve teaching quality, support individualized approaches, and foster student creativity. However, concerns were expressed regarding the accuracy of AI-generated content, the potential reduction in student social interaction, and unresolved ethical issues. The lack of education and clear institutional guidelines was highlighted as a significant barrier to successful implementation.\nThe study contributes to a deeper understanding of teachers' perceptions of AI's role in education and points to the need for a strategic approach to introducing these technologies into the school system.

Luka Brodarič, Snježana Babić

Conference Proceedings