Intelligent Human Systems Integration (IHSI 2025): Integrating People and Intelligent Systems

AHFE International

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

Intelligent Human Systems Integration (IHSI 2025): Integrating People and Intelligent Systems

book-cover

Editors: Tareq Ahram, Waldemar Karwowski, Carlo Martino, Giuseppe Di Bucchianico, Vincenzo Maselli

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2025

ISBN: 978-1-964867-36-6

DOI: 10.54941/ahfe1005804

Articles

Concept and development of a user interface for human-robot collaboration during a safety briefing

Collaboration between humans and robots - also known as human-robot collaboration (HRC) - is revolutionizing the way we work and produce and will become increasingly important in the future. The basic idea of HRC is to combine the strengths of humans and robots. Regarding this future field, a considerable amount of attention is being paid to collaborative robots, so called cobots. These robots are intended for direct human-robot interaction within a shared space respectively defined collaboration space (e.g., EN ISO 10218-2). Direct collaboration can be controlled in different ways, for example via user interfaces. Today, graphical user interfaces are often chosen for this. In the presented paper, the question should be highlighted whether there are also situations in which a cobot itself operates a user interface. This seems to make particular sense if the cobot can offer added social value, for example in the areas of service, care or education. In elderly care, for example, a cobot can increase people's independence and accessibility by helping them to operate a cell phone or a tablet to stay in contact with their beloved or receive telemedical support. Using a cobot within this interaction, the cobot could show the person how to achieve their goal or choose the correct steps, instead of controlling the application directly via programming commands which can be challenging for the user. Hence, in this case the cobot acts as a tutor or friend together with the user. However, there is currently a gap in literature regarding this topic. For this reason, a user interface that is operated directly by a cobot was designed and investigated. The user interface is a newly developed short serious game called “SafetyBot”, which conveys safety instructions in a playful way. The idea was, that a social robot, which is positioned opposite the user, operates the game together with the user. During the developmental processes we faced various challenges regarding choosing the right robot and how to interact together on one user interface. These challenges and the resulting solutions, which then served as the basis for the evaluation in an experiment with users shall be described in more detail in this paper. The insights gained within this process provide a basis for future research on this topic and help with the integration of cobots into everyday life.

Janine Tasia Stang, Verena Wagner-Hartl

Conference Proceedings

User-centered design of professional social service robots

Professional services are services provided by businesses. These commercial services strongly differ in their complexity, volume and human interaction. Depending on the service task, robots within service operation have the potential to increase service quality and reduce costs. Additionally, they are indispensable in ageing industrial nations with an increasing shortage of skilled workers. One form of service robots are professional social service robots. They provide employees and customers with interactive situation-specific services like a robot guide or a restaurant service robot. A social service robot not only has technological features needed for services, but also has to have the ability to interact with people. Due to their level of human-robot interaction and needed adaptability, their design is a challenging task, but indispensable for their acceptance by customers and employees. Methodology: As a social service robot a predefined use case of a cloakroom robot was chosen for which a prototypic implementation and its validation through usability testing was conducted. A literature review was the starting point for a concept definition of the robot. Results: The results indicate that users require an intuitive user interface with feedback for each step. Process speed also turned out to be a crucial design requirement, as a slow process speed led to waiting time and user dissatisfaction. It has been shown that the robot itself served as a unique attraction - users preferred the service robot over the common solution of a cloakroom attendant. This work contributes to the understanding of the design requirements of a collaborative service robot, emphasizing the importance of HMI, logical process sequence and process speed to ensure a positive user experience. The findings emphasise the need for user-friendly design of professional social service robots and underline their capability within service operation.

Katja Gutsche, Julian Genovese, Paul Serstjuk, Selin Altindis

Conference Proceedings

Human Systems Integration and Design in Port Terminal Concessions: A Bibliometric Study of End – of – Life Management and Decommissioning Guidelines

This paper addresses the complexities in managing port terminal concessions, focusing on the final asset compensation sub – phase during the pre – biding phase, a critical yet under – researched area in maritime academic literature. The employment of bibliometric analysis revealed four key clusters: (1) Sustainable Concession Strategies in Port Management; (2) Evolving Governance Models in Port Concessions; (3) Sensor – Driven End – of – Life Management in Supply Chains; and (4) End – of – Life Recovery Strategies in Manufacturing Systems. Sixteen decommissioning guidelines are developed: (1) The first eight focus on organizational structures and human factors to establish a structured approach; and (2) The second eight centre on technical integration for enhancing end – of – life management. These guidelines align with Human Systems Integration and Design (HSID) principles to clarify decommissioning and asset recovery processes. The paper highlights the need for early planning and consistent compensation approaches in terminal concession agreements and emphasizes future research to explore the application of HSID in different regional and economic contexts.

Alen Jugovic, Tanja Poletan, Goran Kolaric, Miljen Sirotic

Conference Proceedings

State-of-the-art in human-centric studies of AI-enhanced situational awareness within the security domain

Advanced situational awareness and decision-making systems in the security domain heavily build upon versatile combinations of different artificial intelligence models, potentially including their earlier versions. Often, the broad variety of implemented algorithms results in complex system architectures which may challenge human comprehension of expert users. System performance is frequently evaluated by different technical metrics against various data sets, such as model accuracy, precision, and recall. However, without any consideration of human-autonomy teaming or human-system interaction, the possibilities of executing comprehensive system assessments are likely to remain limited. This systematic review examines the current state-of-the-art in human-centric studies on situational awareness systems applying machine learning or artificial intelligence as key technologies. Our findings are based on up to 40 studies that were identified in our literature searches. This paper outlines the transition in research on the domain and current trends. It also discusses the research gap on human-centric approach.

Laura Salmela, Jussi Okkonen, Roosa Heikkiniemi

Conference Proceedings

Humans and AI writing lectures together

With the recent advancements in Generative Artificial Intelligence (GenAI) technologies, particularly Large Language Models (LLMs) like GPT4, there has been a significant shift in how information can be easily accessed, generated, and utilized. This study uses these advancements to create a tool where humans and AI generate complete lectures, encompassing the entire process from structure outlining and scriptwriting to slide creation and delivery via a digital avatar.The motivation behind this study comes from the challenges faced in the educational sector, including the time-consuming nature of lecture preparation and the potentially static nature of reused lectures. By integrating LLMs and other GenAI technologies such as image, video, and speech synthesis, the proposed solution aims to provide a dynamic and adaptable workflow that may speed up the lecture creation process and keep content up-to-date. We are interested in whether such a hybrid system of human experts and AI technologies can be helpful.To answer our research question, we developed a tool that combines multiple AI technologies into one easy-to-use interface. It allows educators to generate a lecture within minutes by simply entering a topic. As LLM’s are not yet fully trustworthy. Thus, we deemed it important that the system allows the user (educator) to step in at any point and make manual changes if needed.The tool creates a lecture in four steps:1. Outline: The process begins with generating a lecture outline, where users enter the lecture topic and specify the students’ proficiency level (beginner, intermediate, advanced). This chosen proficiency level is passed to the LLM, which helps to create a lecture tuned to the student’s level. Additionally, users can offer more context by indicating the students’ Existing knowledge and pinpointing specific areas they should learn more about. The user can edit the outline by changing the titles or adding and removing sections or chapters.2. Script: Based on the outline, a script for the lecture is generated. The script generation process went through several different iterations. Initially, the whole script was generated using a single-generation process. This worked to a certain extent; however, it is only a viable approach when creating a concise lecture.3. Slides: Based on the script, complementary slides are created. Each slide contains bullet points and an image. The slides are generated through a collaborative process involving a language model, an image generation model, and Google Images. First, the language model dissects the script into smaller chunks. The model has complete control over how to split up the text. We decided to give it complete control because this is a task that language models should excel at, and we want to evaluate its performance in finding the right balance between the number of slides and detail per slide.4. Avatar: A digital avatar is created by selecting a face and voice. This avatar will present the lecture. There is the option to use any custom image the user can upload.To evaluate the usability and effectiveness of the tool, a user study was conducted with 12 experienced educators from various fields and educational levels. The study revealed that the prototype achieved a mean System Usability Scale (SUS) score of 80,42, indicating a good level of usability. It was found that the tool increased workflow efficiency, with most participants agreeing that it made lecture creation faster and more streamlined. Most participants said they would integrate this tool into their workflow, but only a few believed it would improve the quality of their lectures.Overall, this research demonstrates the practical applications of GenAI technologies in an educational context. While the prototype shows promise in increasing educators’ productivity and streamlining the lecture creation process, it also highlights the need for expert oversight to make sure the content is accurate and qualitative. Our study found that most participants would integrate AI-generated lectures into their workflow, albeit to serve as a starting point or inspiration. This indicates that GenAI cannot educate people properly, but the thesis clarifies GenAI’s current capabilities in an educational context. Further advancements in large language models will make them more reliable and helpful in creating lecture content. For now, an expert educator is still needed to craft a quality syllabus and teach the content. Future work may focus on addressing the identified limitations and further refining the tool to better meet educators' needs.

Andreas Stöckl, Tim Willaert, Rimbert Rudisch-sommer

Conference Proceedings

Digital Networking for Economic Growth: Interactions Between Natural and Artificial Intelligence

This paper investigates how human knowledge, i.e. (Natural Intelligence: NI), mixes with "Artificial Intelligence" (AI), which relies on operating operational data-driven computation methods traditional firms' infrastructures ranch as humanly-based applications formalizing tools. An integrated multilayer network framework is proposed for the efficient and effective creation of economic value. The essential question is: How can copula-driven co-integration through multilayer networks enable NI-AI integration to generate economic value at digitalized firms? This study empirically tests all the cost-benefit improvements likely to be derived from AI technologies across a wide range of industries, from manufacturing and retail to finance. The results provide evidence that huge efficiency improvements, such as optimizing operational protocols and practices to be more effective in decision-making, tend to occur alongside significant reductions in total costs. Copula nodes amplify interactions between NI and AI to achieve a cohesive joint effect capable of delivering maximum economic benefits for participating firms. These findings provide a unique strategy for firms to increase profitability and compete in the digital age.

Roberto Moro-visconti

Conference Proceedings

Dynamic Alarm Information Presentation Strategy under the Influence of Dynamic Elements in Smart Factory.

This study aims to propose a dynamic design strategy to assist operators in swiftly identifying alarm-indicating controls within dynamic background environments. Through comparative data analysis of alarm signals in behavioral experiments, the research identifies the most suitable combination of alarm information for the current smart factory interface, thereby laying the groundwork for improving alarm presentation methods on monitoring interfaces. With the advent of the Industry 4.0 era, the digitalization process is driving contemporary industrial manufacturing towards unmanned and intelligent development. smart factory is an advanced factory that integrates factory automation with complex information technology. hmi acts as a connection between the user and the controlled process by providing important information, alarms, and other features.The application of visual alarm formats in visual display interfaces exhibits diverse characteristics, offering advantages such as rapid capture of user attention, intuitive discernibility, and the proactive provision of situational urgency. However, operators typically engage in sustained attention towards system interfaces, necessitating prolonged focus to identify specific target signals. This process imposes high demands on the operator's perceptual attention levels, and extended periods of attention may lead to visual fatigue and increased cognitive load.In many smart factory human-machine interfaces (HMIs), the incorporation of dynamic elements can partially capture operators' attention, such as dynamic arrows or color blocks indicating the status of flowing pipelines. While these dynamic elements can significantly reduce users' search time for pipeline directions and signal the normal operation of the pipelines, an excess of dynamic information may lead to a decrease in users' visual search efficiency. When an alarm is triggered by a control on a line, it typically indicates an abnormality in the flow rate or valve of the pipeline. Some scholars argue that static alarms are difficult for operators to detect within dynamic backgrounds, which may compromise system safety. Crisp (1988) noted that when multiple moving items are present on a display, the search tends to be limited to the moving set, while static items are often overlooked.{Citation} Conversely, other researchers assert that static objects are generally more conspicuous in dynamic environments. McLeod et al. (1988) demonstrated that operators can identify a stationary target among moving items, and this ability is independent of the number of moving distractors, although the search efficiency remains slightly lower compared to identifying moving targets among stationary distractors. According to the previous theory, the experiment was designed with three independent variables, the background screen color (dark background R17, G31, B54 and light background R242, G242, B242), the dynamic/static alarm signals (differentiated by whether or not they are blinking, and the blinking frequency of 2Hz), and the transparency (10%, 30%, and 50%); as well as two dependent variables: the accuracy rate and the response time.The experimental interface simulates the screen when an alarm signal appears in the monitoring interface of a smart factory, as shown in Fig. 1.The experimental phase consisted of 10 × (2 × 2 × 3 + 5) × 2 groups of trials (10 subjects × (2 background screen colors × 2 blinking signals × 3 transparency levels + 5 no-alarm controls) × two repetitions), for a total of 340 TRAIL trials. The experimental interface was simulated using E-prime 2.0 and the material was edited in AE software.Each trial subjects need to watch a video of the analog monitoring interface, once the alarm signal appears, subjects need to press the “K” key; if no alarm signal appears, choose to press the “D” key. The correct rate and reaction time of the subjects on different visual alarm forms are recorded, and the average correct rate and average reaction time of each group can be statistically obtained after the data output. Conclusions(1) The effect of the transparency of the warning signs on task correctness is significant.(2) The presence of dynamic blinking effect does not have a significant effect on task correctness.(3) Light-colored backgrounds are more likely to be recognized as warning signals relative to dark-colored backgrounds.(4) There was no interaction between the three variables of transparency, flashing frequency, and background color.Application：By analyzing the experimental data, a design strategy suitable for the dynamic interaction background of this smart factory is derived. The research results can be applied to the study of dynamic alarm message presentation in human-machine interfaces containing dynamic elements as background.

Pengli Zhu, Linlin Wang, ChengQi Xue

Conference Proceedings

Development of Techniques for Measuring Lower Limb Flexibility in the Elderly

Flexibility as one of the influencing factors of physical fitness, is an essential component of overall health and can be regulated through muscle control and joint range of motion.However, the range of motion of many joints tends to decrease with age.The research suggests that, irrespective of gender, shoulder flexibility decreases by approximately 10% per decade from the age of 65. While some individuals maintain their flexibility as they age, their joint function range remains significantly less than that of younger individuals. The decline in joint flexibility directly contributes to reduced physical and functional capabilities, potentially impacting the independence and quality of life for older adults. Therefore, maintaining flexibility is crucial for the elderly population.However, the presence of the body's compensatory mechanism often complicates the detection of a decline in flexibility, leading to limitations in regular individual measurements. Mainstream methods for assessing flexibility primarily involve conventional physical fitness testing techniques and relevant range-of-motion evaluation tools. Common techniques for measuring flexibility mainly encompass the use of contact and non-contact measurement tools such as rulers, goniometers, inclinometers, etc., which quantify range of motion numerically. These methods are well-established in terms of technical principles and offer relatively low costs. Non-contact measurement includes two-dimensional image-based body measurement technology, three-dimensional body measurement technology, and 4D scanning technology. Two-dimensional body measurement relies solely on subject image information but has drawbacks such as difficulty verifying measurement errors. Three-dimensional human body measurement technology is widely used in fields like fashion industry, industrial design, medicine, and gaming due to its relatively accurate data; however high venue requirements and equipment costs hinder its widespread application in daily scenarios.Therefore, this study takes the flexibility of the lower limbs of the elderly as an example, and will develop a new flexibility measurement technique through the construction of a flexibility measurement unit, the determination of the measurement base, and the establishment of the measurement method.To develop a flexible measurement technique, this study centers around four processes: concept definition, method creation, technology selection, and tool design. In terms of conceptual definition, it is proposed to use the ratio method to establish a mathematical formula for flexibility measurement by taking into account the internal factors affecting flexibility in the elderly, and to improve the concept of flexibility measurement, redefine the time and frequency of measurement, and redefine a scientific unit of flexibility measurement. In terms of method creation, it is hoped that the location of key skeletal points in the human body can be deduced from the characteristics of the human body surface, to build a personalized human skeletal structure and accurately measure external joint activity. In terms of technology selection, we comprehensively compare the application of non-contact measurement technology and contact measurement technology, explore the new direction of traditional technology development, and look for breakthroughs in the application of technological innovation; in terms of tool design, we utilize the mirror theory to turn complaints into wishes, explore creative solutions, and design a new type of measurement tool to be used with the mobile phone application of data logging and data display, to measure human body's flexibility in all dimensions, Through the design of new measurement tools, together with data recording and data display mobile applications, we can measure human flexibility in all directions and multiple dimensions, build a visualization platform for flexibility data, accumulate and count the flexibility data in the long term, and help improve the construction of the flexibility database.This study will fill the gap of human factors engineering in the methodological dimension of flexibility measurement, and develop a new lower limb flexibility measurement technology for the elderly, which will not only provide data support for the development of the elderly health industry, but also open up business opportunities for the industry, and innovate the technology system and commercial service model.

Bingbing Feng, Yulin Zhao

Conference Proceedings

Real-Time Cognitive Tools for Space Systems

This paper presents an innovative integration of real-time cognitive monitoring technologies with cognitive flexibility and awareness tools, framed within the Skill, Rule, and Knowledge (SRK) model, to enhance human performance and resilience in extreme environments. Conducted at NASA's Lunar/Martian habitat simulator at the University of North Dakota (UND), the study investigates how these advanced technologies improve cognitive readiness, decision-making, and overall mental fitness during long-duration spaceflights (LDSF).The SRK model, developed by Jens Rasmussen, categorizes human cognitive behavior into three levels—skill-based, rule-based, and knowledge-based actions—providing a structured approach to understanding and enhancing cognitive flexibility in high-stakes environments. By leveraging EEG-based monitoring and Brain-Computer Interface (BCI) technologies, this research enables dynamic, real-time assessments and interventions that are critical for maintaining cognitive control and adaptability during space missions.Traditional cognitive training and monitoring methods, which rely on periodic assessments and static protocols, fall short in providing the continuous feedback required for high-pressure scenarios. In contrast, the integrated system described in this study offers ongoing, adaptive training aligned with the SRK model, allowing for more precise and effective cognitive interventions. This approach facilitates seamless transitions between different levels of cognitive control, optimizing decision-making and preventing cognitive overload.The findings from this research have significant implications beyond space missions. The application of these cognitive tools within the SRK framework demonstrates potential for enhancing performance in other high-stakes domains, including aerospace, healthcare, and military operations, where cognitive readiness is paramount.In summary, this paper introduces a novel framework that integrates cognitive monitoring and flexibility tools within the SRK model to sustain cognitive readiness and performance in extreme environments. The results suggest that this approach not only enhances individual cognitive capabilities but also improves overall mission outcomes by reducing cognitive overload and optimizing decision-making processes, making it a valuable contribution to the field of intelligent human-system integration.

Curtis Cripe

Conference Proceedings

Analysis of experimental consensus-building tasks with evaluation indices

We routinely engage in consensus-building activities on issues ranging from the trivial, such as deciding where to go on a group trip, to the socially significant, such as the issue of final disposal sites for radioactive waste. In order to build consensus, it is necessary to reach one unanimous conclusion [1].In such communication, it is known that “Kansei” plays an important role in improving human relations [2]. Therefore, it is believed that analyzing consensus building from the perspective of Kansei can provide suggestions for achieving more amicable consensus building.Therefore, in order to analyze the relationship between sensitivity and consensus building in the previous study, we designed a consensus building task to be used in an experiment to record the favorability for each utterance.In this consensus-building task, two experimental participants (A and B) decide by consensus “whether A will wait a certain amount of time without doing anything after the task ends.” B is initially provided with six foods, such as chocolate, etc. For A, waiting represents a penalty that A accepts.B uses these foods as bargaining chips. At this time, if both parties agree that A will not wait, both cannot get the foods; if A waits, both can get them as per the consensus distribution. However, the results of the consensus building were evaluated using the objective consensus results of waiting or not waiting and prize distribution only, and no significant relationship could be shown between the consensus building results and Kansei.It is said that gaining mutual trust is important in risk communication, which is a type of consensus building [3]. Therefore, we believe that it is possible to evaluate the results of consensus building from the perspective of trust in this consensus building, which discusses the acceptance of penalties.It is also said that there is a relationship between trust and the degree of agreement on the outcome. [3]Therefore, in order to analyze the relationship between Kansei and consensus building results, this study get the foods the level of mutual trust and the level of agreement with the results as subjective evaluation indices of consensus building results, and analyzes the relationship between them and Kansei.In other words, in order to investigate the degree of agreement and trust in consensus building, both parties are asked to answer the questions about their level of trust and their level of agreement with the results of consensus building after the task is completed.The experiment was conducted with 5 groups of 10 undergraduate and graduate students, and it was suggested that the sum of the trust level of both parties and the liking level have a relationship. We are currently running an experiment of the same content, and in the Final Manuscript, we would like to describe the results of this experiment in detail and specifically show its impact on the degree of trust and the degree of delivery in the consensus building process. Specifically, we would like to analyze the results of the consensus building process by focusing on the relationship between the ratio of the decrease in favorability of the proposing side and the level of agreement and trust.[1] Susskind, L., McKearnan, S., & Thomas-Larmer, J. (Eds.). (1999). The consensus building handbook: A comprehensive guide to reaching agreement, SAGE Publications, Inc.[2] Tei, S., Kawaguchi, T., Sim, T., Shizuka, H.(2020). Understanding and Supporting Users to Improve Atmosphere of Communication by Kansei Agents, Proceedings of International Symposium on Affective Science and Engineering 2020.[3] CLundgren, R. E., & McMakin, A. H. (2018). Risk communication: A handbook for communicating environmental, safety, and health risks (6th ed.). Wiley-IEEE Press.

Shion Matsuoka, Kimi Ueda, Hirotake Ishii, Hiroshi Shimoda

Conference Proceedings

An Action Recognition Method based on 3D Feature Fusion

Video, which is distinct from a simple image, encompasses both spatial and temporal dimensions. In the spatial dimension, it contains various visual elements similar to those in static images. However, the addition of the temporal dimension makes it far more complex. It includes static image features such as color, texture, shape, and edge information that are crucial for identifying objects within each frame. Moreover, motion features play a significant role as they describe the movement of objects over time, including velocity, acceleration, and direction of movement. Additionally, external features like lighting conditions, background clutter, and occlusions also affect the overall nature of the video.As an important branch within the broad field of video understanding, human action recognition has attracted widespread attention from the research community and industries alike. The ability to accurately recognize human actions in videos has numerous applications, ranging from surveillance systems to human computer interaction, sports analysis, and entertainment.At present, there are three mainstream methods for processing video data, especially for action recognition: C3D, two stream network, and (2+1) D Net.SlowFast is a typical variant of C3D.The core of SlowFast is to process videos using two channels. These two channels are named Slow pathway and Fast pathway respectively. Compared with Fast pathway, Slow pathway has a relatively lower frame rate but has a greater number of channels. Slow pathway is used to capture semantic information in space, that is, Slow pathway captures the relatively static information in the video.While Fast pathway has a higher frame rate but a smaller number of channels. This greatly reduces the computational complexity of Fast. At the same time, it weakens Fast's ability to model spatial information and makes it pay more attention to information with obvious changes in the temporal dimension.Slow pathway and Fast pathway do not exist independently. The information fusion between the two is unidirectional information fusion. The two achieve information fusion through multiple lateral connections. And the direction of the lateral connections is from Fast to Slow. This means that Fast pathway will not receive any information about Slow pathway. This will undoubtedly lose some semantic information that describes space. We believe that adopting a more effective feature fusion method can further improve the recognition accuracy.Based on the well-known two branch network SlowFast, this paper introduces a significant improvement. Specifically, we propose an enhanced SlowFast network named ESL Net. A key innovation in this network is the addition of an improved 3D feature fusion module. This module is designed to make the most of the temporal information available in the video for effective feature fusion. It employs temporal and spatial attention mechanisms to precisely identify the most significant parts of the features. By analyzing the temporal information, it can also determine the crucial elements between dual - temporal features. Extensive experiments have demonstrated that our proposed method is highly effective when applied to the UCF-101 dataset and the HMDB51 dataset, showing superior performance compared to existing methods especially SlowFast Network in terms of accuracy and robustness in human action recognition tasks.

Yinhao Xu, Yuanyao Lu

Conference Proceedings

The effect of Hue difference in vibration environment on the cognitive performance of aircraft HUD Interface for pilots

In the aviation domain, the color design of the aircraft head-up display (HUD) is crucial for flight safety and operational efficiency. However, the effect of color difference on pilots' cognitive performance in a vibrating environment remains inadequately studied. This experiment aimed to address this gap. A precise experimental method was employed. For color variables, four basic hues in the HSB color system served as backgrounds, and foreground colors with specific color differences were carefully selected. The vibration conditions were set to 5Hz, 10Hz, 15Hz, 20Hz, and a non-vibration environment, simulating diverse flight scenarios. Subjects were required to perform a HUD information search task, and their reaction times and accuracy rates were recorded.The results showed significant interaction effects. In a high-vibration environment, a color difference of 60 degrees led to the shortest reaction time. In a low-vibration environment, 90 degrees performed better under certain backgrounds. In a non-vibration environment, color difference had a relatively minor impact on accuracy. Different background hues also affected the relationship between color difference and performance. For example, the green background had a lower accuracy rate at a 30-degree color difference.This study provides a solid basis for HUD color coding design. It helps optimize color design in a vibrating environment, enhance information recognition efficiency, and thus improve flight safety and operational efficiency. It offers valuable references for related fields and promotes the development of human-computer interaction technology in aviation.

Chen Junwu, Wenyu Wu, Jiayu Guo

Conference Proceedings

Human Intelligence and Artificial Intelligence Interaction in Start-Up Enterprise

Innovation capability is significant in the business environment, especially in start-up enterprises. This article emphasizes the growing complexity of technology and the need to manage the innovation process effectively. Integrating generative artificial intelligence tools using agent technology is essential for enhancing the efficiency of building start-up companies and innovation processes more broadly. Artificial intelligence (AI) supports team operations throughout all phases of the innovation process in start-up enterprises. The co-evolution of personal competence identification and team cohesion building is a crucial aspect of new entrepreneurship and start-up development. Data is recognized as a valuable currency in the innovation ecosystem, driving the data-driven innovation process. Human-oriented approach is necessary for capturing data from various sources and executing it in businesses. The strategic challenge is to apply a systematic approach using generative AI agents across all innovation phases. Overall, the abstract outlines the importance of human factors, team cohesion, artificial intelligence, and data-driven approaches in the innovation process, proposing a co-evolution framework for human and artificial intelligence interaction. The case study company analyzed is Husqtec Corp., a start-up company concentrating on situation and operational management. Use case is nature disaster management.

Vesa Salminen, Matti Pyykkönen, Krista Salminen, Oliver Tian

Conference Proceedings

The role of Artificial Cognitive Systems in the Implementation of the Aviation Fatigue Risk Management Systems

Aviation Fatigue Risk Management Systems (FRMS) are crucial for ensuring operational safety by systematically monitoring and mitigating the risks associated with human fatigue in complex and high-demand aviation environments. This paper explores the integration of Artificial Cognitive Systems (ACS) into FRMS, focusing on how these intelligent systems can enhance human decision-making and fatigue management, contributing to improved safety and efficiency in aviation operations. ACS possess the capability to process vast amounts of real-time data and make context-aware decisions, enabling more accurate identification of fatigue risks through predictive analytics, pattern recognition, and human-machine interaction. ACS can complement traditional fatigue management methods in the aviation sector by continuously assessing physiological data, work schedules, environmental conditions, and operational demands to dynamically adapt fatigue risk mitigation strategies. These systems can proactively alert pilots, air traffic controllers, ground staff, and flight crews when fatigue thresholds are reached, enhancing the overall effectiveness of FRMS. This paper analyzes key methodologies and frameworks—including the International Civil Aviation Organization’s Fatigue Risk Management guidelines and regulations by the European Union Aviation Safety Agency (EASA) and the Federal Aviation Administration (FAA)—to illustrate how ACS can be integrated into current fatigue risk systems while adhering to international safety standards. Additionally, we will examine worldwide case studies where ACS has been applied in fatigue monitoring and management within the aviation industry, highlighting the impact of AI-powered decision support systems in reducing fatigue-related incidents and accidents. The analysis also addresses the human factors implications of implementing ACS within FRMS, emphasizing the balance between human oversight and machine-driven recommendations. Understanding the relationship between human cognitive limitations and the capabilities of ACS is critical in ensuring that these systems enhance, rather than hinder, human performance. Through a human-centric approach, ACS can help reduce workload, improve situational awareness, and ultimately provide more reliable fatigue risk management without leading to over-reliance on automated systems. In conclusion, this paper will propose a framework for integrating ACS into FRMS, demonstrating how artificial intelligence-driven solutions can complement human expertise to reduce fatigue-related risks, improve safety, and create a more resilient aviation system. By focusing on both technological advancements and challenges related to human factors, this paper provides a comprehensive roadmap for the future of fatigue risk management in aviation.

Debra Henneberry, Dimitrios Ziakkas

Conference Proceedings

Underwater Fish length detection Using the AI-Based Depth Estimation

The scale of terrestrial aquaculture is steadily increasing compared to marine aquaculture. It is crucial to automatically observe and manage the growth process in terrestrial aquaculture facilities. However, the need to handle fish out of water to measure their size and weight can decrease their market value. This paper proposes the use of cameras to install underwater cameras for the automatic measurement of fish size, utilizing essential distance detection. This method allows for the relative estimation of the distance of fish underwater, where the pixel to meter approach is not feasible. It enables more accurate predictions of fish size by inferring the depth crucial to the pixel to meter calculation.

Ji Yeon Kim, Ki Hwan Kim, Young Jin Kang, Seok Chan Jeong

Conference Proceedings

Relationship between Attitudes toward Tourism Interaction and Motivations for Migration

Japan's declining population, falling birthrates, and rapid aging of society are long-term and rapid. This has made it difficult for some regions to even sustain themselves. Under these situations, the increase and decrease in the number of people in a region and the interactions that bring them to the region have a significant socioeconomic impact on each region. Therefore, it is necessary to elucidate the mechanisms of movement, such as tourism and migration. This study focuses on tourism interaction and population migration, and aims to clarify the relationship between attitudes and motivations related to movement. Specifically, the following contents will be analyzed. Regarding attitudes toward tourism and motivations for population movement, a questionnaire will be used to analyze the importance of each item in terms of tourism interaction and migration, as well as the importance of each item in the selection of tourist destinations. In addition to the previous analysis of attitudes toward tourism, a covariance structure analysis will be conducted to clarify the relationship between each factor and the factors. A cluster analysis will be conducted on the relationship between awareness of tourism and motivations for migration targeting each of the factors. This will elucidate the relationship based on the results of how they are categorized.The results show that there is a high degree of commonality between the two movement ideas of tourist interaction and migration, including a preference for stability and a preference for activity. It is quantitatively revealed that people are willing to make moves such as tourism and migration according to each person's preferences. It is quantitatively revealed that people are willing to make moves such as tourism and migration according to their individual preferences.

Akiko Kondo, Satoshi Togawa

Conference Proceedings

Does Military Experience Influence Strategic Decision-Making with Respect to Geographical Headquarter Placement

Intelligence, Surveillance, and Reconnaissance (ISR) operations leverage five key disciplines to facilitate and support the detection of our adversaries defensive posture, battle rhythm pattern, and headquarter location. These disciplines include geospatial intelligence (GEOINT), measurement and signature intelligence (MASINT), signals intelligence (SIGINT), imagery intelligence (IMINT), and human intelligence (HUMINT). However, understanding when to utilize the appropriate discipline for intel collections can be extremely challenging. To combat this issue, the 711th Human Performance Wing at Wright-Patterson AFB developed Intrage. Intrage is a strategic decision-making game developed to augment and enhance intel analysts understanding of ISR operations. The objective is to identify the location of the opposition’s headquarters on a fictional map. Moreover, previous literature has discovered that behavioral characteristics learned through experience can significantly influence decision-making outcomes. Therefore, a study was conducted to determine if there is a correlation with respect to headquarter placement based on military experience when provided a fictional map. The findings provided underlying evidence that participants with military experience centralized their headquarter location compared to participants with no military experience (p=0.02). This discovery will support the maturity and development of Intrage and provide behavioral characteristics which can be used to predict future military actions.

Justin Nelson, Timothy Heggedahl, Justin Morgan, Samuel Johnston, Jenna Cotter

Conference Proceedings

Elevating Student Success: Harnessing Machine Learning to Enhance University Completion Rates

This research paper presents a machine learning approach designed to aid universities in identifying students at risk of not completing their studies. Predicting student attrition and academic success is pivotal for universities to proactively intervene and enhance student retention rates. The proposed machine learning model harnesses historical student data, encompassing demographic information, academic performance, and financial status, to construct predictive models. These models employ a comprehensive array of algorithms, including Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), Decision Tree (DT), and Feedforward Neural Network (FNN), to categorize students into distinct retention-completion groups. By adopting this approach, universities can effectively allocate resources and implement targeted interventions, offering support to students likely to either transfer out or face academic challenges. In pursuit of these objectives, this paper highlights the specific methods employed to gather and preprocess historical student data. The rationale behind the selection of each algorithm is elaborated, showcasing their combined efficacy in providing a holistic analysis of student retention patterns. As an embodiment of data-driven education, this research holds the potential to reshape how universities approach student retention. Beyond the immediate insights derived, this work suggests a promising trajectory for further research and seeks to uplift academic outcomes and foster a more supportive learning environment.

Dandan Kowarsch

Conference Proceedings

Machine Learning-Based Prediction of Emergency Department Prolonged Length of Stay: A Case Study from Italy

Overcrowding in Emergency Departments (EDs) is a pressing concern driven by high patient demand and limited resources. Prolonged Length of Stay (pLOS), a major contributor to this congestion, may lead to adverse outcomes, including patients leaving without being seen, suboptimal clinical care, increased mortality rates, provider burnout, and escalating healthcare costs. This study investigates the application of various Machine Learning (ML) algorithms to predict both LOS and pLOS. A retrospective analysis examined 32,967 accesses at a northern Italian hospital’s ED between 2022 and 2024. Twelve classification algorithms were evaluated in forecasting pLOS, using clinically relevant thresholds. Two data variants were employed for model comparison: one containing only structured data (e.g., demographics and clinical information), while a second one also including features extracted from free-text nursing notes. To enhance the accuracy of LOS prediction, novel queue-based variables capturing the real-time state of the ED were incorporated as additional dynamic predictors.Compared to single-algorithm models, ensemble models demonstrated superior robustness in forecasting both ED-LOS and ED-pLOS. These findings highlight the potential for integrating ML into EDs practices as auxiliary tools to provide valuable insights into patient flow. By identifying patients at high risk of pLOS, healthcare professionals can proactively implement strategies to expedite care, optimize resource allocation, and ultimately improve patient outcomes and ED efficiency, promoting a more effective and sustainable public healthcare delivery.

Paolo Perliti Scorzoni, Anita Giovanetti, Federico Bolelli, Costantino Grana

Conference Proceedings

Avatar-based emotion representation with varying degrees of realism

In the age of digitalization with its progressive visualization of a wide variety of content, avatars are becoming increasingly important. Consequently, virtual human representations are also being used in healthcare, for example in therapeutic applications. The use of technologies such as virtual reality or virtual characters like avatars can support people who find social interactions challenging. This is often the case for people with autism spectrum disorder (ASD). The aim of the presented study was to evaluate the suitability of different avatar types for the development of a future digital application for people with ASD. Based on the results of a previous study, two avatar types that differed in their degree of realism were analysed: a cartoonish, simple avatar and a stylized, moderately detailed avatar. First, it was investigated how participants set different basic emotions on these avatars and whether these settings are comparable between the different types of realism as well as with previously defined values for the basic emotions. Afterwards, a threshold test was used to determine at what point the emotions displayed by the avatars became recognizable and at what point they were rated as pronounced. Overall, ten men and ten women (M = 24.9 years old, SD = 3.64) participated in the study. The results show that the average values set by the participants correspond to the previously defined values for the basic emotions, with a relatively high degree of variation in some cases. Overall, the insights gained within this experiment provide a basis for future research on this topic.

Valentin Wunsch, Knut Möller, Verena Wagner-Hartl

Conference Proceedings

FULL PAPER ONLY: Investigating the Impact of Confidence Scores in AI-based Decision Support Systems on Decision Quality and Reliance in Work Contexts

Due to the rising demands in work contexts, for example shortage of skilled workers and the increasing complexity of work environments and decision-making context, the use of artificial intelligence (AI) -based decision support systems, is increasing. These interactions differ in several ways from interactions with AI in leisure contexts:For example, in work contexts, individuals make decisions for which they are held accountable. In contrast, when using AI in leisure contexts, the consequences of an incorrect decision may not reflect them in a professional way. Also, because individuals are experts in their respective fields, they tend to be more critical of using AI-based assistance systems in work context. Furthermore, using AI in leisure contexts is voluntary, attracting individuals who are interested in and familiar with such systems. In contrast, the use of AI systems in work contexts is often mandatory, requiring even those who are less interested and of differently competent in using AI systems to engage with them. This raises the question of how to best support individuals in work contexts where they have a high need for assistance but may be the most critical of new systems and have diverse competency levels in dealing with AI.One opportunity to support users of AI-based systems is to assist in the interpretation and critical evaluation of the output of the systems. A promising approach in this regard is the communication of uncertainty through confidence scores. These scores aid end users in interpreting the output by conveying the level of certainty of the AI recommendation. Ultimately, this approach aims to achieve a realistic calibration of trust in the system.Many studies in this field do not sufficiently consider the specific characteristics of work contexts and focus on artificially constructed decision-making situations that are not transferable to professional settings. Often, these studies involve binary decision scenarios, such as distinguishing between sick and healthy in medicine. However, in practice individuals are confronted with not only binary but also multidimensional decision situationsThe present paper addresses this gap by designing an empirical study that investigates how uncertainty communication, in the form of confidence scores, affects decision quality, reliance in the AI system, and perceived task load in the context of a multidimensional decision-making situation at work. The paper presents the current state of literature and derives hypotheses related to these questions, discusses the requirements for the experimental design, and finally addresses these through deriving a specific study design.This research aims to provide valuable insight for both academics and practitioners engaged in the interaction of human and AI-based decision support systems, their collaboration, and implementation in the practice.

Antonia Markus, Lea Marleen Daling, Esther Borowski, Ingrid Isenhardt

Conference Proceedings

Classification of Food Challenges and Values Based on Open-ended Responses

Emerging technology refers to new, unestablished, and not widely recognized science and technology, and differs from existing science and technology that has widely penetrated society and occupies a definite position . One of the emerging technology is genome-edited crops. In terms of climate change risks and population growth, the potential of novel foods has a significant impact on food security. On the other hand, it has not been fully accepted by society at this time. In order for attitudes toward genome-edited crops to be formed in the future, it is believed that adequate information must be provided to the general public. In doing so, it is expected that providing information tailored to the orientation and values of each person, rather than providing the same information to all people, will lead to effective information provision. This study aims to analyze each person's food challenges and values considering their acceptability and knowledge of genome-edited agricultural product, and personality characteristics, and to derive findings that will lead to the provision of appropriate information.As a first step, the purpose of this study is to classify the challenges and values toward food based on the open-ended statements in the questionnaire survey and summarize the characteristics of each.2.MethodIn this study, a questionnaire survey was conducted on the following items:-Attributes (gender, age, place of residence, marital status, family composition living together, occupation)-Acceptability of genome-edited crops (8 foods)-Knowledge related to genome-edited crops (5 items)-Personality (10 items)-Food Challenges (Are there any new foods or dishes you have tried recently? Tell us about that experience)-Food Values (What factors do you think are most important in your food choices? Please be specific, indicating your own experiences) The survey was conducted on 2000 Japanese men and women in February 2024 via a research company. The age range was 20s to 60s, each comprising 20% of the total population, with half of the male and half of the female population in each age group.The respondents were asked to answer the questions “Food Challenges” and “Food Values” in free-text form, and to write at least 140 characters in Japanese.3.ResultThe two questions answered in the open-ended responses were classified using BERTopic, a natural language processing technique. BERTopic is a method of topic analysis using sentence vectors obtained with Sentence-BERT. Here, UMAP is used to reduce the dimensionality of the sentence vector and HDBSCAN is used for clustering. This allows for the creation of clusters of semantically similar responses. Here, clusters with a sample size of 5 or more were extracted. As a result, 75 and 57 clusters were obtained for “Food Challenges” and “Food Values,” respectively. Mapping in two dimensions also allowed us to identify broad categories of responses to “Food Challenges” and “Food Values,” from which 10 and 9 categories were extracted, respectively.4.Conclusion This study targeted genome-edited crops as one of the emerging technology, and aimed to provide appropriate information to promote social acceptance. Specifically, we categorized “Food Challenges” and “Food Values” based on free-response statements in a questionnaire survey of 2,000 Japanese men and women. As a result, 10 and 9 categories were found, respectively.In the future, we will analyze the results together with the results of other questionnaire items and consider how to provide information suitable for each orientation and sense of values.

Kyoko Ito, Yosuke Fukuda

Conference Proceedings

Intelligent Tourist Guide System: Four Seasons Pavilion in Humble Administrator’s Garden

This paper proposes a "Four Seasons Pavilion Wisdom Tourism" platform, which combines fine scene modeling, digital human and artificial intelligent technologies. The system enhances visitors' experiences and understanding of Humble Administrator’s Garden, a classical Chinese garden in Suzhou, China, by providing an immersive and personalized tour. The system focuses on the iconic Four Seasons Pavilion, utilizing technologies like augmented reality (AR), virtual reality (VR), and AI-driven interactive digital guides. This work disrupts traditional tourism models and introduces a new era of personalized, enriching, and interactive cultural experiences. Unreal Engine 5 (UE5) powers 3D character animation and a dynamic user interface, offering real-time fantastic interactions. It provides a prototype and reference for building up an intelligent tourist guide system.

Fang Liu, Zihang Lu, Yang Liu

Conference Proceedings

Exploring cybersecurity challenges of digital transformation in higher education

Cybersecurity is a critical issue when it comes to the digital transformation of operations and services undertaken by many organizations and sectors worldwide. In Saudi Arabia, the government aimed to improve the education sector by integrating the latest technologies in learning and by automating the workflow within schools and universities. In this study, we explore how potential cybersecurity threats resulting from the digital transformation are managed by Saudi higher educational Institutions. We conducted semi-structured interviews with cybersecurity and digital transformation experts to understand their digital transformation and risk management plans and practices. Based on our findings, the adoption of advanced technologies, such as IoT devices and cloud computing services, can lead to security and privacy risks, particularly the possibility of unauthorized access and misuse of data. Our study also reveals the key challenges organizations face when securing their systems, including the limited awareness among staff and students about cybersecurity issues and data compliance rules, the lack of resources, and the legacy systems and infrastructures. This study also outlines a set of practices to protect the digital infrastructure and resources within educational institutions.

Fatimah Alshahrani, Shoug Alyami, Mahdi Alyami, Abdulmajeed Alqhatani

Conference Proceedings

QHS Methodology for Mathematics Teaching in Engineering

The Fifth Systemic Helix (QHS) methodology represents a systemic tool to develop mathematical competencies in engineering. A key aspect of the QHS Methodology is to promote the integration of theoretical and practical knowledge, which is essential in the training of engineers. This includes the application of mathematical concepts in real engineering problems. Focusing on developing critical thinking skills, problem solving and the ability to argue and communicate mathematical ideas effectively. Collaboration between students, professors, and industry professionals enriches the learning process and prepares students for teamwork in professional environments. The implementation of technological tools and digital resources is an integral part of QHS, facilitating interactive learning and simulation of complex scenarios. The methodology includes continuous assessment mechanisms to monitor student progress and adjust teaching strategies as needed.

Rodolfo Martinez, Sonia Moreno Cabral, Sergio Ivan Nava Dominguez, Veronica Quintero Rosas, Janneth Sarai Villegas Quiñonez

Conference Proceedings

The Challenges of Integrating AI in Aviation Incident-Accident Investigations: A Human-Centric Approach

Integrating Artificial Intelligence (AI) into aviation incident-accident investigations presents unique opportunities and significant challenges. This paper explores the complexities of incorporating AI into the aviation investigation process, emphasizing the importance of a human-centric approach to ensure the technology's reliability, transparency, and accountability. The application of AI in investigations necessitates thorough adherence to existing international frameworks, including ICAO Annex 13 and regulatory guidelines from the Federal Aviation Administration (FAA), the European Union Aviation Safety Agency (EASA), and the National Transportation Safety Board (NTSB). However, AI provides improved data analysis, predictive modeling, and pattern recognition capabilities. Through the examination of crucial case studies, such as the investigation into the Lion Air Flight 610 and Ethiopian Airlines Flight 302 (Boeing 737 MAX) accidents, we illustrate how AI-driven data analytics helped investigators to analyze large quantities of flight data recorder (FDR) and cockpit voice recorder (CVR) information (FAA, 2024). AI-based systems contributed to investigating the Air France Flight 447 accident (Airbus A-330), where advanced data analysis techniques provided insights into pilot responses under adverse conditions (Stewarts, 2017). These case studies highlight AI's strengths and limitations in understanding complex system failures and human-machine interactions.Moreover, these examples underscore the necessity of human oversight in interpreting AI outputs and ensuring accurate, context-driven conclusions. Considering regulatory differences, the research findings address the intricate challenges of harmonizing AI systems with established human-led investigative methodologies. Specifically, the research focuses on how AI can be effectively integrated without compromising the critical decision-making processes traditionally managed by human investigators.Furthermore, the presented research examines how human factors must be prioritized to prevent over-reliance on AI outputs, maintain investigative integrity, and foster cross-disciplinary collaboration between AI experts and aviation safety professionals. By analyzing these case studies and providing a comprehensive review of AI's role in modern aviation safety, the research team aims to illuminate the path toward developing AI frameworks that complement human expertise rather than replace it. Ultimately, this paper calls for a balanced approach that leverages AI's strengths while addressing its limitations, ensuring that future aviation incident-accident investigations remain human-centered and safety-focused.

Dimitrios Ziakkas, Debra Henneberry

Conference Proceedings

Explainability in AI-based shift scheduling

As digitalization becomes more widely used in factories, preference-based shift planning is evolving into an important tool for human-centered work in various workplaces. Human-centered shift planning not only increases the efficiency of work, but above all considers the individual's preferences for certain shifts or activities and thereby empowers human workers. However, the planning algorithm used in previous work is based on AI and the algorithm is not able to explain why certain decisions in scheduling were made. The aim of this publication is to use AI-based shift scheduling as an example to make AI systems comprehensible for everyone and thus increase the transparency of the system as well as the user’s trust. Starting from psychological research, we developed a user-friendly explanatory model, that consists of four parts: Starting section, what-if-scenarios, educational classroom and FAQs. A user survey was then conducted to test the effectiveness of the model. The results show that most respondents find the model intuitive and understandable, although they have different preferences for explanations. This study provides insights into the design of explanations for shift planning systems and examines the effects of different explanatory approaches. It thus is the foundation for further research and development in this area.

Charlotte Haid, Gia-phong Tran, Johannes Fottner

Conference Proceedings

A graph theory approach for data lineage in complex information systems using a technology, organization,and people integrated model in nuclear plants

In the nuclear sector, the implementation of digital technologies plays a crucial role in optimizing the performance of installations throughout their entire lifecycle. It contributes to the timely and cost-effective delivery of all phases of the life cycle, including design, procurement, construction, commissioning, and operation, as well as facilitating the transition between these phases. The intricacy of nuclear projects and their digital transformation faces significant challenges related to the large and diverse supply chain lifecycle, which includes entities of varying sizes, durations, and maturity. This increases the complexity of information systems, which often results in fragmented data exchanges and the formation of silos, thereby creating loopholes in information exchanges and negatively impacting project delivery performance.The exponential growth of Complex Information Systems (CIS) has resulted in significant challenges in data management, data governance, and digitalized human-centered activities. To address this complexity and guarantee the lifecycle of these CIS, the emergence of the concept of data lineage—defined as the flowchart of all data manipulations—is a promising approach, for a large array of applications such as maintenance. However, CIS often consist of diverse elements communicating through various protocols and tools, which presents a considerable challenge for accurately modeling these interactions using traditional methods. The present study proposes a methodology based on graph theory for the analysis of data lineage. Moreover, the methodology incorporates the concept of Human System Integration (HSI), which is represented through the TOP (Technology, Organization, and People) model, with the objective of modeling the diverse interrelationships between CIS components. In this study, a maintenance chain of value was selected as a key use case of a real-world CIS system from the nuclear sector. The data flow begins at the stage of design of new components in nuclear power plants and continues through to the deployment of equipment that is active, operational and maintainable within the power plant units. This method permits the visual representation of data flow within the complex information system, thereby facilitating a more suitable data management and a comprehensive understanding of the interaction between its elements.

Luigui Salazar, Olivier Malhomme, Lies Benmiloud-bechet, Robert Plana

Conference Proceedings

Menu optimization of digital twin system based on user experience: A case study of lyophilized injection workshop

Menus are not only a basic user interface element in digital twin systems, but also a key component to improve system usability, user experience, and operational security. Pie menus have been used in SunView, NEWS, and many other systems since Hopkins pioneered them, but they are not widely used in digital twin systems. Previous studies have shown that its usage efficiency is better than that of linear menus, so this paper takes the lyophilized injection workshop digital twin system as an example to verify the user experience differences between pie menus and linear menus within the digital twin system. According to the function of the production line in the lyophilized powder production workshop, the pie menu and linear menu are designed for the interface of the cartoning robotic arm equipment in the intelligent packaging line, and the usability test is used to quantify the user experience data, and through the reliability and validity test and data analysis, it is concluded that the pie menu is higher than the linear menu in terms of ease of learning, use efficiency, usability, and satisfaction, etc., and that the adoption of the pie menu can help to improve user experience.

Xinlu Qu, Zhang Yiran, Wenyu Wu, Xiaojun Liu

Conference Proceedings

Narrative Utilization Ecosystem for Person-Centered Care

Person-centered care is proposed as a principle that values each care recipient as an individual (Kitwood et al. 1992). In nursing care, it is necessary to provide high-quality individualized care based on a deep understanding of the narrative, which is the life story of each care recipient, including their life background and values (Guendouzi et al. 2015). However, it is not easy for busy care workers to practice individualized care according to the person-centered care principle. Fragments of narratives are typically gathered during initial assessments when users start using nursing care services and through daily conversations. Unfortunately, these narratives are often underutilized in actual care practices. This issue arises from various factors, including challenges on the care recipient side, such as difficulty in self-disclosure due to dementia and inadequate rapport, and challenges on the care worker side, such as heavy workloads and variability in communication skills among care workers.Our goal is to collect and structure narrative fragments from care recipients, organize their life background, values, and characteristics related to their thinking and behavior, and then develop tools to effectively utilize this information in caregiving settings. This paper proposes a narrative utilization ecosystem to enhance the quality of nursing care services by implementing and disseminating these tools to care workers. By incorporating narratives into care services, we aim to improve the rapport between care workers and care recipients, encourage further self-disclosure from care recipients, and facilitate the collection of additional narratives. This approach is expected to create a virtuous cycle within the ecosystem. In this paper, we will describe the components of this ecosystem, including the aspects where care workers can leverage their interpersonal skills and the areas where technologies such as AI and robots can enhance efficiency in the future.In this study, to collect narrative fragments, we conducted an experiment in which a person with dementia walked and talked with a care worker in familiar areas where he had lived or visited in the past. During the experiment, we gethered narrative fragments by asking him to recount past episodes based on the scenery he saw while walking and the questions posed by the care worker. In this case study, we, along with the care workers, analyzed narrative fragments from the conversations during the experiment, generated interpretive stories, and attempted to understand his past episodes. Through this analysis, we uncovered his memories of his father, who was a train driver, from the narrative fragments shared at the site of the railroad tracks. Additionally, from the narrative fragments shared while looking at the river scenery, we understood his memories of playing in the river and his recollections of his mother, who was a good swimmer. In this paper, we also analyze the reasons why narratives are not effectively utilized in nursing care settings and discuss the requirements for providing better care services as a team by sharing narratives among care workers.Kitwood, T., Bredin, K. (1992). Towards a theory of dementia care: Personhood and well-being, Ageing and Society, 12(3), 269-287.Guendouzi, J., Davis, B., Maclagan, M. (2015). Expanding Expectations for Narrative Styles in the Context of Dementia. Topics in Language Disorders. 35. 237-257. 10.1097/TLD.0000000000000061.

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

Conference Proceedings

The Lack of Explainability in Automatic Speech Recognition Can Cause Faux Data Work

Automatic Speech Recognition (ASR) is increasingly used in healthcare to reduce documentation workloads by transcribing spoken words into Electronic Health Records (EHRs). However, these systems, based on machine learning, require ongoing data annotation and validation by healthcare professionals to ensure accuracy. This paper, based on fieldwork at a public Danish hospital, investigates the challenges healthcare professionals face in detecting and addressing technical issues, such as glitches, within ASR systems. Using mixed methods, the study reveals that healthcare professionals spend significant time annotating and training the machine learning algorithms—time that could otherwise be dedicated to patient care. Without access to clear metrics, like recognition rates, healthcare professionals are unable to effectively evaluate their data annotating efforts, leading to "faux data work," where data tasks seem productive but fail to improve system performance. The paper proposes two strategies to mitigate this issue; 1) providing transparent system metrics to enhance user engagement; and 2) creating structured sites of collaboration between healthcare professionals and IT professionals for better reporting of technical issues. These solutions aim to reduce inefficiencies and improve ASR accuracy in clinical settings.

Silja Vase

Conference Proceedings

Grasping the complexity of UX in the Long-term in Interaction with Embodied Conversational Agents

To comprehensively evaluate the experience of interaction between humans and ECAs (Embodied Conversational Agents), it is essential to consider a complex entanglement of dimensions that dynamically develop over time. This paper provides a review of the available methods to evaluate the human-ECAs interaction, and discusses the relation between this experience of use over time. The research was carried out through a systematic literature review, on 5 databases: Scopus, ACM, Web of Science, PubMed and IEEE Xplore. Findings reveal that over 147 publications on human-ECAS interaction, only 13 address the experience evaluation. Of these, only 3 face evaluate the user experience with ECAs over time. The majority of these evaluation methods concentrate on momentary experiences, neglecting the long-term perspective. The paper provides a map of methods to evaluate several user experience dimensions of interactions with ECAs, highlighting the importance to apply these methods not only on the momentary interaction but repeatedly over time.

Alessia Nicoletta Marino, Joy Ciliani, Giulia Teverini, Patrizia Marti

Conference Proceedings

Bridging Creativity and Technology: Integrating Generative AI into Architectural Pedagogy Through Hybrid Frameworks

Integrating Generative AI into architectural pedagogy marks a transformative shift in how design is conceptualized and taught. However, the primary challenge for educators lies in understanding how students can effectively control AI tools to produce design outputs that align with their creative ideas and address the requirements of the modules, all while navigating the complexities introduced by these technologies. This study explores a hybrid, human-artificial system-centered design approach employed in a series of speculative design workshops, to enhance the educational experience by integrating AI tools with traditional design methodologies. Two workshops focused on developing the future of lighting were conducted at a transnational university in China, utilizing a speculative design methodology that combines future thinking with a series of interrelated experiences involving numerous dynamic phases (Burns,1999). These elements are introduced as forms of experiential learning during the workshops to enhance students' engagement in diverse and complex activity settings. (Kolb,1984). The hybrid framework allowed analog and digital inputs, encouraging students to maintain control over their creative processes while leveraging AI's capabilities to augment their design outcomes. Integrating generative AI within a structured pedagogical framework significantly enhanced students' cognitive processes and engagement with complex design tasks. This approach fostered an environment where students could experiment with unconventional ideas and rapidly iterate on their designs, leading to more innovative and cohesive outcomes. The experiential learning approach also helped bridge the gap between theoretical knowledge and practical application, enabling students to better understand the implications of AI in contemporary design practice. The findings underscore the need for a structured yet flexible approach to integrating AI in design education, which helps students navigate the complexities of new technologies while enhancing their creative potential and skills. This approach sets a precedent for future educational strategies in design disciplines, fostering the creation of powerful hybrid-human artificial systems fully centered on the development of high-quality design solutions.

Gianmarco Longo, Silvia Albano

Conference Proceedings

Investigating Interface Layout Optimization for Enhanced Visual Search Efficiency in Industrial Manufacturing Systems

This study examines interface layout optimization to enhance visual search efficiency and cognitive performance in industrial manufacturing systems, addressing the high cognitive demands of human-machine interfaces. By improving information visualization, interface design can significantly enhance operators' comprehension and response time, ultimately boosting production efficiency. Two experiments were conducted: Experiment A assessed six layout configurations, identifying LT and MT as the most efficient for visual search. Experiment B used eye-tracking analysis to compare MT and LT layouts, with Scheme 1 (MT layout) demonstrating superior cognitive efficiency, logical structure, and user satisfaction. These results confirm the effectiveness of the proposed design standards and highlight the need for data-driven, intelligent interface layouts in modern manufacturing. The findings suggest that advanced information visualization within HMIs fosters coordination and efficiency in industrial ecosystems, supporting innovative future developments in interface design.

Yuchen Yuan, Xiaojun Liu

Conference Proceedings

Ethical Implications of Virtual and Augmented Reality in Workspaces: Challenges and Opportunities to Promote Inclusion and Safety

Contemporary workspaces are constantly evolving, and we have seen the emergence of remote and hybrid workspaces using virtual and augmented reality. With these advancements come many ethical considerations that need to be identified and addressed before these environments become more widespread. This includes issues concerning inclusion, access, and safety of Virtual Reality (VR) and Augmented Reality (AR) technologies in both virtual and in-person workplaces. Two research questions arise: (1) What are the ethical considerations and potential challenges associated with the use of VR and AR technologies in hybrid and virtual working environments? (2) How do these technologies impact inclusion, access, and the safety of shared content in hybrid and virtual workplaces? To answer these questions, our study systematically analyzes recent research on the ethical implications of VR and AR technologies in hybrid and virtual working environments. A total of 13 studies were identified based on specific inclusion criteria, such as the publication date and the presence of certain keywords in the title or text. While the research found some articles on the ethics of VR, AR, and the metaverse that briefly discuss work-specific dilemmas, we found scarcity of studies that focused specifically on ethics in VR, AR, and metaverse in the context of working environments. With this study we aim to provide a comprehensive understanding of some of the challenges and opportunities that VR and AR technologies can offer to users of workspaces and offer recommendations for organizations to address these ethical dilemmas in the name of inclusion and safety.

Joshua Chong, Xinyi Tu, Matteo Zallio

Conference Proceedings

Evaluating the Effectiveness of Different Directional Signage Systems in Indoor Wayfinding: A Human-Centered Experiment Conducted in Virtual Reality

The design of wayfinding systems plays a crucial role in shaping both indoor navigation efficiency and the overall spatial experience. Well-designed directional signage not only facilitates the swift and accurate navigation to destinations, minimizing physical fatigue, psychological stress, and frustration due to disorientation, but also plays a vital role in enhancing safety, particularly in emergency situations, by preventing accidents resulting from navigational errors. This is especially critical in complex architectural environments, where the presence of an effective wayfinding system is indispensable. Traditional indoor navigation strategies generally fall into two categories: the first involves grouping destinations and utilizing repetitive signage and arrows to indicate routes, which relies on the user's continuous spatial orientation; the second involves the implementation of continuous guiding paths on floors or walls, often distinguished by varying colors or line styles, designed to reduce cognitive load and minimize directional uncertainty, thereby promoting smoother navigation. Although each of these methods offers distinct advantages and limitations, a systematic comparison of their performance in different environments, especially through the combination of multiple signage types, remains an area that warrants further investigation.This study utilizes immersive virtual reality (VR) technology to simulate virtual environments and assess the efficacy of four distinct wayfinding systems in indoor navigation tasks. The research specifically examines the influence of signage systems on the wayfinding behavior of individuals unfamiliar with a building. Participants were tasked with navigating from the building's entrance to designated rooms under four different signage conditions: wall-mounted signage, ceiling-hanging signage, floor-based continuous guiding signage, and wall-based continuous guiding signage. Key performance metrics, including task success rate, travel distance, completion time, number of pauses, and average movement speed, were recorded and analyzed to evaluate the potential of each signage system in enhancing navigation efficiency.This research not only elucidates the effects of different signage systems on indoor navigation efficiency but also offers empirical evidence to inform the optimization of wayfinding systems in future architectural designs. The findings suggest that by strategically selecting and configuring signage types, the efficiency of navigation in complex or unfamiliar environments can be significantly improved, cognitive load reduced, and valuable insights provided for building design, spatial planning, and emergency evacuation strategies.

Yao Shi, Xiaozhou Zhou

Conference Proceedings

Advancing HCD through Interdisciplinary Approaches: Insights for enhancing User-Centric Innovation

The rapid advancement of digitalization and AI presents significant opportunities for small and medium-sized enterprises (SMEs), particularly in manufacturing. However, adoption is often hindered by limited resources, expertise, and scalability issues. This paper introduces an interdisciplinary framework combining engineering, labor sciences, and business informatics to address these challenges. The approach integrates the DMME model for technical rigor, Human-Centered Design for usability, and Action Design Research for iterative development. Through a series of co-design workshops with SME participants, the framework is validated, emphasizing the need for adaptable AI solutions that align with SMEs' unique operational requirements. The findings underscore the importance of bridging technical, human, and business aspects to develop AI systems that enhance user experience, operational efficiency, and digital transformation. Future work aims to refine the approach and extend its scalability for broader implementation.

Carolin Böhme, Dorothea Schneider, Mauritz Mälzer, Martin Schmauder, Steffen Ihlenfeldt

Conference Proceedings

Enhancing Technology Acceptance in Socio-Technical Systems: A Human-Centered Approach to AI Implementation

The integration of Artificial Intelligence (AI) into existing operational socio-technical systems presents a significant challenge, as it necessitates interventions in ongoing systems. The success of implementing new technologies critically hinges on the consideration of human factors, established workflows, and human needs. Neglecting these elements can lead to the failure of implementation at the human component. Therefore, it is imperative to involve humans not only in the development of technology but also in its implementation.This study explores how technology acceptance in socio-technical systems, particularly concerning AI, can be enhanced. Research, such as that conducted by acatech, reveals that the primary obstacle to the successful implementation of AI technologies and data-driven assistance systems is the human factor. Consequently, the inclusion of the human component in both technology development and implementation is pivotal for success.Effective knowledge transfer from research to businesses, especially within the framework of Human-Centered Design (HCD), is of utmost importance. Aligning with the United Nations’ sustainability goals is particularly supportive in creating functional networks and conserving resources. Adapting knowledge to individual practical cases is essential.The study advocates for a theoretical approach, emphasizing the necessity of HCD at different levels. HCD methodologies must be tailored to specific contexts, breaking down the approach into practical steps.There are three levels of Human Inclusion in AI Implementation:1. Technology: Adopting a genuine HCD approach, the research emphasizes moving away from inventing technology for non-existent problems or irrelevant issues. Instead, the focus should be on developing technology that addresses operational challenges.2. Organization: Training leaders, incorporating agile principles, and considering the organizational context are crucial for successful AI implementation.3. Mutual Participation: Advocating for participatory development where humans and technology collaborate, aiming to diminish technology apprehension and foster acceptance without overwhelming individuals.This study supports its arguments through existing research, logically concluding that a human-centered approach is essential for successful AI implementation. It emphasizes the need for suitable technology development aligned with operational challenges. We conclude by providing practical recommendations for implementing a human-centered approach within socio-technical systems, aiming to enhance technology acceptance without inducing change fatigue. Following the proposed approach promises technology acceptance without the negative impact of change fatigue. This outlook underscores the importance of a thoughtful and inclusive strategy in implementing AI within socio-technical systems.

Carolin Böhme, Claudia Graf-pfohl

Conference Proceedings

Evaluating AI-generated Research Plans: Expert Insights from a Blind Authorship Study

Artificial Intelligence (AI) is increasingly being adopted in academia to enhance various research activities and has proven to be a valuable research accelerator in recent studies. This study examines the capabilities of large language models (LLMs), specifically ChatGPT and Gemini, in generating comprehensive research plans during the early stages of research. We tasked both models with developing research plans on the topic of “Gen Z's willingness to sacrifice convenience for environmental benefits” including interview guidelines and survey questions. Eight expert researchers evaluated these research plans without knowing they were AI-generated. Our findings provide in-depth insights into the perceptions of expert researchers regarding the quality of AI-generated research plans, identifying missing elements and pitfalls of utilizing AI in the planning activity of research. The necessity for researchers to oversee and intervene in AI outputs is emphasised in our research to fully leverage the advantages offered by this technology.

Thi Thien Nhi Dam, Leo Glomann

Conference Proceedings

Characterization of motion and warning light signals for flying robots

As the use of flying robots in various types of human-robot collaborative work continues to increase, but their interaction with humans remains somewhat deficient, it has become critical to ensure that flying robots are able to convey information to humans in a timely and accurate manner. Lightspeak is an effective means to achieve this goal by controlling the lights on flying robots to convey information in a specific pattern, color, or frequency. In the field of industrial robotics, specific light patterns can be used to indicate the robot's working status, production progress, or possible malfunctions. Such visual signals can help plant operators quickly recognize robot status and act accordingly, thereby increasing productivity and reducing potential errors or hazards. Although the application of light language in industrial robotics has achieved some success, the research on human-robot interaction for flying robots is still relatively limited. Especially in dynamic and complex environments, how to design efficient light language patterns to adapt to the multi-dimensional motion characteristics of flying robots and to ensure that humans can quickly interpret light language messages remains an urgent challenge. Using virtual reality (VR) technology, this study aims to develop a set of flying robot intention characterization methods based on light signals by simulating flying robot light changes, designing light language rules applicable to the multi-degree-of-freedom motion and warning states of flying robots, and optimizing their performance in user understanding and interaction through experiments. Based on the task analysis of the flying robot, this study identifies seven degrees of freedom of motion and three main warning modes by decomposing the motion and warning states of the flying robot in detail. Based on this, we designed three basic light modes including constant light, blinking, and surge, and optimized their colors, blinking frequencies, and timings. The experiment uses 73 motion state light languages and 8 alarm state light languages to test the characterization effect and user preference of different light languages in multiple contexts through animated video and randomized design. The experimental study shows that in the stationary state, the all-light constant light signal has the highest preference rate, while in the dynamic motion state and emergency alarm state, the flashing signal (e.g., double flashing, long and short flashing) exhibits higher saliency and information transfer efficiency. Users' choices of light language patterns are highly correlated with their visual saliency, clarity of signal meaning, and situational urgency. The red light signal has a significant advantage in the warning state, and the high-frequency flashing signal is the most effective in the “hardware failure” scenario, while the stable constant light signal is more suitable for the “active stop” scenario. In this study, we propose a light language design method that combines perceptual theory, color design, and light animation, which significantly improves the efficiency of the flying robot's message delivery in multi-degree-of-freedom motion and alarm states. Through experimental verification, this set of light language rules provides important support for the safety and human-robot interaction ability of flying robots in complex application scenarios, and lays a foundation for the expansion of the light language in the field of robotics.

Zhuoran Ma, Ruihong Ma, Xiaozhou Zhou

Conference Proceedings

Optimizing Industrial Forklift Human-Machine Interface (HMI) Position

In a freight system there are many pieces of equipment that compose a system context. The system of interest for our examination is less than truckload (LTL) assets. This paper extends previous research of the tractor fleet to the dock fleet comprised of forklifts and operators. Forklifts are used to transport heavy shipments (i.e., fixed assets) inside a warehouse facility. Electronic documentation of these shipments determines trailer manifests, informs customers on freight location, and observes service constraints in real-time. Placement of incoming freight (i.e., warehouse stock) is communicated to forklift operators via an electronic tablet to enable tasking. The tablet displays workflow and informs the operator where to dock or load freight being processed. Finally, we must understand how the forklift operator interacts with the screen. The luminous intensity, luminous flux, luminance, and illuminance resulting from the tablet placement are used to calculate screen glare and realize necessary adjustments. Methods utilized for this research include analysis of device design alternatives, mounting options, and operator visibility. Interviews were conducted to assess perceived distractedness by the operators. This research concludes with a recommendation for tablet mount location that will maximize forklift operation effectiveness within the LTL system context.

Sarah Rudder, Sean Bumgarner

Conference Proceedings

Human Factors-Centric Validation of a Security Management System in a Linked Critical Infrastructures Environment

This work reports the human factors-related validation results of a security system for the protection of linked critical infrastructures (CIs) against combined cyber-physical attacks. Attacks of any kind on CIs have increased in number and complexity. In order to prevent or mitigate interruption of services to the public, the protection of CIs is of high importance. As an evolution of recent security research on single and linked CIs, the EU H2020 project PRAETORIAN adopted a holistic security management approach that addressed linked CIs with one overarching toolset.The PRAETORIAN toolset is specifically designed to support security managers of CIs in their decision-making processes. It enables them to anticipate, manage, and withstand potential cyber, physical, or combined security threats that could target their own infrastructures, as well as other interconnected CIs. These threats could have a substantial impact on the operational performance or service provision of these infrastructures and potentially compromise the safety and security of the population residing in their vicinities.The toolset consists of four primary systems: the Physical Situation Awareness (PSA) system, the Cyber Situation Awareness (CSA) system, the Hybrid Situation Awareness (HAS) system, and the Coordinated Response (CR) system. Central to the toolset is the Interoperability Platform (IOP), which interconnects all the modules within the PRAETORIAN toolset. This interconnection facilitates seamless information exchange across all systems and modules, ensures efficient data storage, prevents the duplication of data between modules, replicates any changes made, and avoids potential inconsistencies. This integration is crucial for providing unified data accessibility across the entire platform and to obtain a clear nomenclature for events and situations across the different infrastructure domains. Each system is composed of multiple modules. This document offers only a brief overview of each system, comprehensive and detailed explanation of the toolset's architecture can be obtained from the corresponding cited documents within the full paper.The focus of the system validation was put on the assessment of operators' feedback about the PRAETORIAN system (the toolset). In four exercises, potential attack scenarios were presented to groups of selected operators along with demonstrations of the PRAETORIAN tools. Feedback was collected using questionnaires, debriefing questions and open questions throughout the presented scenario. The key validation results show that the system could offer benefits for cross-infrastructure security management, but that improvements relating to systems and HMIs, procedures and responsibilities are required.

Florian Piekert, Tim H Stelkens-kobsch, Hilke Boumann, Meilin Schaper, Nils Carstengerdes

Conference Proceedings

Optimization-Based Automated Tasking for Complex Multi-Drone Missions

In this article, we present a concept for generating collaborative behavior for a heterogeneous team of drones with different capabilities that allows executing complex tasks in future military Manned-Unmanned-Teaming (MUM-T) helicopter missions. In these missions, the pilot is required not only to control their own helicopter but also to manage a large number of drones. This scenario quickly creates excess workload, as well as possible underusage of available resources. To prevent this, we create a simple command interface for the pilot that allows to assign multiple tasks to the drones by selecting only essential parameters. These, in turn, are used to automatically distribute the resources and generate an easily adjustable mission plan.Our approach starts by designing the interface that allows the pilot to choose from a menu of broad objectives (for example, the two main use-cases considered: “reconnaissance” or “coordinated attack”) that express the desired goal. Then, some more specific parameters need to be chosen. In the first case, the pilot needs to select the area, point or object to be analyzed, as well as the level of desired accuracy and time invested. For example, on the coordinated attack , where the drones need to engage a certain number of targets at the same time, the pilot needs to manually select the intended targets. In order to create reliable automated tasking, two main aspects must be taken into account. First of all, the mission scenario, with parameters such as the level of risk of the considered area; the number, size, type of defenses, and location of targets, and whether these are static or moving. These elements, along with the goal, will determine the success criteria and variables to be optimized for each mission. For example in the first use-case, if the targets are moving, the mission may only be deemed successful once the section is swept multiple times. For the second use case, both the trajectory as well as the UAV velocity need to be computed in order for an attack to happen simultaneously. Additionally, drone characteristics must be considered, such as sensor capabilities (with respective uncertainty and range), replacement costs, and airspeeds. Once all these elements are properly defined, they can be used to define the utility function (which is the probability of mission success) that is then maximized by the candidate parameters (such as trajectory and velocity).These aspects are used to calculate the probability of mission success to be maximized, as well as the optimization constraints needed. This concept will enable complex multi-drone missions and will be integrated into our mission and cockpit simulator environment for testing and verification by pilots from the German Army .

Verónica Mendes Pedro, Axel Schulte

Conference Proceedings

Teaching with Artificial Intelligence in Rural Communities for Microenterprise Development

This study explores the use of artificial intelligence (AI) as an educational tool to train rural communities in sustainable development and microenterprise creation. The initiative aimed to strengthen local knowledge on the sustainable use of native species, particularly Atractosteus tropicus (tropical gar), and to foster economic growth through the development of innovative products and the creation of small businesses. The communities were trained on the importance of conserving local biodiversity while sustainably utilizing these natural resources for economic purposes.AI played a key role in creating customized educational training materials designed to meet the needs and cultural context of the communities. These instructional materials focused on sustainable fishing practices as well as the development of products derived from this local species. AI helped bridge the gap between existing community practices and new sustainable approaches by applying traditional knowledge with personalized teaching techniques. This integration empowered communities to balance environmental management with economic opportunities.A fundamental component of the program was the development of entrepreneurial skills. Participants, many of whom were women, received training in microenterprise creation, branding, and marketing strategies. AI-generated materials guided them in creating value-added products, such as tropical gar tamales and empanadas, which could be marketed locally and regionally. The hands-on approach, which included financial management and sustainable production, provided participants with a solid foundation to establish and grow their businesses.The training aimed to empower community members by providing them with the necessary tools to effectively start and manage microenterprises. Additionally, the AI-driven approach facilitated financial education, enabling participants to acquire business management practices that support long-term economic sustainability. This approach combined biodiversity conservation with business development, fostering a greater understanding of how environmental care can coexist with economic growth.Preliminary results indicate that community members gained confidence in applying sustainable practices and creating new businesses, expressing through interviews an interest in continuing to participate in similar projects that address socioeconomic development through the sustainable use of natural resources. The project reinforced a sense of belonging and responsibility towards natural resources within the community, and the trainers expressed interest in continuing to use AI-driven methods to enhance their skills. The success of this project demonstrates that AI can be a powerful tool for promoting sustainable development in rural areas, particularly when combined with education and discipline in management, community participation, and the protection of native species.Future research will focus on the long-term effects of these educational initiatives on the economic and environmental outcomes of the communities. The potential to expand this approach to other rural areas facing similar challenges will also be explored, with the aim of contributing to the Sustainable Development Goals (SDGs) related to environmental conservation and the economic empowerment of rural communities.

Diana Rubí Oropeza-tosca, Rodolfo Martinez, Roger Notario-priego, Karina Gonzalez -izquierdo, Maria Rivera-rodriguez

Conference Proceedings

Automating customer feedback in online marketplaces with retrieval augmented generation

This paper proposes a solution for automating customer review responses in online marketplaces. The goal is to save time and resources for sellers. The proposed system combines traditional methods with Large Language Models, allowing the sellers to provide a personalized service and improve customer satisfaction. The system has been implemented and integrated with two main online marketplaces in Russia: Wildberries and Ozon. The study demonstrates promising results in terms of response quality and efficiency. In particular, the system was used to answer more than 3800 reviews for three sellers, which was estimated to be an equivalent of 120 working hours.

Gleb Shalimov, Mikhail Kuskov, Nursultan Askarbekuly

Conference Proceedings

Observatory of Social and Solidarity Economy, NODESS, SDGs, and Research Networks

The project of the Municipal Observatory of Competencies for Sustainable Development Goals (SDGs) Mexico 2030 Agenda, is a research initiative through the Social and Solidarity Economy Research Network (RIESS Network) of national category of the TecNM, which contemplates the development of the diagnosis and training of Students and Professors of Higher Education on the Sustainable Development Goals (SDGs), as a strategy to encourage the development of research project initiatives and methodological skills; as well as to propose the bases of a model for the development of the Voluntary SDG Reports at the city level, and the variables of a Municipal Observatory of SDG Competencies of the Mexico 2030 Agenda. With the application of QHS methodology, management is promoted to achieve the skills, management and productivity of the desirable profile of Professors and Researchers, the consolidation of the Academic Bodies, through collaborative work in Network, achieving the impact and benefit on Higher Education Students, training of new cadres for generational replacement of Teachers, new Researchers, consolidating the capacities of Research, Teaching, Technological Development and Innovation with Social Responsibility.

Rodolfo Martinez, Diana Rubí Oropeza-tosca, Gaudencio Lucas Bravo, Sonia Moreno Cabral, Carmen Esther Carey Raygoza

Conference Proceedings

Evaluating the Impact of Head-Up-Display Position for Navigation Systems on Driver Safety and Usability

Head-Up Displays (HUDs) in passenger vehicles are increasingly recognized as a promising technology for enhancing driver immersion and improving road safety by projecting essential information directly into the driver’s line of sight. Despite the apparent advantages, HUD systems have also been associated with challenges, particularly concerning cognitive overload and the possible impact on drivers' focus and overall safety. This study seeks to address these concerns by evaluating HUD navigation systems in comparison with traditional Head-Down Display (HDD) systems. To systematically investigate the effects of HUDs on driver behaviour, a controlled driving simulator study was developed and tested by 22 participants. Each participant engaged in driving tasks using both HUD and HDD interfaces, allowing for a direct comparison of driving behaviour on key behavioural metrics. Authors evaluated variances in the participants' attention to road conditions, their cognitive load, and interaction patterns with the navigation systems. In addition to these objective measures, subjective feedback was collected from participants to capture their personal impressions and preferences regarding the usability and effectiveness of each display type in the simulated Laboratory driving environment. The findings from this research highlight several notable advantages of HUD systems. A significant majority of participants expressed a preference for HUDs, primarily due to the reduced need for frequent focal shifts between the display and the road, which allowed them to maintain better situational awareness of their surroundings. Quantitative performance metrics, such as the duration of road focus and the accuracy of environmental perception, were consistently higher when participants utilized HUDs compared to HDDs. The research offers specific recommendations for future design refinements aimed at achieving an optimal balance between information presentation and driver safety, paving the way for more effective and safer HUD integration in future vehicle models.

Ahmed Farooq, Mehmet Mertkan, Toni Pakkanen, Roope Raisamo

Conference Proceedings

A Multimodal Sensor Setup for In Situ Comparison of Driving Dynamics, Physiological Responses and Passenger Comfort in Autonomous Vehicles

With the growing integration of automated driving (AD) functions in passenger vehicles, it is essential to focus not only on safety but also on passenger comfort which is often overlooked in the design process. Integrating this in the design cycle requires a thorough understanding of the relation between objective metrics and the subjective passenger response. This paper introduces a novel multimodal measurement platform for efficient measurement of objective metrics and subjective comfort in a representative AD setting. The platform, built on a commercially available electric vehicle, contains sensors to concurrently capture data on vehicle dynamics, environmental conditions, and passenger physiological responses. An automated data processing pipeline has been developed to compute and visualize metrics related to both vehicle performance and passenger comfort. The platform has been utilized in a proving ground jury test, with preliminary qualitative analyses identifying potential comfort-related indicators, such as Time-to-Collision and Galvanic Skin Response. The platform and its processing pipeline will be the basis for further investigation into objective-subjective comfort correlation and prediction in the future.

Harald Devriendt, Mathieu Sarrazin, Thomas D'hondt, Konstantinos Gkentsidis, Karl Janssens

Conference Proceedings

The Effect of Tactile Prompts During the Takeover Process of Autonomous Driving

Autonomous driving technology is a key approach to enhancing road traffic safety and efficiency. Autonomous vehicles operate at a semi-autonomous level, necessitating driver intervention in certain situations. When the autonomous driving system encounters an emergency and issues a takeover request warning, it is imperative for the driver to promptly, safely, and smoothly assume control of the vehicle within the prescribed reaction time. During driving, auditory and visual channels are often occupied, which may lead to missed takeover information delivered through these modalities. Tactile signals emerge as an effective alternative to address this issue. This study utilizes a driving simulator to replicate driving scenarios and investigates the impact of tactile takeover signals on driver takeover efficiency. Additionally, subjective questionnaires were administered to assess drivers' psychological perceptions. The results demonstrate that tactile signals can effectively enhance driver takeover efficiency and are favorably received by drivers.

Sijia Guo, Wenyu Wu

Conference Proceedings

The Evaluation of AR-HUD Visual Augmentation Method Based on Situation Awareness

Augmented Reality Head-Up Display (AR-HUD) enhances driving safety and experience by overlaying virtual information into the driver’s forward view. However, AR-HUD may lead to attention capture, causing the driver to focus excessively on the AR-HUD and neglect other critical environmental information. Therefore, it is crucial to study how to balance the driver’s attention allocation between AR-HUD information and environmental information to ensure effective situational awareness (SA). The study based on Situational Awareness Theory, evaluates the impact of different AR-HUD augmentation methods (boxes, arrows, and shadows) on drivers' SA through analyzing eye movement data and Situation Awareness Rating Technique (SART) data. The results show that the different augmentation methods significantly affect drivers' SA levels. The box-type augmentation method performs the best overall and effectively improves the driver's SA. The study provides a theoretical foundation and practical guidance for the optimization and application of AR-HUD design.

Weiran Rong, Wenyu Wu, Xuan Sun

Conference Proceedings

Dynamic Optimization of Adaptive Vehicle Lighting Systems: A Multimodal Assessment of Driver Performance and Well-being

This study introduces a pioneering method for optimizing Adaptive Vehicle Lighting Systems (AVLS) by integrating eye-tracking technology and physiological indicators to assess driver performance and safety comprehensively. Building upon previous research on AVLS's impact on driving outcomes, this study employs a multimodal evaluation strategy that captures the intricate interplay between visual attention, cognitive load, and stress response under various lighting conditions. The primary objective is to identify personalized lighting configurations that enhance situational awareness and diminish cognitive demands on drivers.Participants engaged in a series of simulated driving tasks under controlled AVLS settings designed to emulate a diverse array of road scenarios. The preliminary findings of this research highlight the intricate relationship between AVLS settings and driver performance. The study reveals that optimal lighting conditions can notably reduce pupil dilation, a physiological marker of cognitive load, improve scanning efficiency, and enhance visual search capabilities. Moreover, personalized lighting adjustments have been shown to alleviate stress levels and enhance driver comfort, as indicated by reductions in heart rate variability and skin conductance responses.This study underscores the significance of a multidimensional evaluation of AVLS parameters. By overcoming the limitations inherent in current research, this method aspires to offer a more precise and effective optimization of AVLS. The ultimate goal is to bolster road safety and driver assistance. Through extensive testing under diverse conditions and a comprehensive assessment of performance indicators, this study sets the foundation for the progression of AVLS technology. The advancement of AVLS technology, in turn, can better adapt to the dynamic and ever-changing characteristics of road environments, ensuring a safer and more comfortable driving experience for all.

Ruizhuo Chai, W Wu

Conference Proceedings

Professional Competencies of Civil Engineers through the QHS-Six Sigma Methodology

The QHS-Six Sigma Methodology is used to promote the development of civil engineer professional competencies, encouraging comprehensive skills to ensure performance with knowledge, skills, and attitudes for systemic development with a focus on continuous improvement and innovation in the quality of professional services projects to clients in the construction industry. The provision of services of civil engineering professionals involves knowing aspects of the context of business, government, academia, associations, and consulting, as well as specific skills of teamwork, quality controls, project management and monitoring of key performance indicators (KPIs). Key aspects in the training of civil engineers, for the field of the construction industry with quality tools based are used to supervise and optimize the management of materials in projects. The contribution of the QHS-Six Sigma methodology in civil works projects is to improve critical thinking and problem-solving skills. Collaboration between students, faculty, and industry experts supports the teaching process and enables students to perform effectively in workplace work teams.

Jose Manuel Alonso Reyes, Arturo Licona Martinez, Rodolfo Martinez

Conference Proceedings

Towards Understanding Human-Technology Migration: Internal Interaction in Automated Road Vehicles

Vehicle automation has evolved from early systems, like cruise control, to more advanced technologies requiring deeper exploration and understanding of human-automation interaction and Human Systems Integration. Initially, research focused on human-computer interaction, but it later shifted towards a dynamic cooperation between humans and machines. As vehicle automation levels will vary in the future from partially to highly and fully automated systems, new safety concerns arise. These are particularly relevant for transitions of systems between automation levels and migrations of humans and technology between different configurations of the socio-technical systems. This paper describes a work-in-progress in the German DFG-project MiRoVA (Migration of Road Vehicle Automation), especially subproject 4, which focuses on internal interaction in the vehicles, e.g. between the automation and the driver. In this subproject we aim to address gaps in understanding the impact of automation migration on human-machine interaction. The focus is to explore how changes in automation levels affect human-machine cooperation and HMI design. This paper presents the fundamental aspect of human systems migration of vehicle automation, followed by resulting goals and the research concept created to investigate the impact of automation migration on human-machine interaction in human-in-the-loop simulations of traffic systems.

Paul Weiser, Michael Preutenborbeck, Marcel Usai, Frank Flemisch

Conference Proceedings

Exploring Inner Landscapes Through Material

Today’s youth are confronted with a complex and ever-changing reality, filled with stimuli and contradictions that challenge their inner world and render them more vulnerable to the demands of daily life. Their “interior landscapes,” shaped by the digital age, are increasingly heterogeneous and contradictory, highlighting fragilities and insecurities that can hinder their educational journey. However, verbal expression and the sharing of emotions, whether positive or negative, is a complex and sometimes painful process, often leading to the internalisation of their discomfort.This paper presents the outcomes of a workshop conducted within the framework of the three-year orientation project POT Design NEED, funded by the MUR (Italian Ministry of University and Research). The workshop took place at the Department of Architecture of the University of Chieti-Pescara, with the participation of students from the Design bachelor degree program and students from the MiBe (Art High School) in Pescara.The workshop aimed to guide students on a journey of self-discovery without their awareness of being subjects in a personal exploratory study, to avoid influencing the final results. This “journey” was valuable for exploring the students’ emotional states, in order to understand their latent needs (emotional, psychological, etc.). The goal was to contribute to overcoming the difficulties and discomforts they encounter in the university environment, thus aiding them in their educational journey.The workshop employed a non-invasive approach to explore the emotional universe of the students. Through a creative process that led them to express their emotions by creating tactile, material-based tablets, it was possible to conduct a needs and difficulties analysis in an environment of mutual listening and dialogue. To achieve this, they were invited to manipulate a synthetic, moldable paste in a synesthetic process, adding or removing material, “imprinting textures,” or treating the surface with various tools, all while listening to music that best represented their current emotional state.By selecting a keyword, the students were able to imbue the material with emotional and symbolic significance, tangibly expressing the nuances of their inner world. The resulting tiles were then presented in a video and discussed in groups, offering students a unique opportunity to reflect on their experiences and connect with the emotions of others.This experience lays the foundation for the construction, over the next three years, of an “emotional atlas” of students, identifying areas of greatest vulnerability. This atlas will serve as a valuable compass for guiding support interventions in education, with the aim of promoting a “personal” educational journey that allows students to face and overcome obstacles with the utmost serenity.

Stefania Camplone, Ivo Spitilli, Giuseppe Di Bucchianico

Conference Proceedings

Harnessing Magnetorheological Fluids in Implantable Actuators: A Novel Approach to Precision Haptic Feedback in Biological Tissues

This research introduces rheACT, an innovative implantable actuator that utilizes magnetorheological (MR) fluids encased in hydrogel to deliver precision haptic feedback. The system leverages the tunable properties of MR fluids, which alter their viscosity in response to external magnetic fields, allowing for real-time, localized tactile feedback when controlled via electromagnetic coils. Designed to be injected sub-dermally, rheACT addresses challenges of biocompatibility and long-term stability through hydrogel encapsulation, which prevents fluid diffusion and can minimize immune responses. Laboratory experiments conducted on animal tissue demonstrated significant mechanical displacement (up to 1.3mm) at lower actuation frequencies (80–100 Hz), indicating the system’s ability to provide distinct and perceivable feedback. A user study further validated the system, showing consistent tactile sensations across varying frequencies and confirming rheACT's potential for precise haptic interaction. Although these findings are within animal tissue testing, results suggest that rheACT could be a reliable, externally controlled solution for applications in human-computer interaction (HCI), prosthetics, and assistive devices, where nuanced and adaptable feedback is crucial. The research highlights the integration of MR fluid technology and smart materials injected into the skin as smart tattoos, paving the way for future clinical and wearable applications that demand responsive, long-term haptic feedback.

Ahmed Farooq, Roope Raisamo

Conference Proceedings

Plant to fork: from sustainably sourced bio-based feedstock to 3D printed delicacies

The study explores the use of vegetable by-products, specifically tomato peels, to promote sustainable consumption of plant-based foods. The case study presented focuses on optimising the cultivation of tomatoes for the synthesis of bioactive compounds such as polyphenols, which are typically concentrated in the peel and discarded during industrial and domestic processing. In Europe, over 200,000 tonnes of tomato waste, primarily peels and seeds, are generated annually, posing environmental and economic challenges. To address this, the project utilises hydroponic and aeroponic cultivation methods to enhance polyphenol production in tomatoes. The bioactive-enriched tomato peels are subsequently transformed into a nutritious and innovative food product—3D printed pasta. The research outlines a detailed methodology involving the drying, pulverising, and incorporation of tomato peel powder into pasta dough, followed by 3D printing and cooking. The pasta’s bioactive content is measured at various stages of the process, from fresh tomatoes to cooked pasta, to ensure the retention of nutritional properties. This project demonstrates the potential of utilising food waste in a sustainable, technologically advanced manner, offering both environmental and health benefits through the creation of visually appealing, enriched food products. The results highlight the viability of transforming food by-products into value-added consumer goods.

Patrizia Marti, Giampiero Cai, Sara Parri, Agata Di_Noi, Sebastiano Mastrodonato, Antonino Gullì

Conference Proceedings

An autonomous shuttle for everyone: What information do users need when using shuttles?

One of the objectives of the publicly funded autotech.agil project is to develop an autonomous on-demand shuttle to make public transport more flexible. In this context, the goal is to develop an inclusive interface solution that provides relevant information to all user groups. As autonomous on-demand shuttles also open up new perspectives regarding mobility for people with disabilities, the user-centered development process will also consider participants with special needs. For this purpose, six workshops with 28 participants from different user groups were conducted: people with undisclosed disabilities (n = 12), retired (n = 4), cognitively (n = 3), physically (n = 4), and visually impaired (n = 4) were conducted. The information needed at the stages, “arrival of shuttle at station”, “traveling with shuttle”, “arrival at destination”, and the preferred location of the information, “display” vs “smartphone” vs “both”, were assessed. The analysis showed that at both stages, arrival of shuttle as well as traveling, all groups needed similar information. Apart from general information such as the time of arrival, the information needed when arriving at destination differed between the groups. Regarding the location of information presentation, most user groups (except retired participants) went for redundant presentation on both, smartphone and display. A subsequent step is to use the information gathered to develop a suitable inclusive HMI for an autonomous shuttle. Further studies need to investigate the comprehensibility of such a solution.

Ida Kuck, Lotte Wagner-douglas, Lena Wirtz, Stefan Ladwig

Conference Proceedings

Innovative Multimodal Translation: Unveiling the Figure Out Application's Real-Time Language Solution

Communication across languages, particularly between deaf and hearing individuals, presents significant challenges. Traditional translation tools, while helpful, often fail to fully address the diverse needs of these users. This paper introduces Figure Out, a mobile application designed to provide real-time translations of text captured from images. By utilizing advanced optical character recognition (OCR), Figure Out translates written text into multiple formats—audio, text, and sign language—making it particularly accessible for individuals with hearing impairments. The app’s key advantage is its support for both spoken and signed languages, offering a comprehensive tool for inclusive communication.By integrating text, spoken, and signed language translations, Figure Out takes a unique approach to breaking down communication barriers and fostering inclusion. It allows users to engage with the world around them, translating everyday text such as signs, timetables, and menus quickly and efficiently.A standout feature of Figure Out is its real-time image-to-sign language translation capability, which is not commonly found in other translation tools. This functionality enables seamless communication in real-world situations like reading public notices, navigating transport hubs, or visiting cultural and historical sites—contexts where written information may otherwise be inaccessible to the deaf community.Beyond casual use, Figure Out offers significant potential in education and tourism. In educational settings, it fosters inclusivity by providing deaf students access to learning materials in sign language. For tourists, especially those who are deaf or non-native speakers, the app serves as a personal guide, translating information into their preferred language, thus enriching their travel experience. Also, it promotes cultural accessibility by enabling greater engagement with museums, galleries, and historical sites. Finally, Figure Out is more than just a translation tool – by offering real-time text, audio, and sign language translations, it addresses the need for accessible, user-friendly technology that benefits both deaf and hearing individuals. Its ability to improve daily interactions and enhance accessibility in cultural, educational, and travel settings positions it as a valuable contribution to breaking down language barriers and fostering a more inclusive society.

Paula Escudeiro, Nuno Escudeiro, Márcia Campos, Francisca Escudeiro

Conference Proceedings

Optimizing Healthcare Efficiency with Local Large Language Models

Large Language Models (LLMs) are increasingly recognized for their potential to alleviate administrative burdens in healthcare, enabling medical professionals to focus more on patient care rather than time-consuming administrative tasks. This paper explores how local LLMs can support healthcare settings by automating and streamlining routine administrative duties, improving workflow efficiency, and ultimately enhancing patient care.One of the key applications of LLMs is in the management of medical documentation. Healthcare professionals often spend significant time on tasks such as transcribing patient notes, updating medical records, and completing forms. By using LLMs, these processes can be automated or simplified. The models can transcribe and structure patient interactions in real-time, generate diagnostic summaries, and update electronic health records (EHRs) based on structured inputs, reducing the time healthcare providers spend on paperwork. This not only saves valuable time but also minimizes the risk of errors associated with manual data entry.Another area where LLMs can be beneficial is in appointment scheduling and patient communication. LLMs can be integrated into practice management systems to manage appointments, send reminders, and handle patient inquiries. By processing natural language requests, these models can schedule or reschedule appointments, direct patients to the appropriate specialists, and provide answers to frequently asked questions. This reduces the administrative workload for healthcare staff, allowing them to focus on more critical tasks and improving overall clinic efficiency.In addition, LLMs can assist with billing and insurance processing. By automatically extracting relevant information from patient records and claims, LLMs can generate billing codes, verify insurance coverage, and ensure that all necessary documentation is submitted. This reduces the administrative burden on healthcare providers and billing departments, streamlining the reimbursement process and minimizing errors in insurance claims.Local LLMs also aid in regulatory compliance by automatically ensuring that healthcare institutions adhere to relevant legal requirements, such as patient consent and privacy regulations. By continuously monitoring the creation and modification of medical records, these models can flag potential issues related to compliance and generate alerts, ensuring that healthcare providers remain in line with regulations such as GDPR. This proactive approach to compliance reduces the risk of legal liabilities and minimizes the time spent on manual checks.In conclusion, by automating tasks such as documentation, scheduling, billing, and regulatory compliance, local LLMs can improve workflow efficiency, reduce human error, and enhance overall productivity in healthcare settings. As the technology evolves, local LLMs have the potential to significantly transform healthcare operations, allowing medical professionals to focus on what matters most: their patients.

Ivan Lorencin, Nikola Tankovic, Darko Etinger

Conference Proceedings

Developing a Liquid Hydrogen (LH2) System Layout for an Aircraft: A Programmer's Perspective

The future of aviation lies in the adoption of sustainable technologies such as liquid hydrogen (LH2) fuel systems. The integration of these systems requires sophisticated management of the fuel flow, control mechanisms, and pilot interaction. This paper discusses the development of an LH2 system layout for a next-generation aircraft, with a focus on the simulation and interface design process from a programmer’s perspective. Utilising Cranfield University’s Future Systems Simulator (FSS), an iterative design and implementation process involved collaboration between pilots, engineers, and human factors specialists. Design and implementation: Initial conceptual designs were created in Miro during a series of workshops with subject-matter experts and pilots that refined key control elements and safety-critical aspects of the LH2 system. These prototypes were implemented in the FSS using Unity and linked with the aircraft and engine models, providing a platform for instant changes based on the pilot's feedback. Key technical challenges included developing control-loop algorithms for HMI that allowed autonomous engine management with pilot override capabilities. Data transmission between the FSS and LH extsubscript{2} model was optimised using half-byte encoding to handle real-time system data efficiently despite the large volume of information. Scenario: A series of test flights were performed in the FSS using the newly developed LH2 engine model and HMI layout. The first test was a "clean" flight, with no system faults, where pilots started the LH2 engines using electronic checklists, completed a circuit flight, and landed. Subsequent flights involved triggering system faults to assess pilot responses. Two sessions were conducted: the first with project-involved pilots aware of the potential faults, and a second "blind" trial with external pilots. Pilots wore eye-tracking devices, and post-flight interviews were conducted to gather qualitative feedback. System Usability Scale (SUS) scores were also recorded to evaluate interface usability.The pilot interface provided intuitive synoptic pages for system monitoring and control to enhance situational awareness and response times. Feedback from the trials will guide future refinements to the HMI layout, focusing on safety and usability optimisation.Conclusions: This paper demonstrates the integration of advanced programming techniques and human-centred HMI design, which is critical to the successful implementation of sustainable fuel technologies in aviation. It also highlights the importance of flight simulation platforms like the FSS in enabling safe and cost-effective development and testing of these systems. Future research will focus on optimising the procedures, layout design, and control algorithms, which will lead to conducting real-world validation tests for certification.

Wojciech Korek, James Blundell, Wen-chin Li, Linghai Lu, James Whidborne, Thomas Clare, Peter Beecroft

Conference Proceedings

The influence of cutural locality on the understanding of visualization in system operation

Digital world brings about thoughts on system operation visualization, the degree of visualization greatly affects the difficulty of system operation. the operation process of easily understand can increase the popularity and inclusiveness of the system to some extent. Currently, the visualization of the system is more based on refined words and simple graphics or symbols. It main purpose is to let users clarify and use the operation by intuitive "understanding", It formed by previous and cultural etc. As Heidegger and Gadamer (1983) both say that this anticipatory projection of meaning underlies every act of understanding. In sensing a thing we sense it as something . And, "any act of understanding language involves an interplay of text context. The whole and the part give meaning to each other" (Snodgrass & Richard, 1997). Actually, this Theory commonly apply on the theoretical base of visualization in system operation, the “understanding” should be placed in the whole region, The region is the whole and the visualization language is the part. The area has a strong locality (Cooke, P., 1990) including conventional concept about the understanding. For example, the empirical influence brought by the "Pictographic" culture in China, they thinking of or seeing a shopping cart we they go online shopping , it must be equated with a symbol similar to a car. In the process of system operation, from left to right (from general to specific), from top to bottom (functional distribution to induction and balance), it is more of an intuitive thinking (Sun & Wang, 2002) . however,it is indeed different in Europe, the guidance to system processes and information is more straight forward as their think. This paper mainly uses comparative research method to take China and Europe as examples to analyze the impact of visualization in system operation in system operation processes and symbol understanding due to the cultural locality.

Hualan Gou, Xinbei Gong

Conference Proceedings

Human Machine Interface Design for Intelligent Vehicle Systems

With the advancement of technology, advanced technologies such as big data, internet and artificial intelligence have been applied to the automotive industry, and the importance of human-computer interaction interface in automotive design has become more and more prominent. In retrospect, traditional automobiles were mainly regarded as tools for traveling, and the interaction between drivers and automobiles was mostly limited to basic vehicle control. However, the needs of modern drivers have become more diversified, and human-computer interface design nowadays has a direct impact on driving safety and overall experience. Based on the driver's perspective, this paper provides an in-depth discussion on human-machine interface design and analyzes the major problems currently encountered by drivers in using intelligent vehicles, including complex interfaces, untimely or inaccurate information transfer, etc. By studying the driver's behavioral habits, psychological needs and special requirements in driving scenarios. Combined with the relevant theories of ergonomics, design psychology and other disciplines, this paper explores how to enhance the driver's user experience through more intelligent and humanized interaction interface design, help users obtain driving information more quickly and accurately, and meet the driver's needs for future automotive human-computer interaction.

Xinbei Gong, Hualan Gou

Conference Proceedings

Intelligent Process Control: The Case of Designing Predictive Service for Wastewater Treatment Plant

The way we carry out our industrial operations needs to be radically transformed to foster sustainable development. In addition, the integration of advanced automation and emergence of AI-based solutions is poised to revolutionize the role of human operators as well as the industrial landscape in process control in general. In this paper, we present a case study on designing and implementing a predictive AI-based service to the wastewater treatment plant of a carboard factory. The new service is aimed at providing an improved overview of the process as well as giving suggestions about the chemical dosing. We have conducted user interviews accompanied with a user experience questionnaire to study how the operators experience the new AI-based service. The results show the potential of intelligent technologies in process control but also highlight the importance of carefully considering the human technology interaction and the need for better integration of expert users’ experiences and knowledge into the AI system. It seems obvious that only human centric approach can lead to smooth and resilient human technology interaction and enhanced industrial operations.

Hanna Koskinen, Päivi Heikkilä, Mari Myllylä, Susanna Aromaa, Antero Karvonen

Conference Proceedings

AI-Supported Personas vs Conventional Personas: A comparative Study Based on The Views and Opinions of Designers

In product design, understanding the target user group, their habits, preferences, and likes is crucial for ensuring a product meets user needs. User research plays a vital role in the early stages of the design process. The persona method, developed by Alan Cooper, is a widely used technique in the design process where users are grouped based on real data and represented by fictional characters. Conventional persona creation relies on qualitative data and designer intuition, which can be time-consuming and prone to bias. This paper explores the use of AI-driven tools, specifically ChatGPT-4o and DALL-E3, to generate dynamic, data-driven personas, offering a more efficient and precise alternative. The study compares four conventional and four AI-supported personas for mobile music streaming apps both derived from interviews with 24 users. Ten product designers evaluated both persona types, with results indicating that AI-supported personas hold significant potential for enhancing user experience design. The findings demonstrate how AI can enable more adaptive, user-centric designs, bridging the gap between conventional methods and AI-supported approaches.

Ece Cinar Balci, Ekrem Cem Alppay

Conference Proceedings

The Role of Immersive Technologies in the Design of eVTOL Simulators

As the electric Vertical Take-Off and Landing (eVTOL) aircraft industry advances, the development of high-fidelity simulators becomes crucial to support pilot training, operational safety, and the integration of eVTOLs into urban air mobility (UAM) ecosystems. This paper explores the transformative role of immersive technologies—such as virtual reality (VR), augmented reality (AR), mixed reality (MR), and Simulated Air Traffic Control Environments (SATCE)—in the design and development of eVTOL simulators, focusing on the convergence of human factors and cutting-edge technological innovation. Combined with SATCE, immersive technologies enable realistic, dynamic training environments that simulate the unique flight characteristics and control interfaces of eVTOLs. SATCE, developed by companies like ASTi, U.S.A., provides a sophisticated simulation of air traffic control (ATC) interactions, allowing pilots to practice real-time communication and decision-making under complex traffic and airspace scenarios. This technology helps bridge the gap between traditional aircraft training and the distinct challenges posed by eVTOL operations in dense urban environments, enhancing pilot situational awareness and decision-making in highly dynamic and unpredictable contexts.This paper examines key case studies where VR, MR, AR, and SATCE have been applied in aviation training, including the implementation of SATCE systems by ASTi and the work of FAST-Group Aero in Germany, who have led the integration of immersive technologies into eVTOL and UAM simulator environments. These examples demonstrate how artificial intelligence-driven communication and immersive simulation transform eVTOL pilot training by offering a comprehensive training experience encompassing technical flight skills and communication with air traffic control, particularly in managing vertical lift, multi-axis control, and navigation through complex urban airspace. Additionally, we explore future trends in immersive technology and its applications in eVTOL simulator design, emphasizing creating adaptable, scalable solutions that align with evolving regulatory frameworks. As UAM continues to grow, there is an increasing need to address the human factors challenges of eVTOL operations, such as pilot workload, human-machine interaction, and emergency scenario management. Integrating immersive technologies and SATCE offers a significant opportunity to optimize these aspects, providing a safe, controlled, and engaging training environment. In conclusion, this paper proposes a human-centric approach to eVTOL simulator design, where immersive technologies and SATCE systems not only replicate real-world complexities but also enhance the learning experience, paving the way for safer and more efficient integration of eVTOLs into the airspace.

Dimitrios Ziakkas, Debra Henneberry

Conference Proceedings

Innovative Nanofiber Membrane Hydration Bladder for Camping: A Sustainable Approach to Lightweight, Portable, and Safe Water Storage

With the increasing popularity of outdoor activities, about 57 million people go camping every year in the United States alone, and they often face challenges in drinking and storing water in the wild. Traditional plastic or metal water storage containers usually have problems such as being too heavy, inconvenient to carry, and environmental pollution. These containers are not only inconvenient to carry, but also difficult to degrade after being discarded, causing long-term pollution to the environment. This study proposes to use a revolutionary ultra-lightweight and breathable nanofiber membrane to design a portable camping water bag to solve these problems. The nanofiber membrane is made of recyclable and bio-based materials, which not only has excellent waterproofness, elasticity and durability, but also has environmental sustainability. The high-density nanofiber membrane can provide excellent waterproof performance, making it very suitable for making portable water bags. In addition, reducing the density of the nanofiber membrane can give it a certain water filtration function, achieving basic water purification effects in outdoor environments. The material can also effectively prevent bacterial penetration, thereby avoiding water resource pollution and ensuring safe water storage in outdoor environments. This material can degrade in the natural environment, greatly reducing the impact on the ecological environment compared to traditional plastic products. The designed water bag has high waterproofness of 10,000 mm H2O, excellent air permeability of 25,000 g/m²/24hrs, and outstanding tensile strength. It can be easily folded for easy carrying and storage, allowing campers to store more water without increasing the carrying burden. A series of performance tests such as pressure resistance, tear resistance, and temperature resistance showed that the nanofiber membrane water bag demonstrated excellent functionality in a variety of outdoor environments. The results of the study indicate that nanofiber membranes have broad application prospects in the design of high-performance, environmentally friendly, and multifunctional camping equipment, which not only enhances the user experience but also minimizes environmental impact. Future research will further optimize the material properties and explore its wider application in outdoor equipment.

Ronghan Wang, Wenjing Li

Conference Proceedings

Wide-Angle Thermal Sensing for Personalized Climate Control: An Infrared Fisheye Camera Approach in Commuter Vehicles

Thermal comfort is a critical aspect of electric vehicle (EV) design, particularly in shared mobility scenarios where passengers with diverse comfort preferences frequently enter and exit. Current climate control systems are primarily reliant on traditional sensors such as those for temperature, sun load, air quality, etc. However, these systems are often unable to provide personalized thermal comfort in dynamic environments, especially in autonomous vehicles where passenger numbers, seating arrangements, and environmental conditions can change significantly. In this study, a novel solution is proposed, utilizing a single infrared (IR) fisheye camera to monitor and optimize thermal comfort across the entire vehicle cabin. The camera is used to provide a full 360-degree view of the vehicle interior, allowing simultaneous monitoring of postures, body temperature, heat dissipation, and environmental factors such as solar heat gain or cold air drafts. This approach enables the dynamic tracking of multiple passengers, ensuring that changes in occupancy and cabin conditions are accommodated in real time. While the focus of the study is placed on an autonomous electric commuter vehicle (AECV) developed at the Karlsruhe Institute of Technology and its partners, the approach is applicable to a range of other vehicles and transportation systems.To process the thermal data, machine learning and deep learning techniques are employed. Spatial features are extracted from the thermal images using convolutional neural networks, allowing patterns such as body temperature distribution and localized hot or cold zones to be identified. Additionally, temporal changes in passenger movement and cabin conditions are modeled using recurrent neural networks, or more specifically, long short-term memory networks, enabling the prediction of thermal preferences based on historical and real-time data. Training of these models is conducted on datasets that combine thermal imagery with contextual behavioral data, such as posture and gestures, detected by a standard fisheye camera in previous studies.The predictions generated by the system are designed to guide real-time HVAC adjustments to provide personalized comfort. For example, cooling is applied to areas where passengers are exposed to sunlight, while targeted heating is activated for those in cooler zones. Validation of the system is planned through controlled laboratory experiments and real-world trials in shared mobility scenarios. These evaluations will assess the ability of the system to monitor thermal comfort accurately, respond dynamically to changes in occupancy, and optimize energy usage when compared to traditional HVAC systems.This single-camera approach is designed to streamline design, reduce costs, and enable advanced thermal comfort systems in dynamic environments. While its primary focus is on optimizing thermal conditions in electric vehicles, the system also presents opportunities to address motion sickness, a common issue in autonomous vehicle passengers. Additionally, its potential applications extend beyond transportation, offering promising avenues in areas such as indoor heating and cooling.

Philipp Román, Eva Maria Knoch

Conference Proceedings

Ergonomic Evaluation Methods for Hand Exoskeleton Prototypes: A Scoping Study

Hand function is essential for daily activities, but neurological, muscular, and environmental limitations can impede hand mobility. Robotic hand exoskeletons offer promising assistance for these impairments, though a standardised evaluation method for their effectiveness is lacking. This study addresses this gap by conducting a scoping review to explore current ergonomic evaluation methods for hand exoskeleton prototypes. The primary objective is to identify and analyse the tests used to assess technical performance and user experience, aiming to establish a comprehensive framework for future assessments. A research question guided the research: “What ergonomic evaluation tests are applied to assess the performance and effectiveness of hand exoskeleton prototypes for assisting with daily tasks?” The review analysed diverse evaluation methods, including physiological, kinematic, and kinetic metrics, alongside subjective user surveys. Usability assessments evaluate safety, comfort, and overall experience, while biomechanical testing explores muscle activity and range of motion, with electromyography (EMG) used to compare muscle activity with and without exoskeleton support. The study emphasises the need for a comprehensive and standardised approach to evaluate hand exoskeletons, integrating technical performance and user experience metrics to ensure effective and user-friendly designs.

Rui Ribeiro, Celina Leão, Susana Costa, Vinícius Silva

Conference Proceedings

Shaping the Future of Physical Retail: Insights into Global Consumer Experiences

This study investigates the global relevance of 14 consumer experience guidelines originally developed in Brazil using the “Experience Compelling Map,” a Design Thinking tool applied to physical retail. By observing 30 retail locations across Tokyo, Osaka, Kyoto, and Seoul, this research explores how sensory stimuli, personalization, and technology shape the shopping journey in Asia's leading markets. Findings indicate strong parallels between Brazilian insights and Asian practices, with personalization emerging in over half of the observed sites and visual and auditory stimuli enhancing brand connection. These results suggest that while consumer experiences are influenced by cultural contexts, they increasingly reflect shared global expectations shaped by digital and sensory-driven engagement. This analysis underscores the importance of human-centered innovation in retail, supporting the theme of integrating human and intelligent systems to create immersive, emotionally resonant consumer experiences.

Paulo Eduardo Tonin, Elton Nickel

Conference Proceedings

Decoding Pet Signals: Bridging the Gap for Accurate Diagnoses

The global pet care market is booming, with pet owners increasingly seeking ways to understand and improve the well-being of their animal companions. This demand extends beyond domestic pets to working animals, such as those in law enforcement and the military, and even to livestock in the agriculture industry. Accurate and timely diagnosis of health issues is crucial in all these sectors, but traditional methods often rely on subjective observations and infrequent veterinary visits. This paper introduces a novel Internet of Things (IoT) platform designed to bridge this gap by providing continuous, objective monitoring of animal behavior and activity.Our platform employs a non-invasive, wearable device equipped with an array of sensors that capture physiological and movement data. This data is then processed using advanced machine learning algorithms to classify the animal's activity into predefined categories, such as resting, playing, eating, or exploring. By analyzing patterns and deviations in these activities, we construct a comprehensive "Activity Level Indicator" (ALI). This index provides a clear and quantifiable measure of the animal's overall well-being, categorizing them as normal, hyperactive, or lethargic.Furthermore, the collected data is visualized through an intuitive dashboard accessible to pet owners, trainers, and veterinarians. This dashboard provides valuable insights into the animal's daily routines, activity levels, and potential anomalies. For pet owners, this translates to a deeper understanding of their pet's needs and early detection of potential health concerns. For trainers, the platform offers data-driven feedback to optimize training programs and monitor progress. Veterinarians can leverage the platform to access objective data, aiding in diagnosis and treatment planning, and enabling remote monitoring of patients.This paper details the development and validation of the IoT platform, including the sensor technology, machine learning models, and dashboard design. We present results from a pilot study demonstrating the platform's effectiveness in accurately classifying animal activities and identifying deviations from normal behavior patterns. The potential applications and implications of this technology are discussed, highlighting its contribution to improving animal welfare across various domains, from enhancing the bond between pets and owners to revolutionizing animal healthcare in veterinary practice and the agriculture industry.

Rafael Pinho, Gustavo Tironi, Walléria Correia, Helouise Mattjie

Conference Proceedings

Enhancing Student Learning: The Impact of Continuous Metacognitive Monitoring Feedback in Location-Based Augmented Reality Environments

With the growing need for augmented reality (AR) technology, understanding and optimizing study behaviors in AR learning environments has become crucial. However, one major drawback of AR learning is the absence of effective feedback mechanisms for students. To overcome this challenge, we introduced metacognitive monitoring feedback. Additionally, we created a location-based AR learning environment utilizing a real-time indoor tracking system to further enhance student learning. This study focuses on the positive impact of metacognitive monitoring feedback in a location-based AR learning environment. Our hypothesis posits that regularly providing students with feedback on their metacognitive monitoring within this new AR learning system positively influences their metacognitive awareness. The study's findings confirm that frequent exposure to such feedback significantly enhances the Metacognitive Awareness Inventory (MAI) scores. Participants who received continuous feedback demonstrated a significant increase in MAI scores compared to those who received feedback only once after the lecture. This improvement is achieved by influencing student calibration and directly enhancing their metacognitive awareness.

Sara Mostowfi, Jung Hyup Kim, Ching-yun Yu, Siddarth Mohanty, Fang Wang, Danielle Oprean, Kangwon Seo

Conference Proceedings

Analysis of Research Progress and Trends in Extended Reality Therapy Based on Bibliometrics

XR technology has provided a great deal of academic research in treating and improving physical and mental diseases. In this paper, 315 articles related to "Extended Reality" and "Art Therapy" collected by Web of Science were retrieved by bibliometric method, and the research status of this research field was analyzed visually by combining Citespace and VOSviewer, and the future trend was predicted. It references the XR healing system in health research direction, discipline frontier, research gaps, etc. The results showed an increasing trend in the amount of literature on the cable range. The United States, Germany, and Italy are leading in research, but the cooperation between institutions could be closer. Finally, from the technical point of view, XR therapy's research hot spots, opportunities and challenges are evaluated. From the interdisciplinary and artistic point of view, the artistry of the XR therapy system and XR art therapy are distinguished.

Qi Xiao

Conference Proceedings

Digital Teaching to Develop Soft Skills – A User-Centered Approach

The development of soft skills, including teamwork, communication, critical thinking, and emotional intelligence, has become essential in the modern workplace. Despite this growing need, conventional teaching methods in higher education often fail to prioritize these competencies, favoring traditional lecture-based approaches. This paper addresses the gap by presenting a digital project management platform designed to enhance soft skills among university students through practical, team-based learning.Following a user-centered design process, the platform was developed using the ADDIE (Analysis, Design, Development, Implementation, Evaluation) model, which structured its creation and evaluation. Semi-structured interviews with faculty and students informed the design of user personas, which were key in aligning the platform's functionality with users’ needs. Central to the platform is a Kanban board that facilitates project management and encourages students to apply soft skills in realistic scenarios, such as organizing tasks, collaborating with peers, and communicating effectively. Additional features support group interaction and provide educators with tools to guide and assess students’ progress.Digital teaching offers distinct benefits for skill development, including greater accessibility and flexibility for learners. By allowing self-paced learning and access from any location, the platform supports personalized experiences tailored to individual preferences. Furthermore, its interactive elements, such as gamified components and simulations, promote active learning and provide students with a safe space to practice and refine their soft skills. The digital format also allows for scalability, enabling widespread adoption and cost-effective implementation across diverse educational contexts.The platform’s usability and impact will be assessed through an eye-tracking study to observe user interaction patterns. This study will help optimize design elements and ensure the platform effectively supports learning objectives. Technically, the platform consists of a client-side application built with React and D3.js for visualizations, and a server-side component that uses Node.js and MongoDB for data management. This architecture supports a seamless and user-friendly experience, enabling students to engage meaningfully with the content.In conclusion, this paper proposes a practical strategy for integrating soft skills training into university education through digital means. By leveraging a user-centered design and modern digital tools, the platform offers a dynamic, engaging learning environment that meets the demands of both academia and the workforce. This approach not only enhances students' readiness for future employment in a volatile, uncertain, complex, and ambiguous (VUCA) world but also encourages the development of essential life skills, bridging the gap between academic knowledge and practical, real-world application.

Jonas Bender, Klaus Bengler

Conference Proceedings

Toward Motivation-igniting Society

The current Industrial Society was introduced by the Industrial Revolution, which is developed to satisfy our material needs. But what characterized humans is we changed four legs to two legs and started to walk. Thus, we were By escaping the constraints of having four legs, that is, the situation in which the center of gravity of the body is fixed, the center of gravity of the body can now be freely moved, which means that the body balance can now be freely selected. Thus, we became able to move the two legs, which had become hands, freely, and unlike when we had four legs and was only able to engage in activities that suited the current environment and situation, it was now able to create the environment and situation that it desired. Thus, it became possible to dream the future and we made efforts to make our dreams come true. But what we pursued was to satisfy our material needs. When we were four-legged, we could not satisfy our material needs such as food and lodging as we wish. In four-leg days, we were only able to take measures within the current situation. But by standing up and walking, we are now able to take diverse actions As we became free to move and it became easier to satisfy our material needs, our material needs became increasingly sophisticated. However, as Maslow pointed out, humans are not satisfied with just the fulfillment of their material needs, and over time they begin to desire the satisfaction of their spiritual needs, and as he pointed out, ultimately we aim for self- actualization.Deci and Ryan proposed Self-Determination Theory and they pointed out that we get the maximum happiness and the feeling of achievement, when we achieve the job in our own way, which is internally motivated. In the Industrial Society product matters, so productivity and product performance were important. Therefore, we introduced mass production and we paid our efforts to improve product performance.Industrial society satisfied our material needs but not mental needs, and as everybody knows, society shifts from one to another. The industrial society is coming to an end, and various problems emerge. The biggest problem is excessive energy consumption. We cannot keep supplying it. AI has been discussed as a solution, but AI also consumes a huge amount of energy.Another big problem is aging is progressing rapidly in the developed countries. In the developing countries, population is increasing, but they have a problem of literacy, so we cannot secure workforce.Thus, we need to design and develop a new society for the next generation.The important point in the above discussion is how we can make our life self-sustaing and make our dreams come true. In the current product- centric ndustrial Society, objective quantification is important. But to achieve Self-actualization, what is needed is subjectiveness. It is qualitative, but we need to make decisions. It is a matter of strategy. The current society looks for better techniques.To express it another way, our society now is running on Euclidean approach. But next society calls for Non-Euclidean approach. So, we introduced Mahalanobis Distance and using this measure, we classified patterns, which we used for detecting emotion from face and succeeded in immediate detection. In short, it enables us to look forward to tomorrow with great enthusiasm, hoping that things will progress even further. Therefore, even the elderly can live looking forward to tomorrow.

Shuichi Fukuda

Conference Proceedings

The impact of Application icon design aesthetics on user downloads

With the rapid development of the Internet, understanding the popularity of APP icon is crucial for designers and R & D personnel. People 's daily life, work and entertainment are inseparable from downloading APP application software. People pay more and more attention to the design effect and experience effect of mobile products. At present, the research on APP icon mainly focuses on program operation and text attributes, and less attention is paid to the design aesthetics of APP icon,how to make users feel the attraction of app itself to users in addition to considering the necessity of app when downloading app icon is a problem that needs to be studied. This paper uses literature analysis, case analysis and interview to study the impact of APP icon design aesthetics on user downloads. The researchers collected the top three APPs of 12 different types of APPs from the seven-wheat data download list, and used the theory of interface design to analyze their design aesthetics commonalities from the perspectives of color, element complexity and symmetry, and proposed four hypothetical questions. Finally, through the interview method, it is concluded that app icon is more popular with users if it follows the principle of conciseness and clarity, the principle of multiple colors, the principle of multiple colors, the principle of balanced U-shaped and the principle of slight complexity, and the download volume will increase significantly. It is hoped that through the research of this paper, the overall design level of APP icon will be further improved.

Yifang Wang

Conference Proceedings

Integrating Design processes and Intelligent systems within supply chain digitalization, Two case studies in Made in Italy manufacturing.

The concept of "Made in Italy" refers to the production of goods in Italy, characterized by a strong association with quality, craftsmanship, and Italian design. In recent years, digitalization has played a crucial role in the evolution of this sector, becoming essential for maintaining international competitiveness and influencing various aspects, as highlighted in the Confindustria Report ‘Digitalization and Innovation in the Italian Manufacturing Sector’ and the European Commission’s Joint Research Centre’s study ‘The impact of digital transformation on Italian manufacturing SMEs’. The integration of intelligent systems into design and manufacturing processes is revolutionizing the industry, promoting greater efficiency, flexibility, and product customization. The National Industry 4.0 Plan, promoted by the Ministry of Economic Development, aims to transform the Italian manufacturing sector through digitalization along four main lines: i) Innovative investments, ii) Skills, iii) Enabling infrastructures, iv) Public support. The plan seeks to enhance the competitiveness of Italian companies in international markets and create an innovation ecosystem. The adoption of technologies such as Industry 4.0, the Internet of Things (IoT), blockchain, Big Data Analytics and integration with additive manufacturing systems has enabled Italian companies to improve product efficiency, quality, and sustainability, while also allowing continuous monitoring and real-time adaptation of production (Goretti et al., 2020; Galli, 2021; Terenzi & Benelli, 2021; Bianchi, 2022; Lombardi & Rinaldi, 2023; Terenzi & Goretti, 2024). Furthermore, the use of artificial intelligence (AI), machine learning, and cyber-physical systems facilitates advanced automation and optimization of design and production processes, reducing time and costs.Simultaneously, the integration of digital archives with manufacturing taxonomies is crucial for organizing and analyzing information in the industrial sector. Digital archives enable the cataloging and management of vast amounts of data related to production processes, materials, and finished products, facilitating traceability and the management of corporate knowledge (Smith & Johnson, 2021; Brown, 2022; Keller, 2023; Wang & Gao, 2022; Zhang & Tao, 2023).The case studies presented demonstrate how these transformations disruptively impact creative processes and design thinking methodologies, bridging the gap between design expertise and production processes. The research introduces a first case study that integrates digital modeling and robotic processes in high-craftsmanship furniture production. A second case study documents the design of a parametric sustainable packaging system through the exploitation of constrained generative AI and product digitization tools. We can thus assert that the digital transition requires significant investments and continuous training of human capital, both in production and in design processes. The research, through the presented case studies, aims to define emerging processes and skills required by Italian high-craftsmanship production districts, which can be developed trans-disciplinarily between historical manufacturing and design knowledge and advanced technologies. By highlighting challenges and opportunities, it is possible to underscore that, while there are positive signs in the adoption of digital technologies, many companies, particularly SMEs, struggle to keep pace with these changes. The main barriers include a lack of digital skills and high investment costs.

Jurji Filieri, Gabriele Goretti, Benedetta Terenzi

Conference Proceedings

Advanced Computational Modeling and Simulation for Immersive Virtual Reality Experiences: Preserving Hong Kong's Traditional Handicrafts

This research investigates the preservation of Hong Kong’s traditional handicrafts, specifically porcelain paintings (Guangcai), through advanced computational modeling and Cave Automatic Virtual Environment (CAVE) systems. The study develops an interactive digital platform that transforms traditional artistic expression into contemporary digital experiences by combining physics-based simulation, haptic feedback, and immersive narratives within a Virtual Reality (VR) framework. The methodology consists of several critical modeling and simulation components, including data digitalization, rendering optimization, real-time performance and interactive solutions, creating an essential framework for cultural heritage preservation in various fields while demonstrating the potential of computational modeling in bridging traditional handicrafts with modern technology.

Lai Man Tin, Xiaoqiao Li, Tsz Fung Lam

Conference Proceedings

Modeling the emergence of collaborationism

This paper explores the complex phenomenon of collaborationism, particularly in the context of Russian aggression against Ukraine. It examines the socio-political, economic, and ideological factors that contribute to an individual's propensity to collaborate with occupying forces. By leveraging extensive data collected in Ukraine, the study proposes a novel approach using neural networks to model the emergence of collaborationism. This approach aims to identify potential collaborators by analyzing indicators such as material well-being, ideological beliefs, and moral qualities. The research highlights the importance of understanding the interplay between pre-existing conditions and trigger events, offering predictive models that can be applied across Europe to enhance national and international security frameworks. The findings underscore the need for comprehensive strategies to address both the symptoms and root causes of collaborationism, thereby strengthening resilience against internal and external threats.

Maryna Zharikova, Stefan Pickl

Conference Proceedings

Automatic Creation of Assembly Instructions by Using Retrieval Augmented Generation

The application of Large Language Models (LLMs) for the automated generation of assembly instructions shows significant potential for improving work preparation in production processes. However, challenges remain regarding the overall information quality and precision of the generated instructions. In light of these challenges, this study explores how the information quality of automatically generated assembly instructions can be enhanced through the targeted provision of structured input data, such as Assembly and Quantity BOMs (Bills of Materials), as well as the use of optimized prompt chaining techniques. The methodology employs ChatGPT-4o in combination with Retrieval Augmented Generation (RAG) within the Microsoft Azure environment. The results demonstrate that structured data inputs, particularly the use of Assembly BOMs with defined Tool-to-Component relations, significantly improve the precision and relevance of the generated instructions. Despite these advancements, achieving consistent information quality remains a barrier to broader practical implementation. Therefore, feedback loops should be integrated into the assembly instruction generation process to ensure continuous refinement and reliability. Future research should investigate the use of RAG or similar frameworks, focusing on optimizing data structures and implementing feedback mechanisms to enhance the automated generation of assembly instructions.

Robin Herbort, Dominik Green, Sven Hinrichsen

Conference Proceedings

Project Eskalator: Navigating the Innovation-Funding Maze in Small and medium-sized enterprises

Small and medium-sized enterprises (SMEs) face significant challenges in navigating the complex landscape of innovation and funding. This paper presents Project Eskalator, an integrated framework designed to bridge the gap between innovation management and funding strategies for SMEs. Through a mixed-methods approach involving surveys, case studies, and expert interviews across diverse industry sectors, we examined the interplay between innovation potential identification, agile business model development, and strategic funding acquisition. Our findings reveal that SMEs adopting an integrated approach to innovation and funding demonstrate higher rates of successful product launches, improved market adaptation, and enhanced resilience during economic uncertainties. The framework emphasizes adaptive business models, rapid prototyping, and lean methodologies suitable for resource-constrained environments. Additionally, we found that SMEs developing concise, compelling narratives around their innovative ideas were significantly more successful in securing stakeholder buy-in and accessing diverse funding sources. Project Eskalator represents a paradigm shift in how SMEs approach the dual challenges of innovation and funding, enabling them to break the paralysis of indecision and navigate the complex innovation-funding landscape with greater confidence and success.

Robin Bakir, Maximilian Müller, Dennis Bakir

Conference Proceedings

Designing Adaptive Immersive Therapeutic Spaces Using Convolutional Neural Networks for Community-Based Elderly Care

As global aging accelerates, it is projected that by 2050, over 22% of the global population will be aged 60 or older. In this context, promoting healthy aging is crucial, with mental health challenges among the elderly receiving increasing attention. Art therapy has been recognized as an effective intervention to maintain physiological, cognitive, and social functions in older adults, significantly improving emotional well-being and social engagement. However, traditional art therapy faces limitations in scalability and assessment accuracy. Digital art therapy, with its real-time adaptability and sustainability, offers promising potential for expanding mental health interventions. This study focuses on Wuhan, China, surveyed and interviewed 2,000 elderly individuals to explore psychological health factors. Results indicate that individuals aged 60-69 exhibit significantly higher levels of depression and anxiety compared to those aged 50-59, with depression (M60-69=12.231>6.272,p<.001) and anxiety (M60-69=13.837>6.441,p<.001). High social participation was found to significantly enhance mental health (p<.001), with most respondents holding favorable views on community-based art therapy activities. To address these findings, this research proposes adaptive immersive therapeutic spaces for elderly care, integrating sensor and projection technologies. Using Convolutional Neural Networks (CNNs), the system analyzes real-time behavioral and emotional data, dynamically adjusting the visual and auditory elements to match the users' emotional states. A follow-up survey with 1,897 participants confirmed the feasibility of these spaces, with the majority anticipating improved emotional regulation. This study contributes to the advancement of mental health interventions for the elderly, offering novel perspectives for future research and practice.

Han Zhang, Siqi Zhu, Yue Fang

Conference Proceedings

Project Ikarus: Catalyzing Digital Transformation in SMEs through Adaptive Education and AI Integration

Project Ikarus represents a pioneering initiative in artificial intelligence and digital transformation education, specifically tailored to meet the needs of small and medium-sized enterprises (SMEs), IT freelancers, consultants, and professionals across various sectors. This innovative AI academy "Fortschrittschmiede-Mittelstand" addresses the growing demand for practical digital literacy in these fields by offering a comprehensive curriculum that bridges the gap between theoretical concepts and their real-world applications. The platform's educational framework is built upon a series of professional online modules, meticulously crafted to adapt to the individual needs of participants through the implementation of agile methodologies and adaptive learning algorithms. This approach implies specific learning paths and ensures that learners from diverse professional backgrounds can effectively engage with and master digital transformation concepts and techniques directly applicable to their industries.

Robin Bakir, Maximilian Müller, Dennis Bakir, Benedikt Kippschnieder

Conference Proceedings

Usability Analysis of Gesture Interaction in Virtual Cycling Games Based on Flow Theory

Virtual cycling has been increasingly implemented across various fields, including healthcare, fitness and gaming, providing a more immersive and engaging exercise experience. The authenticity of virtual cycling games relies on effective human-computer interaction, with gesture interaction demonstrating significant potential in virtual fitness applications. Currently, these games primarily utilize traditional controller interactions, requiring users to stop cycling, which results in low operational efficiency and interruptions in movement continuity. This study aims to explore user operational needs in virtual cycling games and to compare the efficacy of gesture interaction with controller interaction, thereby validating the advantages of gesture interaction. We developed a virtual cycling game using Unreal Engine, incorporating both interaction modes, and established an experimental platform to record players' speed, heart rate, and other physiological data in real time, as well as to gather user experience assessments from subjects following the experiment. The findings indicate that gesture interaction significantly enhances operational efficiency and facilitates continuity in cycling, thereby improving training outcomes. Additionally, gesture interaction fosters a more immersive flow experience. Therefore, gesture interaction in virtual fitness games can substantially elevate both user experience and exercise efficiency.

Zhenhua Zheng, Qi Wang, Bo Yan, Houren Zhou, Ruofei Li

Conference Proceedings

Exploring the Influence of Environmental Context on Visual Attention and Spatial Perception in Virtual Reality

Spatial perception plays a fundamental role in how individuals navigate and interact with their environments, and visual attention, particularly fixation patterns and durations, is a key component of this process. This study examines how fixation behaviors vary across different environmental contexts using Distance Perception (DP) and Size Perception (SP) tests conducted in virtual reality (VR). Participants were placed in three distinct environments: a cityscape with familiar landmarks (Control Group), a simulated Martian surface with limited spatial cues (Experiment Group 1), and an outer space simulation devoid of recognizable reference points (Experiment Group 2). Eye-tracking data captured variations in fixation counts and durations to explore how these factors are influenced by environmental familiarity and complexity. In the DP test, participants demonstrated the highest fixation counts in the Control Group, with an average of 24.59 fixations, compared to 21.25 in EG1 and 22.19 in EG2. The analysis suggested significant shifts in visual attention strategies when participants moved from the familiar cityscape setting (CG) to EG2, where fixation counts dropped notably. Between the CG and EG2, patterns were more comparable, with similar fixation counts suggesting overlapping visual engagement demands. Additionally, fixation durations were longest in the CG, averaging 4.80 seconds, indicating sustained engagement with the stimuli. In contrast, durations in the EG1 (4.17 seconds) and EG2 (4.23 seconds) environments were shorter, reflecting a reduced level of sustained focus in unfamiliar or visually sparse conditions. The SP test provided further insights into how participants directed their attention across objects within each environment. Participants in the Control Group exhibited the highest fixation frequencies, with an average of 28.34 fixations per trials, compared to 22.67 fixations in Experiment Group 1 and 23.12 fixations in Experiment Group 2. Alongside the increased fixation frequency, the Control Group also demonstrated longer average fixation durations when interacting with objects, indicating stronger engagement and familiarity with the environment. A clear relationship emerged between fixation counts and durations, suggesting that objects attracting more frequent gazes also held participants’ attention for longer periods. Changes in fixation behaviors were most pronounced when comparing the Control Group to the Martian environment (EG1), highlighting the cognitive adjustments required when transitioning to less familiar settings. These findings illustrate how environmental context influences visual attention patterns and, by extension, spatial perception. Environments with familiar visual landmarks, such as the cityscape, supported greater fixation counts and longer durations, reflecting enhanced cognitive engagement and processing efficiency. In contrast, the Martian and space environments (Eg1 and EG2), characterized by reduced or unfamiliar spatial cues, required participants to adopt different visual strategies, leading to altered fixation patterns. This research highlights the importance of environmental familiarity in influencing visual attention and spatial perception. It also emphasizes the importance of eye-tracking data in designing effective training and operational environments, especially for fields like space exploration, where adapting to unfamiliar conditions is crucial. Future research should explore the effects of demographic factors and task complexity to create more targeted strategies for improving spatial performance in demanding contexts.

Faezeh Salehi, Manish Dixit

Conference Proceedings

Experimental Evaluation of Pilot Visual Response To Understand Situational Awareness While Controlling Multiple UAVs

This work presents the results of an experiment examining a pilot’s situational awareness as they are tasked with controlling increasing numbers of unmanned vehicles. The primary metric for determining situational awareness was the pilot’s gaze response time to on-line queries about the location of assets under control. The gaze response times are evaluated to determine the impact of additional drones on the pilot’s situational awareness. We also document specific types of degraded situational awareness observed throughout the experiment. Finally, we identify challenges encountered and suggest future work that could provide deeper insight into the research questions addressed here.

Tyler Shillig, Axel Schulte, Karl Tschurtschenthaler

Conference Proceedings