Human Interaction and Emerging Technologies (IHIET 2024)

book-cover

Editors: Tareq Ahram, Luca Casarotto, Pietro Costa

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2024

ISBN: 978-1-964867-33-5

DOI: 10.54941/ahfe1005457

Articles

Autonomy at the Crossroads: Knowledge Workers Teamed with Intelligent Machines: A Qualitative Systematic Review

This study aims to identify risks in adopting artificial intelligence (AI) for organizational decision-making by examining empirical studies. AI, is increasingly applied to automate tasks and decisions which were traditionally made by humans, posing challenges to sense of autonomy. Design/methodology – A total of 28 empirical studies were selected using predefined inclusion and exclusion criteria. To this end, this research systematically explored the processes of inquiry, identification, selection, critical appraisal, and the synthesis of empirical studies. This study is undertaken to address the following primary inquiries: (1) What is the direction of the observed effect? (2) What is the magnitude of the effect within the inclusion criteria? (3) Does the effect exhibit a consistent pattern across the spectrum of studies encompassed in the analysis? (4) What is the level of evidentiary robustness underlying the discovered effect? Findings – This content analysis interpretated within task-technology fit (TTF) model revealed that AI adoption represents a promising outlook for the future of human-AI teams. Anchoring on reliable data, this qualitative systematic review informs knowledge workers and leaders on adoption of AI systems and how it positively influences their working processes. Contributions/value – This research conducted a structured analysis to reveal the gap between collective perception of AI adoption, and what leaders and knowledge workers have experienced in relying on AI systems. AI tools are becoming more autonomous therefore a true representation of human-AI team interaction must be displayed. By uncovering the diverse approaches of leaders and the reactions of knowledge workers to AI integration, this paper contributes to a deeper understanding of the evolving landscape of working in the age of AI. The provided insights can assist organizations in harnessing the potential of AI while maintaining a healthy balance of autonomy within their domain.KEYWORDS Leadership, AI-Driven Decisions, Problem-Solving, Digital Autonomy, Hybrid intelligence, Human-Machine Teams, Qualitative Systematic Literature Review.

Mahdis Smith, Luke Houghton, Carla Riverola, Ali Intezari
Open Access
Article
Conference Proceedings

Ergonomics and Collaborative Robotics: The synergy to prevent workload in industrial assembly tasks

The synergy between Ergonomics and Collaborative Robotics represents a crucial and emergent framework to achieve innovative and human-centered assembly workstations. Among the various I4.0 technologies, Human-Robot Collaboration (HRC) has emerged as a cutting-edge solution to address ergonomic challenges while enhancing manufacturing productivity. Despite this potential, there is a significant gap in empirical studies on the implementation of these technologies, particularly in the context of integrating ergonomic requirements. This study aims to present real-world applications of HRC in assembly tasks performed by workers with musculoskeletal complaints, as well as to indicate future research challenges in this field. Our previous work involved the digital transformation of two real-industry workstations, mitigating musculoskeletal risk factors by the HRC implementation according to a human-centered design. During this work, ergonomic assessments of the workstations before and after the introduction of HRC were performed (e.g. the application of Inertial Measurement Units to quantify the Rapid Upper Limb Assessment score). Key performance indicators, such as production rates, were measured through time studies and direct observation. To gather additional insights into workers' well-being, questionnaires were applied. This multi-method approach revealed that the workstations with HRC resulted in (i) reduced production costs, (ii) improved ergonomic conditions, and (iii) enhanced worker well-being. Based on these previous findings, our current research is focused on creating a flexible integrated robotic system capable of executing a shared human-robot task plan and reasoning about the working conditions. This system will integrate a real-time ergonomics assessment system to track and evaluate postures and other physical indicators and extrapolate corrective measures. In our research, we intend to highlight that this synergy between Ergonomics and Collaborative Robotics underscores the continuous improvement of industrial processes while ensuring sustainable productivity and worker well-being.

Ana Colim, Estela Bicho, André Cardoso, Carla Alves, Amin Salimi, Duarte Fernandes, Nuno Sousa, Nélson Costa, Paula Carneiro, Sérgio Monteiro, Luís Louro, João Gaspar Cunha, Pedro Arezes
Open Access
Article
Conference Proceedings

How many Robots is too many? Findings about Single-Human Multiple-Robot Systems

Mobile robots are increasingly being used to perform tasks that are difficult for humans to reach. Due to their high degree of autonomy, a human can control multiple robots through a graphical user interface, which is called one-human multiple-robot (SHMR) system. However, information about them is scarce. The current literature review synthesizes the features of SHMR systems related to safety and health at work for the operator and system performance. A total of 658 records were identified through an exploratory search since 2000, and 35 were selected to meet the inclusion criteria. The characteristics were consolidated and provide valuable insights about field of application, team composition, and reported outcomes. Future research can focus on exploring these systems in industries that have not yet been studied, or it can examine the impact of individual operator characteristics on these systems.

Estefany Rey-becerra, Sascha Wischniewski
Open Access
Article
Conference Proceedings

Robotisation of work - what are the experiences among employees in automotive industry company in the Czech republic

The appearance of new technologies, such as advanced robotic systems that can closely interact with humans, has led to a revival of the debate on the automation potential of jobs and tasks as well as their consequences on occupational safety and health (OSH). Especially for the automation of physical tasks, industrial robots appear most frequently. The possible associated health effects for the employees has not yet been fully explored. Inadequate robotic task allocation and design can be mostly associated with psychosocial risks like reduced wellbeing, emotional exhaustion, nervousness or irritability. Mechanical robotic failures may cause physical harm. Also the prevalence of information and communication technologies (ICT) is growing rapidly. The digital stress may negatively affect individual physiological wellbeing, user satisfaction or individual performance at work.Purpose: The aim of the qualitative study was to describe experiences with introduction of robots into work activities among employees in automotive industry.Methods: We interviewed 8 employees of automotive industry company in the Czech Republic using a semi-structured guide and subjected the interviews to qualitative content analysis.Results: We summarized 9 themes: General perception; Change; Fear; Problems; Support (training, current support); Social relations and communication; Characteristics of the employee; Physical health and Mental health (stress, fatigue, cognitive function: memory and attention, abuse.Conclusion: Findings from this study suggest the importance of support in terms of adequate and easy to understand training and also supportive leadership. The characteristics of the employee who is collaborating and cooperating with robots in the studied company was unique – not highly educated but very skilled and proactive. It also seems that company culture and managerial support are necessary to create a healthy and successful organization.Supported by Ministery of Health, Czech rep. - RVO (NIPH, 75010330)

Vladimira Lipsova, Viola Pirova, Jana Murza, Ivana Libalova
Open Access
Article
Conference Proceedings

Empirical analysis of social implications during the development of automated driving

This article presents and discusses studies and their first results on the development of an empirical method for the investigation of social implications caused by automated driving. The basic research project KARLI is funded by the German Federal Ministry for Economic Affairs and Climate Action. One of the objectives of KARLI is to develop a methodological approach for the empirical identification and evaluation of social implications expected in different phases of the user-centred development of automated driving. In KARLI, the empirical analysis of social implications is integrated in different studies throughout an iterative user-centred development process of interaction concepts for automated driving (SAE 0-4). In our definition, social implications address the consequences of a technological development for social structures or processes, as well as the development-related prerequisites necessary for a desired social target state. The empirical identification of possible social implications is conducted in two studies, using a qualitative survey (N = 12) and open-ended questions as part of an online survey (N = 35). Based on the results, a first draft of a questionnaire with closed questions is designed to assess the social implications previously identified. In a forthcoming third study, a VR simulation to test three different concepts to promote level-compliant driver behaviour, the social implications are assessed using the designed questionnaire. In addition, further expected social implications are elicited through open-ended questions. The study runs from the end of March to May 2024 with participants between 35 and 45 years of age (N = 95). According to the results, the statements about probable social implications are well answerable by car users, but the validity of the forecast given by the users remains unclear. That for, for a valid estimation of social implications a combination of users and expert’s perspectives seems to be helpful.

Nuria Brüggemann, Sebastian Preis, Heinrich Claus Arnd Engeln
Open Access
Article
Conference Proceedings

The Best Fit Framework for Human Computer Interaction Research ‒ Is it possible?

The Best Fit Framework, originally proposed by Carroll et al. (2013) to synthesize qualitative data has been successful to conduct a review of the literature to produce models or frameworks for decision making and health behaviours. While successful in health behaviours, it has not been implemented within Human-Computer Interaction before. This paper aims to convey knowledge, experiences, and recommendations towards the use of the Best Fit Framework to synthesize data in the field of Human-Computer Interaction. The Best Fit Framework involves various stages. The first two stages run simultaneously and involve identifying relevant frameworks, models, or theories, using the BeHEMoTh (Behaviour of Interests; Health Context; Exclusions; Models, Theories, Frameworks) search technique, and to identify relevant primary research studies with qualitative evidence, using the SPIDER (Setting/Population; Phenomenon of Interest; Design, Evaluation, Research) search technique. The selected theories, frameworks, or models are then reduced to key elements and used as themes in the new framework. These themes are interpreted and compared to new or similar types of themes across the literature, found with the SPIDER technique. New identified themes are incorporated to create an updated framework. After the framework is created, it is tested as a final part of the synthesis process. To apply the Best Fit Framework in the field of Human-Computer Interaction, the researchers expanded the context of BeHEMoTh. The researchers sought to also include the prevention or minimization of Cybersickness. The inclusion of quantitative primary research studies as part of the SPIDER technique was added, as the original SPIDER technique focused on qualitative studies which assisted in expanding the pool of primary research studies. The last change addressed how the framework synthesis was tested. Rather than only revisiting evidence to create and explore relationships, the researchers evaluated as part of the newly created CyPVICS framework in a real-world case study to determine validity. The case study compared the usability and user experience of two immersive Virtual Reality navigation methods, namely touch controllers vs. omnidirectional treadmill, in the training of nursing students. In conclusion, the Best Fit Framework proved to be adaptable and useful in Human-Computer Interaction research.

Benjamin Botha, Lizette De Wet
Open Access
Article
Conference Proceedings

A Human Centric Design Approach for Future Human-AI Teams in Aviation

Human Factors and Aviation have been effective partners for decades, with systematic research leading to guidance and regulations on cockpit design, air traffic control display and interaction design, fatigue management and crew resource management, all of which have helped aviation maintain its record as the safest mode of transportation. The introduction of Artificial Intelligence (AI) in aviation has already begun, with Machine Learning systems supporting aviation workers in a number of areas. But so far, such AI additions can be seen as 'just more automation', as the human - whether pilot or air traffic controller - remains very much in command and control, maintaining situation awareness and being the principal safety barrier against accidents. With the advent of future AI systems likely to appear in the next decade, this is likely to change. AI systems are envisaged, and already being researched, that will have a higher degree of autonomy. A collaborative relationship is foreseen - generically known as Human-AI Teaming - in which the human will 'partner' with 'Intelligent Assistants'. This may include the AI deciding what to do and executing its own tasks, negotiating with the human crew, and even reconsidering its goals as part of the team. Human-AI Teaming raises a host of questions and challenges for Human Factors, such as how to achieve trust between human and AI, how to achieve satisfactory 'explainability' functions in the AI so the human can understand its advice and choices, as well as designing means of human-AI interaction, whether visual, verbal or gestural. An overriding question, however, is how to ensure that the AI design remains human centric, so that the human can still maintain their safety function and an overview of system performance, able to detect and step in if the AI goes wrong or finds it is out of its depth. Given the prospect of such advanced human-AI teaming scenarios, Human Factors will need to raise its game to assure human centricity of aviation systems design.As a first step towards preparing Human Factors for Human-AI teaming (HAT), the European HAIKU project has developed a provisional methodology and applied it to several 'use cases'. These use cases involve AI support in emergencies to a single pilot in the cockpit, AI support to flight crew who have to deviate to a different airport, AI support to remote tower controllers in dealing with arriving and departing aircraft, and an executive manager of pilot-less drone and sky-taxi traffic in urban environments. These four use cases vary in terms of their AI autonomy, and so are a reasonable test-bed for applying new Human Factors approaches.A six-step Human Factors process to designing human-centric HAT systems has been developed:Task AnalysisHuman-AI Teaming RequirementsHuman HAZOPHuman-in-the-loop SimulationsTraining & Operational Readiness TestingMonitoring, Adapting and LearningThe paper will focus mainly on the first three steps, in the context of the use cases, highlighting the novel issues found, e.g. relating to different explainability requirements depending on the AI's function, interaction design considerations, and training requirements that go beyond what is normally required. In particular, the approach monitors subtle shifts that can occur in the role and responsibilities of the human operator, which helps determine whether the system is in danger of becoming less human centric in nature, and identifying what the safety-related consequences could be.:

Barry Kirwan, Roberto Venditti, Nikolas Giampaolo, Miguel Villegas Sánchez
Open Access
Article
Conference Proceedings

Analysis and Interview Survey to Detect Subjective Fatigue and Accident risk of Truck Drivers

[Methods] In this study, interview survey and analysis were conducted with the aim of detecting accident risk from subjective health data of drivers. For interview survey, we observed time-series changes in VAS for 1956 individuals over a year and selected 11 drivers who showed a significant worsening of subjective health. The 11 drivers were asked two types of questions. The first was, "Are there any factors that you are aware of about the period of time during which you showed significant worsening?" The second was, "What factors do you think are present that could have a dangerous effect on your driving?" The Analysis phase of the study examined whether the use of subjective health information and additional information would be useful in detecting accident risk. From the first question, we defined four patterns of VAS worsening trends and analyzed the relationships between these patterns and accident risk. From the second question, the index "change in the time of work start" was derived as a factor that many drivers consider dangerous. We then analyzed the correlation between this new index and the near-miss rate. [Results] for the relationship between VAS and accident risk, it was found that two of the four VAS risk patterns had a significant negative correlation with the rate of near-misses. Furthermore, analysis of the relationship between “change in the time of work start” and the accident risk revealed a significant negative correlation when the absolute value of “change in the time of work start” was within ±6 hours. This means that the rate of near-misses increases when the workday starts earlier than the previous day. [Conclusion] To detect a hazard leading to a driving near-miss with the VAS data alone, the worsening would have to continue for long time over 4 or 8 weeks. However, the newly discovered convince indicator "change in the time of work start" is a feature with a short span, and its addition to the VAS and accident risk analysis may improve the accuracy of health risk detection.

Nao Ito, Takeshi Tanaka, Yun Li, Shunsuke Minusa, Hiroyuki Kuriyama
Open Access
Article
Conference Proceedings

Revolutionizing Automotive Industry for Servicing An Autonomous Adaptive Lift System

The automotive industry stands at the cusp of a transformative innovation with the development of an autonomous adaptive lift system designed to revolutionize vehicle servicing. Traditional automotive lifts require manual adjustments to fit various car sizes and positions, often leading to inefficiencies and safety concerns. In response, our proposed model introduces an autonomous lift system that detects and adjusts to the optimal lifting points for diverse vehicles, eliminating the need for human intervention in positioning.Powered by cutting-edge hardware components, including an Arduino controller serving as the main board, REV kit for motor and extruder assembly, and precision servomotors, this system incorporates advanced sensor technologies like IR(infrared), ultrasonic sensors, and specialized point detection sensors. This comprehensive sensor array enables the lift to comprehensively assess a vehicle's dimensions, weight distribution, and ideal lifting positions upon entry.By harnessing an amalgamation of sensors, actuators, and programmed instructions within the Arduino controller, the lift autonomously adapts to diverse vehicle shapes and sizes, facilitating precise and safe adjustments. This integrated system, comprising sensors for dimensional analysis, actuators for responsive adjustments, and sophisticated programming, enables the lift to dynamically conform to various vehicles. Furthermore, stringent safety protocols, including failsafe mechanisms and emergency stop functionalities, are inherent to this hardware setup, ensuring unwavering reliability and operational security.This research aims to elucidate the pivotal role of this autonomous adaptive lift system in reshaping the automotive servicing landscape. It will delve into the technological innovations, operational functionalities, and the added value this system brings to garage operations, emphasizing its potential to elevate safety standards, increase efficiency, and transform the industry's approach to vehicle maintenance.

Haissam El-Aawar, Omar Mohammad
Open Access
Article
Conference Proceedings

The Rolling Robot and the Human Brain: Handover of the Driving Task in Automated Vehicles

The automation of driving represents a pivotal innovation in vehicular technology, transitioning from automating secondary and tertiary tasks such as ignition, gearboxes, and rain sensors, to automating the core driving procedures. This redefinition of the driving process fundamentally alters the human-machine interface (HMI) and vehicle interiors. Ensuring safe driving, vehicle usability, and a positive user experience necessitates clear delineation of responsibilities between human and machine drivers.In a laboratory study with 20 participants (55% female, 45% male, ages 20-59) with varying experience in advanced driver assistance systems (ADAS), four handover procedures were evaluated for understandability and user experience. The study comprised two parts: testing the comprehensibility of animated icons and a comparative analysis of four handover procedure designs. Icon sets differed in their representation—one holistic and the other detailed—and varied in their display strategy and location.Data were collected via direct questioning, the Net Promoter Score (NPS), the meCUE user experience questionnaire, design rankings, and open interviews. Results indicated a preference for detailed icons over holistic ones. The most favored handover procedure featured a centrally located, single detailed icon representing the current activity, leading to superior scores in NPS, meCUE, and overall ranking. Interview feedback highlighted preferences for clarity, simplicity, and central icon placement. Younger participants favored animated icons with bubble effects, while older participants preferred simpler designs. These findings underscore the importance of user-centric design in automated driving systems.The study was performed during the KARLI project funded by the German Ministry of Economy.

Peter Roessger, Cristi Acevedo, Miriam Bottesch, Samuel Nau, Tobias Stricker, Frederik Diederichs
Open Access
Article
Conference Proceedings

Age-based Differences in Pedestrians’ Feeling of Trust and Safety when Crossing in Front of a Real Communicating Self-driving Car During Daytime or Nighttime

The introduction of self-driving cars (SDCs) onto public roads will raise challenging issues to ensure traffic fluency. One of these is to guarantee pedestrians feel safe and confident when encountering this new type of vehicle in order to promote pedestrian crossing in front of SDCs. Hence, the aim of the study was to investigate the impact of different types of external Human-Machine Interfaces (eHMIs) indicating the yielding behaviour of a SDC on pedestrians’ feeling of safety and trust. Thirty-four participants (19 young adults aged 22-41 and 15 older adults aged 63-80) volunteered to take part in the experiment. Participants were requested to cross in front of a real SDC which gave way to them on a crosswalk. The SDC was equipped with devices that could send different types of eHMI signals. In the hourglass condition, two displays located in front of the SDC were showing a luminous hourglass when the SDC yielded (daytime and nighttime tests). In the safety zone condition, projectors were sending a cyan light signal onto the ground around the SDC when it yielded (nighttime tests). In the no eHMI condition, none of the above-mentioned signals were shown. The participants were not informed in advance about the presence of the eHMI signals or their meaning. After each crossing, they were asked to rate their level of trust (on a Likert scale from 1- no trust at all to 7- totally in trust) and their level of safety (on a Likert scale from 1- not secure at all to 7- totally secure) during their crossing in front of the SDC. Finally, semi-directive interviews were lead in order to gather additional information such as the cues used by the participants in their crossing decision-making, other than the eHMIs signals. Our results showed high levels of self-reported trust and safety overall. Moreover, a significant main effect of the age group indicating a stronger level of trust during the crossing of the older adults as compared to the young adults was found. However, no significant effect of the age group nor of the type of eHMI signal were found on the participants’ feeling of safety during their crossing. In addition, no significant effect of the type of eHMI signal was found on the participants’ level of trust during their crossing. Yet, the analysis of the semi-directive interviews revealed that the young adults were likely to use more implicit communication cues exhibited by the SDC during the nighttime tests as compared to the daytime tests while the older had a more conservative crossing decision-making strategy during both daytime and nighttime tests. These findings provided understanding elements of pedestrians’ crossing experience with regards to communicating SDCs in realistic conditions.

Aïsha Sahaï, Onoriu Puscasu, Natacha Métayer
Open Access
Article
Conference Proceedings

Exploring the Risks of Password Reuse across Websites of Different Importance

This study attempts to simulate the different ways through which a malicious hacker may attempt to gain unauthorized access to user accounts by leveraging the similarities between multiple linked passwords of the same user. The issue of managing multiple password-protected accounts exemplifies the usability/security trade-off in cybersecurity. Users often reuse the same password, with little or no modifications, across websites of different importance, compromising the security of the high-value accounts. By combining syntactic similarity, dictionary attack, service-related keywords, and semantic similarity on a set of 62,213 linked passwords available from the leaked databases on the internet, 82.3% of the high-value passwords were cracked with an average of 1.82 seconds spent on each attempted password. Similarly, the syntactic method alone achieved an accuracy of 73.6% at 0.82 seconds spent per password attempted. We further connect our findings to the broader issues in cybersecurity and offer a few suggestions to protect the high-value accounts of the users.

Anurag Mathews, S M Taiabul Haque
Open Access
Article
Conference Proceedings

Human Factors in Alarm Response Procedures: an Empirical Analysis of Paper versus Digital support

The objective of a Human Machine Interface (HMI) is to communicate process monitoring information, data, metrics and graphics to an operator through a screen or dashboard and offer an opportunity to control equipment and processes in factories and plants. But after the annunciation of an alarm, how effective is the supporting documentation. The existence of a refined set of instructions and procedures in the form of checklists has been a major factor contributing to the improved safety outcomes observed in the nuclear and aviation sectors. The use of paper-based checklists has been the norm, however, trials of digitized instruction systems have been on the rise in these sectors. The focus of the paper is to analyse an operator on their behaviour and situational awareness from when an alarm is annunciated to the completion of the intervention process using either paper or digitised procedures. The participants(n=46) were split equally into two groups, each testing three tasks with increasing levels of complexity. Results showed that those who were presented with the procedures on paper had slightly better situational awareness and preferred to use paper procedures when compared to those using the digitised procedures. The rationale for this outcome and recommendation for subsequent redesign of the HMI are presented in this paper.

Chidera Amazu, John Mcgrory, Maria Chiara Leva, Gabriele Baldissone, Davide Fissore, Micaela Demichela
Open Access
Article
Conference Proceedings

Inclusive smart navigation service design for the blind and visually impaired: a proposal for the city of Genoa

The advancement of interactive technologies offers promising potentials for enhancing mobility and quality of life for visually impaired individuals in smart cities. Goal 11.7 of the 2030 Agenda emphasizes the importance of inclusive, safe, and sustainable urban spaces, specifically addressing the needs of elderly and disabled citizens. This paper examines the potential of interactive technologies, such as smart white canes, wearable aids, and smart devices, in transforming urban public spaces to support the daily activities of individuals with blindness or vision-related challenges in Genoa. By integrating these technologies effectively, this study proposes inclusive service solutions aimed at improving accessibility and promoting independent navigation within the city.

Francesco Burlando, Federica Maria Lorusso, Boyu Chen
Open Access
Article
Conference Proceedings

The design of Generation Z camping car system based on Grounded Theory-AHP method

Car camping industry has been developed for a long time in western countries, and the related research has been more mature. However, there are still differences in the field between China and the West due to economic development and national characteristics, so it is important to carry out targeted and systematic research on the car camping industry in China. Several researchers have found that young people of Generation Z, as one of the major consumer groups, have distinct preferences and consumption differences, such as tolerance of diversity, love of personalization, interest-driven consumption, etc. Because of this, they are more inclined to glamping, which is mainly manifested in higher requirements for camping scenes, recreational facilities, and equipment styles. It means that campers put their emphasis on the activity experience. Therefore, to improve the camping experience, exploring the needs of Generation Z people is one of the most important ways. In addition, Chinese people usually choose private cars as camping vehicles rather than an RV, but the basic functions of an ordinary private car are obviously unable to meet the users’ camping needs any more. Consequently, the fundamental purpose of this paper was to propose a design strategy for Generation Z user camping car systems by studying the scenario needs and preferences to improve the users experience.This paper proposed an innovative applied methodology for camping car system design. In order to ensure the accuracy of design and development, qualitative and quantitative methodologies was combined. Through this methodology, we successively output a needs model of the target population and the weight ranking of needs, and used it as a design strategy. The main processes were as follows:(1)Qualitative research sectionTwenty young men and women (1:1) were included in the study (n = 20, age 22±4 years, car camping enthusiasts). Participants were asked to take part in a semi-structured interview lasting approximately 30 minutes, which focused on user needs and preferences in the car camping scenario. The questions were based on five sections: user information, vehicle needs, scene accessory needs, experience descriptions, and desired needs. In this study, we will collect information on users' needs and preferences, which will serve as the raw material for the subsequent study. In the information analysis and processing, combined with the Grounded Theory method, the original interview data were analyzed and summarized through three levels of coding. After that, a three-level “User Requirements Model for Generation Z Camping Car System” was summarized upward, with the levels being: independent category, main category and core category.(2)Quantitative research sectionIn this paper, the AHP method will be used for quantitative research. Firstly, convert the demand model into a hierarchical recursive model. Secondly, the judgment matrix was constructed, and experts were invited to score. Finally, the scoring data are processed to derive the weights of the indices of user-specific requirements (independent category layer) and sequentially ranked to extract the key requirements and their priorities. In this research, car camping enthusiasts (n = 15) and car designers (n = 5) were invited as experts to compare the scoring of the requirement factors.(3)Design Strategies Application SectionSince the main categories and core categories were more abstract and cannot be implemented into the design, they were used as strategies to provide design guidance. Specific applications were below: the user requirement model was used as a strategy to construct the overall framework of the camping car system, and the extracted key requirements were used as the focus for planning the functions of the camping car system.The final camping car demand model output 3 core demand categories, 7 main demand categories and 30 independent categories (specific primary needs). Besides, 14 key demands were extracted from the category of independence. With that conclusion in view, this paper described the design strategy of a camping car centered on Generation Z users in detail. Based on it, a whole vehicle system was designed, which consisted of the interior and exterior of the vehicle body and the interaction screens inside the vehicle. The findings and design applications in this paper had the potential to provide design references for future product development of camping vehicle systems and could also be considered as a guide for research with similar objectives.

Shihan Tang, Qijun Ye, Wenjing Wei, Bowen Zhou
Open Access
Article
Conference Proceedings

Bridging the Gap: A Comparative Analysis in Creative Processes between AI-Generative and Traditional Art

The creative process has significant importance in the realm of artistic creation, as it involves a series of cognitive and generative acts that culminate in the production of unique and original artworks. The advent of artificial intelligence has given rise to a new kind of creative output, hence posing inquiries on the essence of creativity in machines. An examination of the creative processes used in AI art may provide valuable insights into the mechanisms via which AI systems generate artworks and the extent to which these processes align with human creative practices.This study undertook a comprehensive analysis of contemporary AI art methodologies, algorithms, and models to explore the fundamental dynamics that underlie the generation of AI-generated art. The aforementioned approaches were subjected to a comparative analysis with traditional art production processes, with careful consideration given to many components including ideation, experimentation, and iteration. The identification of similarities and differences may be accentuated via the process of identifying them.

Amic Ho, Ruth Chau
Open Access
Article
Conference Proceedings

The role of negative emotions in videogames

This work will explore the literature on the different ways in which videogames can elicit negative emotions and which game's elements can provoke such reactions in players. Videogame development and research have, in their early years, mostly focused on their fun and pleasant side. In the last two decades, however, research on different emotions evoked by certain videogame titles and essays on how failure is an indivisible part of the playing experience have been successfully illuminating the nuances of what we feel when we play. The tools used to bring out such reactions are many, such as story aspects, visual and audio cues and mechanical elements. Most of these not completely fun games are also pleasant, even though this is not their main characteristic, which implies a certain type of balance between positive and negative meanings, a composition that is similar to the eudaimonia concept of media studies. This research hypothesis is that, although the majority of videogames aim mainly to stimulate pleasure and fun in their players, there is a growing number of games that aim to engender negative emotions. These games, however, do not stimulate only these emotions, but rather, weaving them together with the most commonly used emotions, such as pleasure and fun. This will be done firstly by examining released games that already evoke these emotions, secondly by isolating the elements in the game that could be responsible. This research will be convenient for researchers by providing a snapshot of what is currently known about the relationship between negative emotions and game design elements and also for the game design field by providing designers with extra knowledge and even tools to approach their métier in a different light and crafting richer experiences.

Thais Arrias Weiller, Pedro Campos, Vanessa Cesário
Open Access
Article
Conference Proceedings

Using an Artificial Neural Network Pre-trained for a Different, yet Comparable Task to Evaluate Extreme-Affect Vocalizations that Are Indistinguishable by Humans

Humans categorize vocal displays of highly intensive affective states with very low precision. However, there are many applications necessitating correct perceptions of alarm calls. We decided to classify two negative (pain and fear), two positive (laugh and pleasure) affective states and compared these to neutral state. We used a unique dataset where all displays had been vocalized by all expressers. We used an ANN that is designed for a different, yet comparable task; one that classifies human and animal sounds as well as mundane events (such as pouring water from a jug). The outputs were then statistically analyzed using Bayesian methods. Our analysis showed that the outputs can successfully classify neutral and non-neutral affective states but they were unable to distinguish the intensive affective states from each other (with one exceptional case of laugh). Given the insights we acquired, we infer that classifying intense affective states will remain an insurmountable barrier for any future ANN. The applicability of our result also shows that the cost, time, and effort overhead of attempting to designing a dedicated ANN will be prohibitive.

Hermann Prossinger, Violetta Victoria Prossinger Beck, Silvia Boschetti, Jakub Binter
Open Access
Article
Conference Proceedings

Through the Psychological Lens: Unveiling Biases in Multi-Criteria Decision-Making

Multi-Criteria Decision Making (MCDM) methods have become a mainstay in navigating complex decision-making scenarios. These methods empower individuals to consider multiple, often conflicting, criteria simultaneously. While primarily developed in computer science and operations research, the psychological implications of these methods are rarely touched on. This paper aims to address this gap by critically analysing the most established contemporary MCDM (Multi-Criteria Decision Making) methods from a psychological perspective. Due to the scope of the field this paper will restrict itself to MADM (Multi-Attribute Decision Making) methods which focus on selecting an option from a set of possible alternatives. By providing additional context and considerations, we aim to empower users to make informed decisions about their application and be mindful of their limitations.

Boris Djartov, Falk Maria Oswald, Jörn Jakobi
Open Access
Article
Conference Proceedings

Redefining Creativity and Artistic Endeavours: Exploring the Impact of AI-Generated Digital Art on Human Society

Artificial intelligence has transformed the field of creative work, challenging existing ideas of creativity and creative work. AI-generated digital art has emerged at the crossroads of innovative technology and human creativity and prompted an extensive investigation into its potential consequences on a wide range of human activity. Students also consider whether AI-generated digital art influences individuals’ willingness to engage in art-related activities and produce their work. The use of AI in art evokes components of self-consciousness and identity. Furthermore, the researchers examined the colours provoked by AI-generated digital art, revealing useful information on how AI art generates new emotions and interactions. This article seeks to identify ways in which AI technologies and methodologies open up new possibilities for creators and artists, investigating through case studies, surveys, and qualitative and quantitative measures the transformative potential of AI-generated digital art and its influence on cultural and social dynamics.

Amic Ho
Open Access
Article
Conference Proceedings

An AI-Driven User-Centric Framework reinforced by Autonomic Computing: A case study in the Aluminium sector

The integration and deployment of AI in the industry faces several challenges, involving not only the need for robust and accurate AI models, but also their seamless integration with existing systems, while ensuring an intuitive user experience for workers. Furthermore, it is critical for AI solutions to be continuosly managed for data governance, performance optimization, and the mitigation of risks, among other factors. This paper presents a service-oriented application that explores the integration of Machine Learning algorithms by adopting Human-in-the-Loop (HITL) strategies to enhance user-technology interactions in an Aluminium industrial environment. The proposed application exploits the use of data-driven Autonomic Computing techniques in AI Data Pipelines to promote the development of self-managed, adaptive systems that support dynamic interactions between technology and workers. Through the implementation of a web interface, workers are provided with seamsless access to real-time data analysis and intelligent solutions within the user-empowered application.

Ramon Angosto Artigues, Andrea Gregores Coto, Jonathan Josue Torrez Herrera, Fernando Lou Tomás, Sabrina Verardi, Mattia Giuseppe Marzano, Andrea Fernandez Martinez
Open Access
Article
Conference Proceedings

Survey of Research Issues and Proposed Solutions for Detecting Parameter Anomalies in System Logs

In the ever-evolving field of software development, the demand for automation of fault analysis that is time-consuming and expertise-requiring is growing. One solution to this challenge is the study of anomaly detection using text logs, which has seen numerous research efforts. However, despite the variety of patterns that system anomalies can exhibit, many studies have predominantly focused on sequence anomalies. This is largely attributed to the limited availability of datasets, with the commonly used Loghub data being oriented towards sequence anomalies. This research addresses the current challenges in anomaly detection models and proposes several new methods for detecting parameter anomalies. Initially, due to the lack of datasets of parameter anomalies, we prepared common parameter anomaly scenarios and compared them with existing sequence anomaly detection models (including DNN models for sequence anomalies and DNN models using semantic information), and with a variety of proposed methods. The prepared parameter anomaly patterns include four Integer types and three String types. For instance, a parameter within a certain range (-100 to 100) is considered normal, while parameters outside this range are deemed anomalies. Our proposed method begins by extracting parameters using LogParser and determining whether they are of Int or String type. For Int types, we use Z-Score, IQR, K-NN and DBSCAN for evaluation, while for String types, we use a Bert-based positive-negative classifier. The experimental results showed that the DNN model for sequence anomaly had an F1 Score of less than 0.5 for all patterns. In contrast, our proposed methods achieved F1 Scores exceeding 0.9 or 0.8 for almost all methods, except for one anomaly pattern. It was found that the proposed methods are effective for common parameter anomaly problems. Furthermore, since our methods do not require prior training, they are particularly advantageous for ad-hoc learning in the context of continuously updated software development.

Hironori Uchida, Keitaro Tominaga, Hideki Itai, Yujie Li, Yoshihisa Nakatoh
Open Access
Article
Conference Proceedings

Predicting Key Substance Levels in Aquaculture through AI-Based Water Quality Monitoring

Land-based aquaculture farms use seawater transported from nearby seas instead of large amounts of freshwater. A seawater recirculating filtration system is essential for sustainable fish farming; however, this system has limitations in improving the levels of ammonia, nitrite, and nitrate, which are directly linked to fish mortality. Therefore, most land-based aquaculture farms periodically exchange a certain amount of seawater to maintain optimal water quality. Despite these efforts, managing water quality remains a significant challenge due to the fluctuating levels of these harmful substances.This study aims to address this challenge by predicting the levels of ammonia, nitrite, and nitrate—the primary causes of fish mortality in land-based aquaculture—using AI models. The training data were collected from various sensors installed in the farms, including those measuring water temperature, dissolved oxygen, dissolved solids, pH level, oxidation-reduction potential, salinity, nitrate, and ammonia. By leveraging this comprehensive dataset, we evaluated the performance of multiple models, such as Random Forest (RF) and K-Neighbors Regressor (KNN).The study demonstrated that these models could achieve remarkable performance metrics, with the Random Forest model recording an MAE of 0.0150, MSE of 0.0008, RMSE of 0.0289, R² of 0.9999, RMSLE of 0.0039, and MAPE of 0.0024. Such high accuracy levels indicate that AI-based water quality prediction models have significant potential for effectively monitoring and predicting fish health in aquaculture farms. Implementing these AI models can lead to more proactive and precise management of water quality, ultimately reducing fish mortality rates and enhancing the sustainability and profitability of aquaculture operations.

Ji-yeon Kim, Ki-hwan Kim, Young-jin Kang, Seok-chan Jeong
Open Access
Article
Conference Proceedings

Exploring The Use of ChatGPT4 API in Approaching Math Word Problems

With the evolving educational landscape precipitated by the COVID-19 pandemic, online education becomes increasingly prevalent. Much help is needed to provide innovative solutions to address the challenges faced by both students and teachers during this time of crisis. This paper describes an independent research project conducted by a pair of high school students between April 2023 and February 2024, under the mentorship of a senior research scientist at the National Institute of Education in Singapore. The project investigates various methods of Tesseract OCR text recognition, OpenCV image processing, Flask web development and OpenAI’s Large Language Models to improve mathematics-solving applications.Our program extracts text using Tesseract OCR, utilising it as input for the GPT-4 API, enabling a conversational presentation of mathematics problems. Users interact by inputting the image address of the math problem that they would like the AI to solve, and GPT-4 provides solutions with detailed step-by-step explanations. OpenCV improves the provided image’s quality such as making the text or diagrams more distinct to reduce the possibility of them being misinterpreted. Through evaluation by testing with different types of maths problems of varying difficulty, our findings underscore the potential for advanced language models in educational tools, offering interactive and intuitive maths problem-solving experiences. There were a few limitations encountered during experimentation, such as challenges with extraction of non-Latin alphabets and accuracy of the OpenAI’s Large Language Modules when solving more complex diagram problems, highlighting the need for further refinement to enhance the system's robustness and adaptability. Future work involves addressing these limitations to broaden the system's applicability for educational purposes and beyond.

Joe Wong, Harsavardhan M G R, Kenneth Y T Lim, Swee Ling Leong
Open Access
Article
Conference Proceedings

An Exploration of Machine Learning and Reinforcement Learning for Emotional Well-Being

With the high levels of stress in Singapore, mental and emotional well-being is an important health and social issue today. Research has shown the positive effects of pet ownership on mental and emotional well-being, however challenges of owning a pet in Singapore such as pet licensing restrictions, high costs, fear of losing a pet, a busy lifestyle and even allergies may deter pet lovers from owning a pet. Thus, we propose a technology-driven solution to emulate the useful effects of pets while mitigating the challenges of pet ownership. This project focuses on designing emotion recognition and reinforcement learning models as a stepping stone to individualise responses to a person’s emotions. Our approach utilises the output from the emotion recognition model as an input in the proposed reinforcement learning algorithm. Hence, the paper first compares pre-trained and custom trained facial recognition models, and postulates the use of physiological signals via hardware sensors to further enhance the emotion recognition model. This is inspired from the ability of pets to perceive and respond to different emotions based on facial expressions and physiological signals like heart rate. The paper then outlines the development of novel K-Bandit algorithms in reinforcement learning tested on simulated reward functions, with the aim of optimising parameters for individualised responses to a person’s emotions. Since reinforcement learning is typically used in simulation scenarios, this paper works towards developing a model that will eventually learn a person’s preferences in real time by monitoring their emotional changes. To conclude, this project has showcased the feasibility of facial expressions and physiological signals for emotion recognition, and established the effectiveness of our proposed parameter optimisation functions in the K armed bandit reinforcement learning model to customise responses based on an individual’s emotions. We hope this paper can act as a basis for future works in creating a human-friendly prototype to emulate man’s best friend.

Kenneth Y T Lim, Ryan T S E Chio, Zhi Wen Lim
Open Access
Article
Conference Proceedings

SME-capable Innovations-Management-System as a Service: Artificial Intelligence by click

The rapid advancement of Artificial Intelligence (AI) is reshaping the landscape of innovation management, especially regarding Small and Medium-Sized Enterprises (SMEs). This paper explores the integration of AI technologies into SMEs' innovation processes, demonstrating how AI can automate complex tasks and enhance operational efficiency and innovation outcomes. Aligned with the structured innovation management processes of DIN EN ISO 56002, encompassing five critical stages— [1] Idea Generation & Evaluation, [2] Concept Development, [3] Development, [4] Prototype Building & Testing, and [5] Production & Market Launch—this study introduces the developed service framework "eskalator.io." By leveraging Large Language Models (LLMs) and APIs, this innovative approach streamlines data analysis and project evaluation, facilitating a nuanced analysis of customer feedback, technical specifications, and market research data to optimize decision-making.The study addresses challenges in adopting AI technologies, such as security and privacy concerns, emphasizing the importance of ongoing developments for secure and ethical AI integration within SMEs' innovation ecosystems. It aims to contribute to the broader discourse on AI's transformative role in enhancing SMEs' innovation capabilities while proposing future research directions. Common barriers to AI adoption and effective innovation management in SMEs, including lack of technical expertise, administrative burdens, and skepticism about tangible benefits, underscore the need for tailored, user-friendly solutions to encourage broader adoption.

Robin Bakir, Maximilian Müller, Dennis Bakir
Open Access
Article
Conference Proceedings

AI-based Chatbot Coaching for Interdisciplinary Project Teams: The Acceptance of AI-based in Comparison to Rule-based Chatbot Coaching

Project-based work is integral in corporate and academic settings, where coaching plays a crucial role in enhancing team performance and project success. To streamline this process and improve scalability, we developed a coaching chatbot at TH Köln/University of Applied Sciences to assist interdisciplinary teams. Utilizing a systemic coaching approach, the chatbot prompts self-reflection through solution-focused questions. We collaboratively created it with student facilitators and lecturers and tested it during a University-wide Interdisciplinary Project Week in November 2023. The pilot study involved two versions of the chatbot: a rule-based system and a hybrid model incorporating generative AI capabilities. As part of the field test, we analysed its acceptance: How effective is the chatbot in supporting projects groups and facilitating reflection processes? Are there differences in acceptance between the two chatbots? Half of the project groups in the one-week course used the rule-based chatbot, while the other half of the project groups were provided with the AI-based chatbot. 134 students participated and used the chatbots at the end of each day of the project week. The results of this study indicate that our test subjects accepted both types of chatbots with moderate to good scores in acceptance. However, the AI-based chatbot fared significantly worse in terms of performance expectancy and effort expectancy. This is possibly due to the fact that hybrid coaching chatbots are neither widely developed nor researched. We conclude that regardless of the technical basis of such a chatbot, conversation design and prompting is an essential part of chatbot development and contributes significantly to acceptance. This study demonstrates the potential of chatbots in supporting group coaching, not only in educational settings but also in corporate environments where they can aid agile project teams. This research marks one of the initial explorations into the acceptance of group coaching through chatbots.

Vanessa Mai, Johanna Nickel, Anna Gähl, Rebecca Rutschmann, Anja Richert
Open Access
Article
Conference Proceedings

Unravelling the Aesthetics and Emotion: Exploring the Artistic Value of AI-Generated Artworks

The debut of AI art, a new cultural realm, has given rise to discussions about its artistry and aesthetic value. On the other hand, since the new path of the art-creational movement does not allow applying traditional components of creativity to evaluate the creative and aesthetic value, art coming from AI creates new difficulties concerning its evaluation. What are the pillars of the art genre – composition, technique, visual phenomena – no longer look the same? New tools are required to give a scientifically sound assessment of the esprit and visual components of AI art. How do we assess emotions driven by works from AI? They may show the extent of faithfulness to the traditional genre due to the same or diverse components from conventional art. This paper tries to compose and define the base on which an assessment of emotions driven by such works is to be done. When the artist agrees, AI uses machine learning algorithms, and the experience is always learning.

Amic Ho
Open Access
Article
Conference Proceedings

BlindSpot: An AI-Powered Intelligent Mirror Assisting with Facial Hygiene Analysis for Blind People

Appearances are important for our everyday lives: it is how we present ourselves. Yet, for people who are blind or visually impaired, it can be challenging to notice or take care of their facial hygiene without sighted assistance. Furthermore, existing AI-powered visual assistive technologies such as Seeing AI do not provide such support.We first performed an online search to identify the needs of blind people and people who are visually impaired by checking their appearances. We found that checking appearances is a pertinent need shared by many people who are blind or visually impaired. For example, in the autoethnography by a blind girl [1], the author explains that growing up with visual impairments is physically and mentally strenuous on teenagers. In Li et al. [2], the authors find that people who are visually impaired “normally keep [their] appearance the same as before the loss of vision. This makes people focus less on [their] face and [their] visual impairments.” And that “people with visual impairments are attentive to their appearance,” by “applying makeup”, so that they “can control [their] appearance again.” Pradhan et al. [3] found that people with visual impairments care about their appearance as “they know people around them can see them,” they also “rely on sighted or partially sighted people to act as their mirrors.” Such prior work highlights the need to develop novel solutions and mechanisms to help blind people check on their appearances more independently. The advances in artificial intelligence, especially with regard to AI’s capabilities on analyzing images, brings tremendous potential to augment the vision of people who are blind or visually impaired. In this project, I propose the design of BlindSpot, which is an AI-powered intelligent mirror to help people who are blind and visually impaired check their appearances through uploading images to the platform. Our prior need-finding search revealed diverse needs by blind people on checking appearances, including checking food stains around mouth area, checking makeup quality, and checking cleanliness of their faces. To use BlindSpot, we imagine users can first upload a reference photo which displays their regular appearance, and then upload another photo that they wanted to have the intelligent mirror check for them. In cases where users do not have a reference photo, they can directly upload a photo of interest and ask BlindSpot to check their appearance for them. To evaluate the design concept of BlindSpot, we first constructed a repository composed of people’s headshot images with different appearance issues ranging from food stuck on teeth, to smudge of makeup. We then prompted GPT-4 to evaluate the headshot images and give users feedback for them to adjust their appearance. We found that in most of the scenarios, GPT-4 is able to generate accurate assessment and give helpful feedback. We report scenarios where GPT-4 makes mistakes and makes suggestions on how to further improve the design.

Toby Lu
Open Access
Article
Conference Proceedings

Design Process for Augmented Reality (AR) Experiences from the Perspectives of UX and Game Designers

This paper presents a cognitive study comparing the approaches of User Experience (UX) designers and game designers in Augmented Reality (AR) experience design. The AR Haunted College is a scenario-based sequential AR experience that transforms the Monroe Hall building at Loyola University New Orleans into a chilling Halloween spectacle. The design of AR Haunted College involved contributions from both UX designers and game designers. We characterize the distinct approaches of UX and game designers by analysing the design process of the AR Haunted College developed in an agile project management framework. Our results show common and distinct HCI and game design principles between UX and game designers’ perspectives. Building on the findings of the analysis, we propose a set of design principles as a basis for an AR design framework and associated heuristics.

Jingoog Kim, Lina Lee
Open Access
Article
Conference Proceedings

Verification of an alternative wheelchair control in a virtual environment

This work presents a training simulator that is being developed in collaboration with electric wheelchair users and medical professionals. The main function of the software is to serve as a development platform for alternative control systems that enable people with paralysis to control a wheelchair themselves. The project developed two prototype control systems using technologies such as eye tracking and a brain-computer interface.

Jendrik Bulk, Benjamin Tannert
Open Access
Article
Conference Proceedings

Collaborative Learning through XR. A study of eye- and hand-based XR interactions to support collaborative learning in the chemistry classroom

In this paper, we explore how extended reality (XR) and virtual reality (VR) can facilitate shared experiences that transcend individual boundaries. Using an example from the chemistry classroom, we illustrate how these technologies can enhance education and learning by fostering collaboration and shared understanding.Despite the vast potential of XR and VR, many of their applications remain isolated. Currently, sharing experiences often involves streaming onto a screen or verbal explanations, which can leave individuals feeling excluded if they are not directly involved. Even when multiple users wear VR or XR headsets, shared experiences are often limited to specific contexts like multiplayer VR games. Unfortunately, in domains such as education, work, or collaborative learning, these technologies are often underutilized.To bridge this gap, our study developed a prototype that leverages the eye-tracking and hand-tracking capabilities of the HoloLens2. This prototype enables collaborative interactions with 3D elements in an XR environment. By tracking participants' gaze within the XR scene, users can easily identify the element they are currently viewing. Through eye control and pinch gestures, users can manipulate digital content on the XR plane. When working within the same XR environment, users seamlessly share interactions and information, fostering a unified and collaborative experience with holograms.The current prototype is tailored to explore the intricate molecular details of sugar molecules within a collaborative XR environment. Teams of users can collectively delve into molecules such as fructose, glucose, galactose, and mannose, gaining deeper insights into their unique characteristics. Through interactions like eye-tracking and pinch gestures, users can directly interact with holographic 3D representations of these molecules. The prototype's user interface intuitively indicates which user is interacting with or observing each 3D object within the XR environment. Unlike conventional controllers, this prototype employs hand-tracking technology, enabling users to effortlessly navigate the XR interface using natural hand movements. This approach delivers an immersive and dynamic learning experience that surpasses traditional teaching methods, fostering heightened engagement and deeper understanding among learners. To assess the functionality and cognitive impact of the XR interface prototype, 19 participants were recruited for evaluation. Criteria for participant selection ensured they lacked prior knowledge or involvement in chemistry or related fields concerning sugar molecules. Following a brief introduction to the prototype's interaction patterns and eye calibration, participants engaged in testing across diverse learning scenarios. Initial survey findings suggest participants could swiftly distinguish between monosaccharides like glucose, fructose, galactose, and mannose based on their three-dimensional structures. However, results regarding gaze interaction evaluation are inconclusive and necessitate further experimentation.

Boribun Wisanukorn, Frank Heidmann
Open Access
Article
Conference Proceedings

Virtual Ergonomics - Ergotyping in virtual environments

Ergonomic assessment of manual work processes is important to prevent workplace injuries. Virtual reality simulations can be used to carry out an evaluation of work equipment and workplaces very early on. In combination with motion tracking analyses, data on posture during task performance and product use can then be collected. However, not all work situations can be equally represented in a virtual simulation. In particular, the virtual analysis of load handling poses a challenge in simulation, as body posture changes under the influence of external load weights. The aim is to increase immersion to bring the body movements in the virtual simulation closer to those in the real simulation with weights.For building up VR simulations with different aspects of visual, auditory and haptic immersion a scheme called immersion cube is presented. In order to be able to simulate load handling in VR, the immersion cube is used to investigate how much haptic immersion is needed to obtain sufficiently good data for the body movements measured in a VR setting. The first study showed that the deviation between real and virtual executions depends heavily on the task (lifting from the ground, move while standing, lifting over the shoulder). In some tasks, virtual and real simulation are very close to one another for certain body movements and could therefore in principle be used for ergonomic assessment. On the other hand there are still movements that vary between these two forms of execution and therefore show a need for increasing the immersion.

Stefan Pfeffer, Marc Roessler, Simone Maag, Lisa Langwaldt, Lara Schunggart, Markus Strigel, Abigail Senger, Moritz Ochtrop
Open Access
Article
Conference Proceedings

Combining system dynamics and agent-based simulation to evaluate and visualise sustainable airport operations.

Facing the backdrop of the climate crisis, we are currently witnessing an intense transformation process in aviation. Aim of this process is a climate-friendly air transport system. In addition to aircraft manufacturers and airlines, airports also must contribute to this transition by improving their operations. A key objective of airport management is therefore to foster climate-neutral aviation and energy-efficient airport operations. European airports are committed to achieving these goals by 2050. An important contribution to achieving these objectives is to enable airport operators to draw informed operational decisions while balancing traffic impacts with economic and environmental aspects. Therefore, we regard an airport as a holistic system with various operational areas and stakeholders in which an overarching and coordinated management allows for targeted prioritisation, e.g. of sustainability parameters. This paper, therefore, presents a concept for combining different simulation techniques resulting in a comprehensive, integrated hybrid simulation model and visualization tool. For this purpose, we combine two simulation techniques, namely an agent-based network simulation that maps the Advanced Collaborative Decision-Making Concept (A-CDM) for joint decision-making at airports via state charts as discrete events with a flow simulation based on system dynamics. The flow simulation is intended to map energy consumption in relation to capacity utilisation in different functional areas. Combining the strengths of these two simulation types enables us to evaluate and analyse ecological and (macro-) economic effects as well as operational impacts on airports simultaneously. One of the main challenges lies in the connection and interaction between discrete events and dynamic system flows and therefore in the combination of micro- and macro-simulation. We describe how to solve this technical and logical challenge of integration and – with a first prototype – we show our ideas on how to visualize the results of this hybrid simulation for airport operators to provide substantial and situational decision support. Commonly used airport Key Performance Indicators (KPIs), which describe the operational performance of an airport, are set in relation to ecologic and economic KPIs in order to obtain a complete picture and thus enable holistic airport management. To this end, existing operational KPIs are supplemented by further dimensions mentioned above and their visualization is developed with a view to perceivability and conceivability in order to increase and maintain situational awareness. A current state of the art algorithm is presented on how to couple these different simulation approaches. Furthermore, an outlook is given on how new types of KPIs can be developed further by using the advantages of combining these simulation techniques. Our approach incorporates both environmental and economic parameters, enabling airport operators to correlate energy consumption with optimised airport management KPIs, such as flight punctuality, utilisation and cost of resources. This will contribute to a more comprehensive approach of airport management and promote sustainability. Finally, next steps in the implementation of this hybrid simulation and visualisation will be presented, and how it will contribute to informed decision-making in airport management by providing multi-dimensional evaluations in real time, thus fostering a climate-neutral aviation for our future.

Florian Rudolph, Martin Jung, Axel B. Classen
Open Access
Article
Conference Proceedings

The construction of egocentric and allocentric spatial representations in visual-spatial working memory in highly immersive virtual reality (CAVE)

In solving spatial tasks, neurocognitive egocentric and allocentric spatial representations storing in the visual-spatial working memory. Egocentric representations encode the visual scenes in self-centered coordinates and allocentric representations – in world coordinates regardless of the observer's position. Previously studies showed a good consistency in spatial processing about real environments compared to virtual reality environments. A presentation method was developed for memorizing and reconstructing 3D scenes using the highest immersive CAVE virtual reality system. A space for task, library of objects and virtual scenes were designed, each containing seven virtual objects located in different 3D positions. Three viewpoints were given for reproduction: «the front» viewpoint (to reproduce the memorized scene from the imaginary egocentric position), «the left» and «the above» viewpoints (to reproduce the scene from the left or above imaginary allocentric positions, respectively). The participant had to reconstructed memorized scene in a natural way by choosing objects from the library and placed it in virtual space in accordance with the given imagine viewpoint. The score of object localizations was estimated separately by three parameters — topology, metrics, and depth. The results showed, that for both types of spatial representations schematic topological properties were preserved better in visual-spatial working memory than the exact metric information (especially for the egocentric representations). Overall, the egocentric representations were more effective in the reconstruction of 3D scenes than allocentric representations. It was also found that when using an allocentric representations, the need to add a height axis (vertical rotation) diminishes the effectiveness of the scene reconstruction from visual-spatial working memory, compared to rotations in the horizontal plane. The results suggest that both egocentric representations and allocentric representations can be formed in visual-spatial working memory, but that egocentric representations are more basic in the solution of spatial tasks using visual-spatial working memory. These results not only have theoretical significance in cognitive psychology, but also have the potential for wide practical application in healthcare, education, developmental and sports psychology, human factor research and related interdisciplinary fields.

Olga Saveleva, Boris Velichkovsky, Galina Menshikova, Grigory Bugriy
Open Access
Article
Conference Proceedings

GlasgowSim - Glasgow Coma Scale Simulation

The training of healthcare professionals is a tough and prolonged process that requires deep understanding of theoretical concepts as well as technical, non-technical skills. Commonly, during the early stages of medical education instructional techniques involve static and unrealistic learning materials, based on the old philosophies. Nowadays, traditional approaches are being replaced by novel methods focused on the use of the new technologies and advanced simulators. The use of serious games and VR simulation can contribute to the training and improvement of the skills of healthcare professionals, thereby contributing to the quality of care, increasing patient safety and reducing costs of training programs. In this project, we developed a simulation-based serious game allowing students and professionals to practice on the evaluation of the patients’ state of consciousness according to the Glasgow scale. The Glasgow Coma Scale (GCS) is a neurological instrument that measures the “severity” and extent of impaired consciousness. The GCS has become the most used tool in the world to document alterations in the level of consciousness caused by brain damage. In combination with other neurological examinations, the scale is used to estimate the vital prognosis of patients with a severe brain injury. Because of its ease of use for all health professionals in all care settings, the scale has become an essential tool in all training programs. The neu-rological evaluation requires frequent simulation-based education to improve the cognitive, psychomotor and communication skills of the health students. However, current simulation approach¬es are resource-intensive and not routinely offered in all healthcare schools. Also, alternative approaches are needed to improve working memory, decision-making skills and teamwork per-formance. Serious games may be effective and more accessible alternatives if they use active, experiential and problem-based learning. They are indeed likely to solicit the student motivation and allow them to develop knowledge in complex learning situations. A multidisciplinary team including experts from healthcare, education and engineering ensure a coherent interaction between the game, content and pedagogical features. The GlasgowSim project aims to develop a pedagogical innovation that meets the requirements of the curriculum and extends the teaching options for the Glasgow Assessment Scale. The user is invited to interact with a computer-based device that combines teaching aspects with playful elements derived from video games. Theoretical and simulation workshops are currently being organized, but straight neurological assessment needs to be made more accessible to health students who will be applying ECS daily as future clinicians. When used for demonstration purposes, these approaches are resource-intensive (mannequins, technicians, teachers, etc....) In addition, through the various satisfaction evaluations, students express their wish to have access to different teaching tools to identify the future challenges of the practice sites. On the one hand, the teachers in the HESAV nursing care stream have developed clinical vignettes that promote the integration of knowledge and student learning, and on the other, the teachers in the HEPIA IT stream have developed a virtual environment that allows users to immerse themselves in a real-life neurological assessment situation. In this way, we will encourage the participants' reflective practice by optimizing their clinical judgement in the assessment and management of patients with neurological disorders. The trainers are convinced that simultaneous learning of Why and How the Glasgow Coma Scale is administered would optimize the clinical judgment of health professionals in the neurological assessment of brain-injured patients. Based on the design decisions, we have broken down the GlasgowSim solution into three essential components. The first component is the simulation tool, which allows the learner to interact with the patient, make diagnosis, and deliver assessments and recommendations. This tool creates the complete simulation environment based on a description of the scenario in JSON format and aggregates the necessary objects with the right configuration. The second component is the interactive patient. We considered this element to be essential given the importance of the patient in the diagnosis to be made by the learner. This patient has been developed to enable realistic GSC diagnosis. Finally, the last component is the interactive scenario creation tool. This tool will enable teachers to define all the parameterizable elements of a scenario and to export the scenario in JSON format to the simulation tool. To be able to create new scenarios and new clinical situations simply and easily, a scenario generator has been developed in the form of a web application connected to the simulator.

Dominique Correia Deoliveira, Yassin Rekik, Stéphane Malandain
Open Access
Article
Conference Proceedings

Hybrid Improvisational Theatre: A Thematic Review of the Production Processes

Hybrid events, offering both in-person and online access, have become increasingly common, since the COVID-19 pandemic, as a way to make work and entertainment more accessible. Furthermore, growing uptake of modern consumer XR products has led to the development of a number of successful hybrid theatre productions. Such productions generally aim to offer an equally entertaining experience for both the in-person viewers and virtual, globe-spanning, audiences that attend performances online, through a range of different methods. However, while such theatre productions are being produced there has been limited academic work investigating its impact on the development of theatre production from the practitioner's perspective. This paper aims to rectify this by developing an in-depth understanding of the creative and technical challenges posed by hybrid theatre by examining the creation of one such production through interviews with the practitioners and audiences. For this purpose, researchers from the University of York collaborated with the theatre company FANDCO to develop a hybrid improvisational theatre production. To achieve this Unreal Engine, Motion Capture and projector screens were utilized to enable the actors to have a simultaneous in-person and virtual presence. The audience were similarly split, with the flexibility to view the performance either in-person at the theatre or online via a live video stream and a moderated interactive chat. After each showing the practitioners and in-person audience were invited to be interviewed and complete a questionnaire asking them to critically evaluate the overall experience. The online audience were sent a link to the questionnaire and provided the opportunity to be interviewed at a later date. To analyse the data a thematic analysis approach was adopted. The results in this paper highlight a clear understanding between the audience and the practitioners on how the process could be built upon to create captivating hybrid experiences. However, there is an interesting disparity between the two viewpoints on the difficulty of implementing change, setting an elevated expectation on what is viewed as possible compared to what can be achieved with the constraints of budget, time and resources. Overall it is clear that the process of creating hybrid performances could be improved to benefit both the audience and the practitioners but adopting such changes is limited by the resources available to the production team. We conclude that the use of hybrid technology positively affects the theatre space and provides opportunities for novel, exciting avenues for immersive and interactive productions. Furthermore, a rich understanding of the needs of practitioners and audiences can positively affect the theatrical production development process. The findings in this paper provide key insights into the challenges for creators and audience in the development of improvisational hybrid theatre productions and XR-based theatre more generally.

Daniel Lock, David Gochfeld, Ben Kirman
Open Access
Article
Conference Proceedings

Formative Usability Assessment of a Rehabilitative Hand Exoskeleton – Directions for User-Friendly Physical Interfaces

Robotic training with exoskeletons has shown promise in the recovery of motor functions within clinical rehabilitation settings [1]. Hand exoskeletons, which is a sub-category of such wearable robotic devices, aim to aid patients in regaining their motor functions. These robotic devices are designed to manipulate the joints of the fingers, primarily for the purposes of rehabilitation and/or interaction. Current hand exoskeleton systems pose numerous usability issues due to challenges stemming from the system complications dictated by the complexity of hand kinematics. Size, bulk and weight are among those complications governing most rigid exoskeletons, negatively affecting the devices' comfort, adjustability, portability and wearability [2]. Many systems have low technology readiness levels, posing challenges for acceptability, marketability and home deployment [3].This paper presents a formative usability test study involving eight healthy individuals to identify user-centred criteria and directions for improving the usability of a hand exoskeleton system. Early identification of potential usability issues is crucial in eliminating those problems during design iterations. The proposed robotic exoskeleton is a two-degree-of-freedom, fully actuated system. It is designed for the index finger using an optimization technique that minimises a cost function which is composed of the isotropy measure and the required actuator torque. It is controlled by an admittance-based control system. The formative usability test was applied as a procedure accompanying the motor learning tests for system validation. The test adopted a qualitative approach combining structured observations during exoskeleton use to complete motor control tasks as they interact with a virtual dynamical system in a leader-follower modality. The observations were followed by semi-structured interviews immediately after use. All sessions were video recorded for thematic analysis.Qualitative findings from the formative usability tests revealed issues related to use comfort, wearability, simplicity and perceived safety of the proposed exoskeleton system. Based on these findings, practical design recommendations will be provided to enhance the donning and doffing of the device, adjustability of finger connections to accommodate anthropometric ranges, material selection and component layout for improved physical comfort. The outcomes of this study are expected to contribute to both the usability improvements of the current system and serve as a reference to the research community in general while developing user-friendly physical interfaces for wearable robotics.[1] Prange GB, Jannink MJA, Groothuis-Oudshoorn CGM, et al. Systematic review of the effect of robot-aided therapy on recovery of the hemiparetic arm after stroke. J Rehabil Res Dev. 2006; 171–183.[2] Ferguson PW, Shen Y, Rosen J. Hand Exoskeleton Systems—Overview. Wearable Robotics: Systems and Applications. 2020; 149–175.[3] Martinez-Hernandez U, Metcalfe B, Assaf T, et al. Wearable Assistive Robotics: A Perspective on Current Challenges and Future Trends. Sensors. 2021, Vol 21; 6751.

Sedef Süner Pla Cerdà, Batuhan Şahin, Kutluk Bilge Arıkan
Open Access
Article
Conference Proceedings

Exploring the potentials of wearable devices in research on wellbeing and stress in workplaces

Work-related wellbeing and stress are major research issues nowadays. Stress at work affects employee’s mental and physical health and reduces productivity. Since the definitions of stress and wellbeing are various, different strategies to investigate the problem and promote solutions have been taken. This study was developed within the innovation ecosystem MUSA (Multilayered Urban Sustainability Action) in the challenge of Spoke 2, Big Data-Open Data in Life Sciences, which aims to create solutions for the collection, conservation, and process of big data to improve lifestyle, prevention, and treatment. The study is grounded on the requirement to meet the complexity of stress and wellbeing conditions, therefore integrating qualitative (EMA questionnaire diary) with quantitative (wearable device Fitbit) data. This article presents the preliminary studies with the principles and recommendations leading to the final design of the experiments included in the research.

Margherita Pillan, Isabella Ruina
Open Access
Article
Conference Proceedings

Evaluating Ergonomic Design: A User Command Interface for Industrial Exoskeletons

Industrial workers perform daily activities with a high risk of musculoskeletal disorders. Diverse studies have reported high rates of musculoskeletal disorders among distinct industry professionals, with values exceeding 75% for most occupations considered. Commonly affected body areas include the neck, back (particularly the lower back), shoulders, and lower limbs. A potential solution to reduce the risk of injury among industrial workers is the use of exoskeletons in the workplace. This wearable suit improves ergonomics depending on the body part it supports. From the actuation point of view, exoskeletons can be categorised in three branches: passive, active, and quasi-passive or active. Active exoskeletons contain sensors, actuators, and electric controller boards; these characteristics make them more versatile for adapting the control strategy to the required task. The wearer of an active exoskeleton, needs of a human-machine interface to modify parameters that impact the exoskeleton control strategy. The user command interface is a wearable device that allows easy adjustments when an interaction occurs.Purpose: In this paper, we present an ergonomic assessment of the User Command Interface. The interface plays a crucial role in addressing the challenges faced by developers in optimising industrial exoskeleton capabilities by offering adaptability, control, usability and performance enhancement features. This electromechanical device attached to the exoskeleton provides a solution for achieving user interaction and is open to the user exoskeleton´s assets. However, human factors regarding physical ergonomics have not been addressed with exoskeleton´ users when the interface is in use.Methods: It is important to highlight the difficulties faced when analysing design requirements in wearable devices, particularly in terms of measuring attributes such as comfort. For instance, this term may be defined differently in various studies, sometimes as a standalone design requirement and in other cases as part of a group of requirements. However, comfort was found to encompass aspects such as freedom from discomfort and pain, acceptable temperature, texture, shape, weight, and tightness, all of which contribute to the overall comfort and usability of a device. To assess the interface, we performed a comparison test of three physical ergonomic attributes: comfort, durability, and safety. Using the mapping wearable design requirements method, five shape-like interfaces were evaluated. Four out of five interfaces are previous versions according to the evolution of our interface, and the last one is a mobile phone. This approach of quantifying and analysing design requirements helps in understanding the complex relationships between different terms and ensures a more systematic and thorough evaluation of design aspects in wearable devices.Results: Twenty subjects participated in the study. The results show the statistical differences of the five shape-like interfaces between the attributes of physical ergonomics, including shape, breathability, hygiene, temperature, size, weight, movement, harm, anxiety, and resistance.Conclusions: Aspects of comfort, such as interface size and weight, represent a challenge when users present diverse ergonomics. Although the interface does not represent a hazard to the user when it is being handling, some versions present a more fragile pattern.

Olmo Alonso Moreno Franco, Chiara Lambranzi, Roberto Pitzalis, Matteo Sposito, Mahnaz Asgharpour, Daegeun Park, Christian Di Natali, Luigi Monica, Darwin Caldwell, Jesus Ortiz
Open Access
Article
Conference Proceedings

Haptic (tactual), portable, hands-free communication for body compliant interfaces

There is a growing number of technical communication devices, not least wearables, which take use of the haptic sense(s). Then tactors (vibrotactile elements, heating elements, cooling elements, pressure generators, active indentators, electro-stimulating electrodes etc.), are employed. Haptic technologies are often limited to binary, point-wise actuation (one vibrator). However, as we discuss, in a semiotic sense, this can only generate a representamen that is symbolic, thus only also concerning symbolic communication. For a richer communication coming closer to what exists for visual and audial displays also haptic communication that is semiologically iconical and indexical are of interest. We here present a classification of tactile displays. For this, we make a distinction between the stimulus (the tactor characteristics and relationship to human reception) and the spatial arrangement i.e. the geometrical placement of tactors. For wearables, in the latter case, the human body shape and anatomy is taken into concern.From this, we build two (partially ordered) hierarchies, the stimulus richness hierarchy and the spatial ordering hierarchy, respectively.Combining these hierarchies gives a (partially ordered) hierarchy of tactile displays for the human body. We show that the informatical richness is fast growing with placement complexity. However, such displays need space. Hands and fingers are sensitive for haptic stimuli but are better reserved for active touch. Instead, other body parts might be used. For this, textiles are employed. We demonstrate a chairable i.e. a portable textile based haptic display for communication to (deafblind) humans, arena spectators etc., that can be applied to furniture, thus enriching the Umwelt of the users.

Nils-Krister Persson
Open Access
Article
Conference Proceedings

Gamification to Enhance the Mini-Conference: A Case Study from Researching Digital Cultural Heritage

Recent trends since the COVID-19 era indicate a rapid increase in remotely organized conferences; however, the remote-based nature of these types of events has gained notoriety for a lack of appeal particularly due to long and exhausting sessions without physical contact. On the other hand, previous research has demonstrated several benefits to well-designed games and gamification such as its ability in creating a state of flow by instilling motivation and rewarding its participants for overcoming challenges. As a case study in the cultural heritage sector, we organized a day-long remote conference known as the mini-conference held among members of a consortium to which we belong. The mini-conference applied gamification in combination with other relevant methodologies using online collaboration tools.This remotely organized event employed four (4) collaborative workshops conducted by the different consortium partners. The results of the workshops presented in this paper employed gamification and were based on qualitative engagement, group participation and outputs emanating from each of the activities. They point towards the positive effects of gamification in drawing interest and enhancing engagement among the remotely located participants.The contributions made by this paper include unique insights to the ongoing research on remotely organized conferences, especially through the purview of gamification. In addition, the paper also sheds light on methods that could be employed by museums within the domain of cultural heritage. These might be relevant to the “post-COVID-19 era” in which hybrid engagement consisting of physical and remote collaboration is becoming the norm

Gautam Vishwanath, Lily Diaz-kommonen
Open Access
Article
Conference Proceedings

UX Sustainability in AI-infused Objects: a systematic literature review of available tools for Designers

The rapid integration of AI-infused objects into our daily lives, as part of the growing Internet of Things (IoT) ecosystem, is transforming common appliances into sophisticated and interconnected systems (ITU, 2020). With projections indicating an increase from 5 billion objects in 2020 to over 200 billion by 2030 (CISCO, 2020), these AI-infused objects create expansive networks of data-consuming devices that persist indefinitely (Crawford, 2018). This surge necessitates a deeper understanding of their ongoing environmental impact, particularly during the use phase. Recognizing the potential for user experience Designers to adjust interactions to mitigate the environmental impact during the use phase of AI-infused objects, we conducted a systematic literature review to pinpoint the Design tools that can assist Designers in this effort. Our systematic literature review aims to identify Design tools that evaluate the sustainability of User Experience in IoT products. We analyzed 24 sources dedicated to sustainability from a User Experience perspective, and 22 that assess UX in IoT devices. The findings reveal a strong focus on product-focused evaluation tools, with general emphasis on User Experience and the usage ecosystem of these objects. As AI-infused objects become increasingly prevalent, it is essential for Designers to gain a comprehensive understanding of the environmental impacts and their cause. This awareness could lead Designers to integrate both technological advancements and environmental considerations effectively into their Design process.

Alice Paracolli, Venanzio Arquilla
Open Access
Article
Conference Proceedings

Data Visualization in the Public Energy Sector: A Study on User Experience and Satisfaction

This study delves into the analysis of how data visualization impacts user experience (UX) when interacting with public electrical energy data. In the era of big data, the volumes of information on energy generation, distribution, and consumption are expanding exponentially. This surge underscores the urgency for presentation techniques that not only simplify complex datasets for the lay audience but also improve engagement and comprehension. Thus, the study aims to bridge the existing knowledge gap by identifying effective data visualization strategies that enhance the public’s ability to understand intricate data, thereby supporting informed decision-making and heightening awareness about energy sustainability. Adopting a mixed-methods approach, the study integrates extensive literature reviews with empirical usability testing involving 30 participants. To complement the quantitative findings, qualitative insights were extracted from interviews and focus groups, aiming to capture user preferences, challenges encountered, and suggestions for improvement. This analysis covered the effectiveness of various visualization components, including filters, information hierarchies, graphical elements, and data diversity, in facilitating an intuitive grasp of electrical energy data. The study showed a correlation between intuitive visualization techniques and the improvement of UX metrics such as engagement, comprehension, and satisfaction. Key findings emphasized that features such as interactive filters and good information hierarchies are instrumental in empowering users to effectively navigate and interpret electrical energy data. The study culminates in the formulation of eleven targeted guidelines for the development of user-centric data visualizations within the public energy sector.

Amanda Lentez, Gabriela Mager
Open Access
Article
Conference Proceedings

The Probable Impact of Social Media on Your Brain

This study aimed to investigate the differences in brain waves during visual (most-liked) social media networking image fusion acceptance or viewing of social media (YouTube, Blog, and Instagram) and low-liked SNS (“low liked”). The study follows a 2 (low-liked SNS and high-liked linked) × 3 (genre-YouTube, blog, and Instagram) research design of the brain wave responses. The brain wave responses were measured using an electroencephalogram by recording alpha (α) waves (8–12.99 Hz) and beta (β) waves (13–29.99 Hz). The different parts of the brain (frontal, temporal, and occipital lobes) were also measured to compare the response differences with the stimulus.The experimental study was based on a statistical analysis of the electroencephalogram responses obtained from 60 subjects. The brain wave differences between the low-liked SNS and high-liked social media were measured first. Thereafter, the responses were measured using a 2 × 3 experimental design to measure the differences in brain waves according to the SNS type (YouTube, Blog, and Instagram). The subjects’ brain wave responses were measured after viewing low-liked SNS and high-liked social media. Social media content with similar messages can be categorized into the following categories: YouTube, Blog, and Instagram.

Sang Hee Kweon, Bo-young Kang, Jihyun Ryou
Open Access
Article
Conference Proceedings

Automated Visualization for Visual Analytics: Trends, Challenges, and Opportunities

Visualization, as a major approach of visual analytics, involves many human interaction techniques, especially in terms of how individuals communicate, comprehend, and interpret information. Creating visualizations is a tedious process and requires skill, but automatic data visualization technologies have made it easier to create visualizations. They completely changed the landscape of data analysis and decision-making processes. As the demand for effective and efficient visualization solutions grows across diverse sectors, researchers and practitioners have developed a plethora of autonomous systems aimed at transforming raw data into meaningful visual representations. This paper investigates the methodologies utilized by these systems, categorizing them based on machine learning approaches combined with various data inputs, template-based approach, and other technique/algorithm-based approach. We collected 31 top-tier journal papers in the field and shed light on the diverse techniques employed in generating visualizations automatically, enhancing our understanding of their capabilities, compatibility, and usability across various contexts. Our survey aims to provide insights into the strengths, limitations, and potential areas for future exploration in automatic data visualization, offering guidance to practitioners, researchers, and developers in selecting appropriate techniques for their specific needs and datasets. By systematically examining these systems and pinpointing areas for improvement, we contribute to the advancement and refinement of automatic data visualization methodologies, fostering progress in this dynamically evolving domain.

Vinay Kumar Uppalapati, Bo Sun
Open Access
Article
Conference Proceedings

Classification of uncertainties in agile development of mechatronic systems

Agile methods are increasingly important for developing mechatronic systems in dynamic and volatile environments. These methods help development teams to deal with uncertainties in the development process and utilize them as opportunities. One feature of agile methods is the active involvement of developers in the flow of communication and information, which has a positive effect on the quality of decision making in terms of the development process. It is essential that the developer understands, accepts, and respects the uncertainty in the development task/process to realistically evaluate development scenarios and make well-founded decisions. Tailor-made approaches are required to deal with uncertainties in the development process, as the causes of these are manifold. This paper is based on extensive literature research, analyses of agile development processes at industrial partners and a series of studies on the agile development of physical products that have been carried out regularly for six years. The aim is to differentiate uncertainties to be able to utilize and adapt the artefacts and activities employed in agile development to deal with uncertainties more effectively.The aim is to evaluate the artefacts (e.g. increment, backlog, prototype...) and activities used in agile development in terms of their potential to illustrate and deal with existing uncertainties. It will be of particular importance here which views the individual roles in the development process (product owner, agile master, developer) have on existing uncertainties and how these are interpreted as a consequence. Conversely, it is important to derive recommendations for designing artefacts and activities in agile methods in order to support communication and information flows in the best possible way.

Kristin Paetzold - Byhain, Franziska Scharold
Open Access
Article
Conference Proceedings

Interpolation and Depth Extraction: A Case Study of Shan Shui Artwork Generated by AI

Traditional Shan Shui artworks (Chinese landscape paintings) have been static representations of the beauty and tranquillity of landscapes, and they have a long history and significance in Chinese art. The advancement of artificial intelligence (AI) technologies brings new possibilities to artwork creation and innovation to tradition. This study proposes using AI technologies, specifically artificial neural networks and computer vision, to learn from traditional paintings, generate new landscapes and extract depths in Shan Shui paintings. The research aims to go beyond using AI technology solely to create new artwork. Instead, it explores the ability of AI to generate dynamic landscapes with perspectives, allowing more immersive and engaging experiences, and through analysis of the depths embedded in the AI-generated Shan Shui paintings, trying to gain insights into understanding interpolation of spatial and dimensional aspects in the work and address the limitation of 2-dimension in art. This research signifies the convergence of art and technology, explores novel ways of creating and viewing traditional Shan Shui paintings, and explores the possibilities of understanding the landscapes generated through the lens of AI and computer vision technology.

Lai Man Tin
Open Access
Article
Conference Proceedings

Enabling Factors in Complex Operations. Lessons from Jazz

The contemporary world is facing a multitude of complex problems that are often rooted in the solutions of the past. Despite the ubiquity of systems in human activity, systems thinking and systems sciences are not widely incorporated into mainstream education curriculums. As a result, the lack of comprehensive understanding of systems and their rules has led to an increase in complexity resulting from political, economic, social, and technological factors. This has resulted in the emergence of new and complex issues that often prove to be insurmountable. Even sensitive domains such as security and defence have been affected, as their operations are required to be carried out in the same complex environment as everyone else. To address these growing problems, which are further exacerbated by the emergence of disruptive technologies, new ways of thinking are required, necessitating non-traditional approaches. One such approach is organisational design and management. Traditional management and organisational schools of thought are ill-equipped to address the rising complexity, and hence, alternative sources of knowledge should be sought. The Jazz Organization is one such field that provides answers to complex problems. They have been studied by special operations forces and even delicate medical teams, who have derived solutions that can be adapted to their contexts.The Jazz Organization differs from most organisational forms, as it has evolved over the last 100 years without much design thought. Like nature's systems, it emerged in a somewhat chaotic manner, yet it is quite effective in harnessing complexity and delivering delicate operations, where improvisation and creativity are key. Jazz musicians do not abide by routine; in fact, they unlearn routines as a key skill. They address problem-solving by jumping into uncharted territory, seemingly without fear. They accept "trial and error" as a normal modus operandi. Their structures are flexible, continuously adapting in the face of last-minute problems. They learn together within jam sessions, providing a unique leadership lesson as there is no central leadership figure, and every musician has his own shining moment during any performance. Lastly, jazz musicians introduce disruptions on purpose, so the entire ensemble can evolve into a better unknown.The benefits of adopting some of the lessons taken from jazz are significant for businesses, governments, special services, and any organisation engaged in complex operations. By following a critical and logical thinking process, a pragmatic analysis can be presented, and transformational action can be suggested. This alternative approach to organizational design and management can help address the growing problems that traditional management and organizational schools of thought are ill-equipped to manage.

Pedro Água, Vítor Conceição
Open Access
Article
Conference Proceedings

Smart IoT soundproofing panels for enhanced environmental comfort

In the context of Ambient Assisted Living, the SISSI project aims to integrate soundproofing panels with IoT technologies, developing a new modular system to improve the comfort of people living and working in shared environments by taking advantage of the acoustic properties of the panels and the automatic monitoring of some relevant environmental variables. To reach a satisfying solution the need to experiment with different technologies arose, and thus the team needed to share observations, problems, and solutions right from the design phase. The first step was checking if perforating the company's current sound-absorbing panels and incorporating electronic components would affect their efficiency, measuring the material's performances in the laboratory to verify its sound absorption value.Measurements were conducted in compliance with ISO 354 standards, assessing both types of sound-absorbing materials in various configurations. They show that arranging the material in a checkerboard pattern or in "thinned" lines is more advantageous in terms of absorption. Indeed, the laboratory tests have shown that a smaller amount of material results in better sound-absorbing characteristics. With this data, the final IoT panel will be more sustainable because less material can be used.In the second step, new panels with integrated sensors to monitor temperature, humidity, CO2, brightness, and people's presence were tested. Based on the data collected, the team defined the functions of the panel, which will be able to monitor the level of air oxygenation and control room or desk brightness level and to switch on or off when the user is present, thus reducing energy consumption.The experimental results changed the redesign of the panels, which now feature accessible electronic components and an interior that is not fully packed with material. Furthermore, the system is designed to integrate additional elements, such as lighting and electronic devices, for seamless interaction with the surrounding environment. Importantly, the sound-absorbing panel system will also provide clear user signals about the monitoring status, enhancing comfort.

Luca Casarotto, Lisa Battagliarin, Filippo Carnovalini, Marco Marigo, Giulio Pitteri, Mauro Longo, Carlo Manara, Jacopo Gonzato, Andrea Pavan, Antonino Di Bella, Antonio Rodà
Open Access
Article
Conference Proceedings

Document Sharing without Internet Connectivity during Study Abroad Programs

With the increasing demand for study abroad trips, students and faculty require a streamlined platform to manage assignments and surveys during the trip. It is common for students studying abroad to lack a reliable internet connection, making it challenging to share and access documents efficiently. This is especially true in countries with underdeveloped areas with poor connectivity infrastructure. Our mobile application, UC Transform (originally “Woforo”, linked below) addresses this issue by offering a one-stop-shop platform for accessing all assignments without requiring an active internet connection. Teachers can build courses, create assignments, and track progress using visual graphs. Students simply join with a code and retrieve their course materials online. Once connected to the internet, they can download the assignments and store them locally on their device. Throughout the trip, students can access the materials and provide their responses. Upon regaining a stable internet connection, students can upload their answers for review by professors. We utilized the Flutter and Dart framework for the User Interface deployed on iOS, Android, and Web Platforms, while leveraging Google Firebase for authentication and data storage. In this paper, we introduce the challenges faced by the students and educators, our methodology/ process of designing and developing UC Transform Application as a solution and sample case study exploring the scenario.

Saumick Pradhan, Nathan Wick, Cedrick Kwuimy
Open Access
Article
Conference Proceedings

Integrating space syntax methods in building environmental simulations and urban studies to enhance designer's critical reflective practice.

The aim of the study assesses how architecture students reflectively evolve their procedural (tacit) knowledge, iterate innovative design strategies and logically link simulation modeling outcomes to develop synoptic synthesis with architectural understanding. A model of Reflective Synthesis Design Cognition (RSDC) is developed that extends Donald Schön’s seeing-moving-seeing model of reflection in action with material of a design situation. Two design pedagogy approaches were developed to test the validity of the RSDC model through the prototyping of student application of simulation modeling tools commonly used in building environmental performance and urban studies. The first trial required young designers to adapt a variety of design simulation modeling approaches to discover and transform the environmental performance of their architecture studio project, with a second trial required students to investigate the urban spatial morphology surrounding their project site. The two trials integrated an unfamiliar methodology, space syntax undertaking modeling with a variety of depthmapX tools. Research methods use in this study include, content analysis of the simulation modeling outcomes in order to classify the formative application of simulation modeling to test design strategy, with an investigative on-line survey questionnaire exploring user experience and self-identification of psychometric processes. Findings highlight the need for descriptive studies examining referential reflection, qualitative assessment reflection, and summative versus synthesis constructivist knowledge formation.

Deborah Middleton
Open Access
Article
Conference Proceedings

AdTech’s AI Appetite: A Case Study in Advertisers’ Perceptions and Concerns of AI Integration

As artificial intelligence (AI) technologies continue to advance, the integration of AI into business operations, particularly into business-to-business software-as-a-solution (B2B SaaS) organizations, presents both opportunities and challenges. This paper addresses the critical need for understanding the potential benefits and risks of adopting AI, focusing on the perspectives of both B2B customers and employees. The study is particularly relevant in the context of advertising, where AI plays a significant role in shaping business strategies and consumer experiences but can also introduce financial, legal, and reputation risks. While existing research highlights potential consumer concerns and potential benefits, there is a notable gap in understanding the adoption phase from the perspective of B2B businesses, particularly within regulated industries like advertising. Our study brings in the perspectives of the marketers using the AI tools and the advertising technology employees that create, adopt, and implement the AI tools. We argue that these perspectives are vital since marketers, as the customer of the advertising technology tool, determine the success of the tool and employees, as the experts of the product, influence what ultimately gets built. As UX researchers at LiveRamp, a B2B SaaS company operating in the ad tech space undergoing this AI adoption phase, we conducted a comprehensive survey study with 469 customers and 166 employees to inform our own AI strategy. With this survey, we investigate various aspects of AI adoption, including perceptions, awareness, utility, concerns, barriers, and preferred levels of automation/transparency. We also capture these perspectives specifically along the various steps of the actual advertising user journey to better understand where we should invest in AI first and where we should not introduce it. Some preliminary findings showed that while customers are legitimately concerned about privacy, this concern is only the top priority in theory rather than in practice. For actual implementation, privacy concerns are overshadowed by technical limitations and concerns over accuracy. In contrast, employees are much more concerned about privacy and ethical data use. Some of the most passionate concerns were voiced by employee AI-advocates concerned over failing to adopt AI quickly enough and AI-averse customers who worry about the accuracy of the AI. While there is a general inclination towards seeing AI's benefits as outweighing its risks, there is also a notable level of uncertainty or neutrality among respondents too, especially among our customers. We plan on furthering these insights by performing a correlation analysis, using Spearman’s Rank-Correlation Coefficient, on the survey results to test whether there is a significant correlation between prior AI experience or technical proficiency and concerns/willingness to adopt AI. We believe this study serves as a valuable case study for other B2B SaaS businesses navigating the complexities of AI adoption in the advertising sector. Furthermore, the study contributes to the broader Human-Computer Interaction (HCI) community by shedding light on the top concerns, barriers, and perceptions associated with AI integration, emphasizing the necessity of considering both customer and employee perspectives in the evolving landscape of AI adoption.

Rachael Boyle, Ruslana Pledger, Hans-frederick Brown
Open Access
Article
Conference Proceedings

Privacy Policy Analysis and Evaluation of Mobile Psychological Consultation Services in Saudi Arabia

Psychological consultation apps have been increasingly used in the last few years. These services collect a variety of sensitive personal information. Typically, a privacy policy is the main way to reduce users’ concerns about sharing personal health information. However, psychological consultation apps are considered an emerging service and their privacy practices have not been fully explored. This study analyzes and evaluates the privacy policies and Terms of Service (ToS) agreements of four Saudi psychological consultation apps, focusing on seven key privacy practices: types of collected information, the purpose of data collection, data sharing, data ownership, data retention, data storage and protection, and notifications about policy and ToS updates. Overall, the findings indicate that the privacy policies of these services must be improved to better inform users, particularly regarding the purpose of collecting their data, with whom the data are shared, and what data are archived. This paper also provides a set of implications to improve the existing privacy policies of psychological health apps.

Abdulmajeed Alqhatani
Open Access
Article
Conference Proceedings

Human Detection Method by 3D-LiDAR with Low Calculation Costs

Since the COVID-19 pandemic, Japanese industry has been facing a labor shortage in various fields. The security sector, in particular, has a severe labor shortage due to the harsh working environment, which involves working early in the morning, at night, and outdoors. Due to the effects of COVID-19, facilities have been closed, price competition among security companies has also had an impact, and salaries are low and career development is difficult. Even in relatively open spaces such as university campuses, patrols are necessary from a safety perspective. University security operations are also being affected by the lack of security guards. Therefore, it is necessary to reduce the patrol duties of security guards as much as possible. They should patrol frequently, especially at night, and it is effective to have robot carts patrol. Robot technology is developing and it is becoming possible to perform not only simple tasks but also tasks that involve interaction with humans. In particular, robots are expected to be introduced in patrol security, which requires a large number of personnel, as much of the work involves confirming that there are no problems. In Japan, for example, robots that serve food at restaurants move around in the flow of people . In terms of security, if it cannot be confirmed by robots that there is no problem, a security guard is required to go and check. In order to reduce such cases, improving the accuracy of confirmation is an absolute requirement. In addition, it is necessary to reduce the cost of introducing and operating the robot as much as possible. Technology for recognizing people using cameras mounted on robots and 3D-LiDAR(Light Detection And Raging) has already been established and is in use. However, no technology has been established for use in poorly lit areas or by low-cost 2D-LiDAR recognition. Several methods were proposed for recognizing people using 2D-LiDAR. However, there were some conditions and problems with accuracy. In this paper, we propose a method for human identification that utilizes only limited information from the point cloud information obtained by 3D-LiDAR. Specifically, when it finds information that differs from the background information, it determines the possibility of a human being based on the distance, and improves its accuracy by moving the robot closer. Criminals and other malicious people will flee. If this is not the case, by notifying the office, it can be used to call out remotely. We have evaluated our method from some aspects which are distance between robots and humans, number of pointcloud data. As a result, we show that by setting appropriate parameters, it is possible to make accurate detection.

Haruki Mochizuki, Ryozo Kiyohara
Open Access
Article
Conference Proceedings

Sexting, age and digital vulnerabilities

Despite popular misconception it is not only young people that are sharing nude pictures and videos. There are a number of studies targeted towards the younger generation about their sexting, but few on older age-groups. In general, younger people take more risk than older people, and some seem to care less about possible negative consequences. For this study we commissioned a market research company to collect data from a national population, with a representative sample from 16 to 69 years old, in total 1071 citizens. We used binary logistic regression for the analysis of responses, a method that can be used to predict a categorical dependent variable – in our case whether a person has been sexting the last 12 months or not. In the study we included the following independent variables: gender, education, self-efficacy; the cognitive reflection test (CRT) to distinguish between a intuitive versus analytical decision style; Machiavellianism, to distinguish a personality trait characterized by manipulativeness and deceitfulness; willingness to share personal data, and finally whether the citizens had experience of ID-theft or credit-card misuse within the previous 12 months. Our results show that the ID-theft/credit-card variable was a significant predictor of sexting for the age-groups 16-29, 30-39 and 50-69 years old. For youngest group, the manipulativeness and deceitfulness trait is also a predictor, whereas for the oldest group, the intuitive decision style a high willingness to share personal data are also significant predictors

Ingvar Tjostheim, Chris Wales, John A Waterworth
Open Access
Article
Conference Proceedings

GoodMaps: Assessing an Indoor Navigation App Built on Camera-based Positioning

This paper presents GoodMaps, an AI-driven indoor navigation tool, and chronicles findings from formative focus groups and user acceptance testing with a diverse group of participants. GoodMaps is built on camera-based positioning integrated with a smartphone app that provides turn-by-turn navigation indoors. Originally designed to support blind and low-vision users in independent indoor navigation, GoodMaps was redesigned in 2023 to help all people navigate safely and efficiently with dynamic routing instructions, orientation aids, visual maps, augmented reality, and landmark recognition. This paper shares key challenges, tensions, and opportunities in designing assistive tools for differently-abled users and app-based navigation solutions.

Jennifer Palilonis
Open Access
Article
Conference Proceedings

Deep Surface Liquid Crystal Displays for Extended Reality Applications

Representing depth on a surface has been a design concern since at least the Renaissance. And yet, despite this long history, 3D displays have not become widely adopted. However, with the emergence of mixed reality applications, the development of new modalities for providing depth to displays has become even more relevant. We present a novel design that addresses these challenges by employing layered transparent LCD screens in configuration, which we call Deep Surface Liquid Crystal Displays (DS-LCD). DS-LCDs require no additional artifacts such as anaglyph glasses. Drawing on both stereoscopic and volumetric approaches, we present the DS-LCD prototype and discuss the visual elements that create the “deep surface” effect. We then describe the initial software applications that were developed to validate the prototype, as well as our initial user studies. We conclude with speculation about future work and applications.

Ian Gonsher, Maya Magavi, Minji Kim, Monica Bhyrappa, Claire Yang, Selia Jindal, John Finberg
Open Access
Article
Conference Proceedings

Digital Transformation for Sustainability: Industry 5.0 in UK SMEs

In the era of Industry 5.0, digital transformation presents a critical opportunity for UK small and medium-sized enterprises (SMEs) to enhance sustainability while driving business growth. This paper will explore how SMEs can leverage advanced technologies, such as artificial intelligence (AI), the Internet of Things (IoT), and collaborative robots (cobots), to achieve sustainable operational practices and meet Environmental, Social, and Governance (ESG) goals. By examining case studies of successful digital transformations within UK SMEs, the research will highlight strategies for integrating green manufacturing techniques, optimising resource use, and reducing carbon footprints. The study will also address the challenges SMEs face in adopting these technologies, including financial constraints, skill gaps, and regulatory compliance. Furthermore, it will discuss the role of government initiatives and support programs in facilitating this transition. The expected outcomes include a strategic framework for SMEs, policy recommendations, and insights into the positive impact of Industry 5.0 on workforce inclusivity and ESG performance. This research aims to provide a practical roadmap for UK SMEs seeking to navigate the complexities of digital transformation and underscores the importance of adopting innovative, sustainable practices to remain competitive in a rapidly evolving market landscape.

Mohammad Rashed Khan, Salford Business School, University of Salforfd
Open Access
Article
Conference Proceedings

Stress, Anxiety, and Depression in Young Adults: Findings from a User Diversity-based Analysis

Young adulthood is a stage of development marked by several changes in social and interpersonal relationships [1]. It is also marked by relatively frequent occurrences of stress, anxiety, and depression [2,3]. Furthermore, during the phase of young adulthood, there is a heightened vulnerability for the development of several mental health-related problems [4]. Early-onset depression is considered a more severe manifestation of the disorder as late-onset depression is linked to fewer psychosocial scars and a lower prevalence of simultaneous mental illnesses [5]. Furthermore, the presence of significant depression or anxiety throughout early adulthood may increase the likelihood of developing drug misuse or dependency later in life [6]. Therefore, analysis of stress, anxiety, and depression in young adults has attracted the attention of researchers from different disciplines in the recent past. However, none of the prior works in this area have focused on the analysis of stress, anxiety, and depression in young adults by considering user diversity with a specific focus on age group and gender. The work presented in this paper aims to address this research gap by presenting the findings of a comprehensive analysis of a dataset [7] that presents the stress, anxiety, and depression levels experienced by 95 young adults, using the Depression Anxiety Stress Scale (DASS). First, for age groups, 18-20, 21-25, and 26-30, average stress and anxiety levels were higher in females as compared to males. Second, for all these age groups, the percentages of females who experienced a higher level of depression as compared to anxiety or stress were 15%, 16%, and 33.33%, respectively - indicating an increasing trend. However, such an increasing trend was not observed for males across different age groups. Third, for all these age groups, the percentages of females who experienced a higher level of stress as compared to anxiety or depression were 80%, 64%, and 66.67%, respectively. The pattern was observed to be different for males as for all these age groups, the percentages of males who experienced a higher level of stress as compared to anxiety or depression were 41.66%, 59.09%, and 28.57%, respectively. Fourth, Pearson’s correlation was used to analyze the nature of correlations between stress, anxiety, and depression for each of these diversity groups of young adults. For the age group of 18-20, the correlation between the DASS Stress Score and the DASS Depression Score was observed to be statistically significant for males but not for females. For the age group of 26-30, the correlation between the DASS Anxiety Score and the DASS Depression Score was observed to be statistically significant for females but not for males. In addition to this, for this age group, the correlation between the DASS Stress Score and the DASS Depression Score was also observed to be statistically significant for males but not for females. Finally, a comparative study with prior works in this field is also presented in this paper to uphold its novelty and relevance.References1.Konstam, V.: Emerging and young adulthood: Multiple perspectives, diverse narratives. Springer International Publishing, Cham (2015).2.Arnett, J.J.: New Horizons in research on emerging and young adulthood. In: Early Adulthood in a Family Context. pp. 231–244. Springer New York, New York, NY (2012).3.Qualter, P., Vanhalst, J., Harris, R., Van Roekel, E., Lodder, G., Bangee, M., Maes, M., Verhagen, M.: Loneliness across the life span. Perspect. Psychol. Sci. 10, 250–264 (2015). https://doi.org/10.1177/1745691615568999.4.Kessler, R.C., Berglund, P., Demler, O., Jin, R., Merikangas, K.R., Walters, E.E.: Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the national comorbidity survey replication. Arch. Gen. Psychiatry. 62, 593 (2005). https://doi.org/10.1001/archpsyc.62.6.593.5.Rohde, P., Lewinsohn, P.M., Seeley, J.R.: Are adolescents changed by an episode of major depression? J. Am. Acad. Child Adolesc. Psychiatry. 33, 1289–1298 (1994). https://doi.org/10.1097/00004583-199411000-00010.6.Chilcoat, H.D., Breslau, N.: Posttraumatic stress disorder and drug disorders: Testing causal pathways. Arch. Gen. Psychiatry. 55, 913 (1998). https://doi.org/10.1001/archpsyc.55.10.913.7.Senaratne, H., Kuhlmann, L., Ellis, K., Melvin, G., Oviatt, S.: Anxiety Phases Dataset, (2021). Available Online: https://bridges.monash.edu/articles/dataset/Anxiety_Phases_Dataset/15176082 (accessed on 26 September 2023).

Victoria Knieling, Nirmalya Thakur
Open Access
Article
Conference Proceedings

Establishing Sustainable Health Services for the Medication of Elderly Chronic Diseases : An Analysis Based on SAPAD

Over 85% of elderly individuals suffer from one or more chronic diseases, with the primary treatment approach involving long-term use of targeted medications. The medication process for afflicted elderly individuals comprises three essential steps: medical evaluation, obtaining prescribed medication, and adhering to the prescribed regimen. Due to various factors such as environment.systems, and cognitive aspects, the average medication adherence rate among the elderly is below 45%, leading to significant loss in terms of both health and life and wastage of medical resources each year. As the aging population continues to grow, the need for sustainable and effective medication services becomes increasingly urgent. This study employs SAPAD analysis to establish touch points for sustainable health medication services. Starting from the behaviors of five typical elderly individuals with chronic diseases and employing quantitative research methods, objective issues within the service system are identified. In response to the identified issues, a design thinking approach is employed to construct sustainable health services for the medication of chronic diseases in the elderly. The aim is to mitigate the medical burden brought about by chronic diseases and actively leverage the roles of communities, pharmacies, online medical platforms, and the Internet of Things to enhance the healthcare experience for elderly individuals with chronic diseases, Furthermore, as an outcome of this research, the optimized strategies are applied to the practical design of the healthcare service system for elderly medication, with the goal of promoting sustainable well-being for the elderly and societal development.

Yuxin Sheng, Tingmin Yan, Yanhao Geng, Zijing Dai, Yinan Li
Open Access
Article
Conference Proceedings

Conceptual approach of an online correction system for the stent production

Stents are the most common form of treatment for coronary heart disease (CHD). Therefore, in Germany, in 2020, 298,557 stents were implanted. Nonetheless, they are relatively expensive. According to the German fee-per-case system, the cost of a single stent can range from 42.17 € up to 1,391.27 €. One possible reason for these costs is the lack of an automated inspection and correction system for maypole braided stents.In this paper, a concept for an online correction system of the stents’ geometry during production is proposed. In contrast to existing proposals, the concept does include the un- and re-braiding of the stent if necessary. This leads to existing errors in the stent being corrected rather than only focussing on the future braiding process. This can on the downside lead to a recursive un-braiding of the complete stent. Therefore, a recursion-prevention is included. Further, multiple options to compute the adapted take-up speed of the Mandel, including a mathematical as well as an AI-based approach, are discussed. Moreover, the concept can handle a complete description of the geometry to be produced, as well as a description based on the mandrels' take-up speed, which is more common for stent producers. All in all, the concept contains three steps. In the first steps, it is detected, if a correction is necessary and the recursion-prevention is applied. In the next step, the number of braid cells, that have to be un-braided, as well as the adapted take-up speed are computed. In the last step, the communication of the changed braiding parameters to the maypole braider, as well as the propagation of the take-up speed regarding the remaining production process, are handled.

Yuna Haas, Eric Sax
Open Access
Article
Conference Proceedings

Sustainable Use of Resources in Hospitals: A Machine Learning-Based Approach to Predict Prolonged Length of Stay at the Time of Admission

Length of Stay (LOS) and Prolonged Length of Stay (pLOS) are critical indicators of hospital efficiency. Reducing pLOS, particularly in public healthcare settings, is crucial for optimizing bed allocation, resource utilization, and overall cost containment, while also improving patient safety and autonomy. This study investigates the effectiveness of different machine learning (ML) models in predicting LOS and pLOS.Methods. We conducted a retrospective cohort study analyzing data from over 12,471 discharges from a northern Italian hospital between 2022 and 2023. Sixteen regression and fourteen classification algorithms were compared for predicting LOS as a continuous variable and as multi-class categories ("1-3 days", "4-10 days", "> 10 days"). The same models were evaluated for pLOS prediction, defined as any hospitalization exceeding 8 days. We analyzed two versions of the dataset: one containing only structured data (demographics, clinical information, and hospitalization details) and another incorporating features extracted from free-text diagnoses provided by clinicians. Only data readily available upon admission was utilized.Results. Ensemble models, combining multiple ML algorithms, achieved superior performance in predicting both LOS and pLOS compared to traditional single-algorithm models, particularly when utilizing both structured and unstructured data. Among the most influential features identified were the average LOS for same-service hospitalizations within the previous month, the number of recent transfers across wards, and the need for multidimensional geriatric assessment. Notably, incorporating text-embeddings from diagnoses led to improved results, especially in the presence of comorbidities.Discussion. Our findings provide evidence that integration of ML, particularly ensemble models, offers significant potential for improving LOS prediction and identifying patients at increased risk of pLOS, representing a helpful tool to guide healthcare professionals and bed managers in making informed decisions. Furthermore, this study underscores the importance of incorporating ML into hospital operations to address the challenges of an aging population with chronic diseases, while containing costs and streamlining patient flow, ultimately contributing to a more sustainable healthcare system.

Paolo Perliti, Anita Giovanetti, Federico Bolelli, Costantino Grana
Open Access
Article
Conference Proceedings

Systematic Gathering of Requirements for Macroergonomic Analysis and Design for Organizations in Brazil

Around the world, several organizations benefit from studies on Macroergonomics. This area of research proposes methods and tools for optimizing socio-technical systems, through the analysis and design of work systems, so that they are suitable for human beings. As a concept, sociotechnical systems refer to interactions between humans and technology, which can be as simple as a single individual using a hand tool or as complex as a multinational organization. In this way, Macroergonomics becomes an important resource for the success of organizational management because it is centered on the human being, that is, it systematically considers professional and psychosocial characteristics in the design or redesign of work systems, thus being a humanized approach in the allocation of functions and tasks. At the same time, it is observed that the main macroergonomic methods currently available in the literature were designed at a specific time and context, in this case, predominantly in the 90s and to mainly meet the demand of North American companies. Therefore, the objective of this paper is to present the process of obtaining requirements that support better performance of macroergonomic analysis and design activities, so that they adequately cover organizations in Brazil. To achieve this objective, the main method used in this research, both for data collection and analysis, was the Systematic Literature Review (SLR), which included the investigation of studies already published in indexed databases about the use of macroergonomic methods in Brazilian organizations. The Systematic Literature Review (SLR) method used was divided into six stages: 1) Definition of the research question and conceptual framework; 2) Search strategy; 3) Search, eligibility and coding; 4) Quality assessment; 5) Summary of results and; 6) Presentation of the study. The result obtained and presented in this paper is a compilation of peer-reviewed scientific studies, which were analyzed with the purpose of identifying the main characteristics, as well as the benefits and/or limitations of macroergonomic methods applied in different organizations in the last two decades. The analysis carried out generated conclusions that made it possible to draw up a list of requirements so that macroergonomic analysis and design activities can be conducted appropriately in this specific context. It is expected that these results will be useful to support the construction of a new methodological approach in the context of organizational management that meets the needs of organizations in Brazil more fully.

Elton Moura Nickel, Flávio Anthero Nunes Vianna Dos Santos, Patrícia Teixeira Parrela, Isadora Pedreira De Assis
Open Access
Article
Conference Proceedings