Artificial Intelligence, Social Computing and Wearable Technologies

AHFE International

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

Artificial Intelligence, Social Computing and Wearable Technologies

book-cover

Editors: Waldemar Karwowski, Tareq Ahram

Topics: Artificial Intelligence & Computing, Human Systems Interaction

Publication Date: 2023

ISBN: 978-1-958651-89-6

DOI: 10.54941/ahfe1004173

Articles

CHAAIS: Climate-focused Human-machine teaming and Assurance in Artificial Intelligence Systems – Framework applied toward wildfire management case study

Climate change and the resulting cascade of impacts pose a real and urgent threat to human safety. Simultaneously, products from Artificial Intelligence (AI) research have grown exponentially and show high potential towards use in climate adaptation. However, an increasingly large barrier to responsive deployment and adoption of AI tools into climate change adaptation workflows is the actionable knowledge discrepancy between the fields of AI, Human Machine Teaming (HMT), AI Assurance, and the work of climate adaptation decision makers. To ensure alignment, applications of AI to climate change adaptation actions need a framework and knowledge base that map development considerations to the decision maker workflow. This paper introduces CHAAIS (Climate-focused Human-machine teaming and Assurance in Artificial Intelligence Systems), a design standard and accompanying knowledge base detailing the necessary human element of AI interaction in the high-risk domain of climate change. CHAAIS incorporates direct user interaction, decision maker adoption considerations, and downstream implications. Our process combines accepted HMT and AI Assurance principles for ethical design while testing specific issues in their intersection in the climate change domain. Specifically, we demonstrate this process with a case study in forestry and implications for wildfire management. The goal for the CHAAIS design framework and knowledge base is to be both a living information source and an adaptable method of tailoring future climate change AI solutions for responsive deployment directly informed by climate decision makers.

Taissa Gladkova, Dhanuj Gandikota, Sanika Bapat, Kristen Allison

Conference Proceedings

The Evolution of AI on the Commercial Flight Deck: Finding Balance between Efficiency and Safety While Maintaining the Integrity of Operator Trust

As artificial intelligence (AI) seeks to improve modern society, the commercial aviation industry offers a significant opportunity. Although many parts of commercial aviation including maintenance, the ramp, and air traffic control show promise to integrate AI, the highly computerized digital flight deck (DFD) could be challenging. The researchers seek to understand what role AI could provide going forward by assessing AI evolution on the commercial flight deck over the past 50 years. A modified SHELL diagram is used to complete a Human Factors (HF) analysis of the early use for AI on the commercial flight deck through introduction of the Ground Proximity Warning System (GPWS), followed by the Enhanced GPWS (EGPWS) used currently, to demonstrate a form of Trustworthy AI (TAI). The recent Boeing 737 MAX 8 accidents are analyzed using an updated SHELL analysis that illustrates increased computer automation and information on the contemporary DFD. The 737 MAX 8 accidents and the role of the MCAS AI system are scrutinized to reveal the extent to which AI can fail and create distrust among end-users. Both analyses project what must be done to implement and integrate TAI effectively in a contemporary DFD design. The ergonomic evolution of AI on the commercial flight deck illustrates how it has helped achieve industry safety gains. Through gradual integration, the quest for pilot trust has been challenged when attempting to balance efficiency and safety in commercial flight. Preliminary data from a national survey of company pilots indicates that trust in AI is regarded positively in general, although less so when applied to personal involvement. Implications for DFD design incorporating more advanced AI are considered further within the realm of trust and reliability.

Mark Miller, Sam Holley, Leila Halawi

Conference Proceedings

TAUCHI-GPT: Leveraging GPT-4 to create a Multimodal Open-Source Research AI tool

In the last few year advances in deep learning and artificial intelligence have made it possible to generate high-quality text, audio, and visual content automatically for a wide range of application areas including research and education. However, designing and customizing an effective R&D tool capable of providing necessary tool-specific output, and breaking down complex research tasks requires a great deal of expertise and effort, and is often a time-consuming and expensive process. Using existing Generative Pre-trained Transformers (GPT) and foundational models, it is now possible to leverage the Large Language Model GPTs already trained on specific datasets to be effective in common research and development workflow. In this paper, we develop and test a customized version of autonomous pretrained generative transformer which is an experimental open-source project built on top of GPT-4 language model that chains together LLM "thoughts", to autonomously achieve and regress towards specifics goals. Our implementation, referred to as TAUCHI-GPT, which uses an automated approach to text generation that leverages deep learning and output reflection to create high-quality text, visual and auditory output, achieve common research and development tasks. TAUCHI-GPT is based on the GPT-4 architecture and connects to Stable Diffusion and ElevenLabs to input and output complex multimodal streams through chain prompting. Moreover, using the Google Search API, TAUCHI-GPT can also scrap online repositories to understand, learn and deconstruct complex research tasks, identify relevant information, and plan appropriate courses of action by implementing a chain of thought (CoT).

Ahmed Farooq, Jari Kangas, Roope Raisamo

Conference Proceedings

A Survey of Beliefs and Attitudes toward Artificial Intelligence — Practical Implications and Fictional Depictions

The relationship between science fiction (sci-fi) and Artificial Intelligence (AI) is a continuing topic of interest in academia and society, especially with the recent, rapid, real-world advances in AI research and application, most notably the emergence of generative chatbots (e.g. ChatGPT, Bard or Sydney). For this reason, we present a survey of an opportunistic sample and self-assessment of n=121 respondents regarding beliefs, perceptions, and impacts of AI as experienced in the real world, as well as depicted in sci-fi media. The results of our 17-item survey show that the majority of our respondents indicate a strong familiarity with the term AI and a lesser degree of acquaintance with AI-related technical terms and concepts (e.g., Neural Networks). In addition, participants express in a total of 255 qualitative comments a broad range of opinions and beliefs about ‘what AI is’ and ‘what AI will do’, describing AI at times as a 'marketing buzzword' and in other instances ‘as a tool to help humanity’. When asked if AI will either have an overall positive or negative impact on the respondents' lives, the majority (58%) comments that AI will indeed be overall beneficial, however, participants frequently express at the same time a contradicting view assessing both, the future opportunities and legitimate threats of AI.

Raiden Santos, Paula Alexandra Silva, Waleed Zuberi, Philipp Jordan

Conference Proceedings

Exploring the Impact of Generative Artificial Intelligence on the Design Process: Opportunities, Challenges, and Insights

Generative artificial intelligence (GAI) created a whirlwind in late 2022 and emerged as a transformative technology with the potential to revolutionize various industries, including design. Its feasibility and applicability have been extensively explored and studied by scholars. Previous research has investigated the potential of AI in different domains, such as aiding data collection and analysis or serving as a source of creative inspiration. Many design practitioners have also begun utilizing GAI as a design tool, stimulating creativity, integrating data more rapidly, and facilitating iterative design processes. However, excessive reliance on GAI in design may lead to losing the uniqueness emphasized in the field and raise concerns regarding ethical implications, biased information, user acceptance, and the preservation of human-centered approaches. Therefore, this study employs the double-diamond design process model as a framework to examine the impact of GAI on the design process. The double diamond model comprises four distinct stages: discover, define, develop, and deliver, highlighting the crucial interplay between divergence, convergence, and iteration. This research focuses on GAI applications' integration, timing, and challenges within these stages.A qualitative approach is adopted in this study to comprehensively explore the potential functionalities and limitations of generative AI at each stage of the design process. Firstly, we conducted an extensive literature review of recent advancements and technological innovations in generative artificial intelligence. Subsequently, we participated in lectures and workshops and invited experts from various domains to gather insights into the functionality and impact of generative AI. Later, we interviewed design professionals experienced in utilizing generative AI in their workflow. Data triangulation and complementary methods like focus groups are employed for data analysis to ensure robustness and reliability in the findings related to the functionality of generative AI.The findings of this study demonstrate that generative AI holds significant potential for optimizing the design process. In the discovery stage, generative AI can assist designers in generating diverse ideas and concepts. During the definition stage, generative AI aids in data analysis and user research, providing valuable insights to designers, such as engaging in ideation by addressing "How might we" questions, thereby enhancing decision-making quality. In the development stage, generative AI enables designers to rapidly explore and refine design solutions. Lastly, in the delivery stage, generative AI can help generate design concept documentation and produce rendered design visuals, enhancing the efficiency of iterative processes.This study contributes to a better understanding of how generative artificial intelligence can reshape the existing framework of the design process and provides practical insights and recommendations for contemporary and future designers.

Yu-ren Lai, Hsi-Jen Chen, Chia-han Yang

Conference Proceedings

Relationships among Personality Traits, ChatGPT Usage and Concept Generation in Innovation Design

The literature reports many evidences about the influence of personality on design activities. At the same time, Natural Language Processing - NLP - tools are gaining importance day by day in product innovation. This research investigates possible relationships among personality traits, ChatGPT usage and the generation of innovative design ideas. A Microsoft Excel workbook implementing the first release of a data analysis framework has been developed and is available for downloading. The reader can use it to carry on personal evaluations; in the near future, an updated release of the framework will allow sending the results to a cloud repository to build a large database and perform more robust statistical analyses. This will allow the relationships highlighted up to now gaining objectivity and discovering new ones.

Stefano Filippi

Conference Proceedings

Leveraging Multi-User Dungeons for Ethical AI Decision Support Systems: A Novel Approach

This paper proposes the innovative use of Multi-User Dungeons (MUDs) as a testbed for exploring and refining Artificial Intelligence (AI) ethics in decision support systems. MUDs are interactive, text-based virtual environments and offer a unique platform for studying AI behavior in a controlled yet complex environment. Our approach involves a combination of machine learning and natural language processing techniques to implement AI as a decision support system, and designs scenarios that challenge players with ethical quandaries and dilemmas. The effectiveness and ethical decision-making of players, the AI, and both together as a team are evaluated through a mix of quantitative and qualitative methods. The approaches detailed in this research aim to contribute to the broader discourse on AI ethics, stimulate a discussion on how to provide empirical evidence of AI decision-making's impact on human behavior in MUDs, and informing the design of ethically responsible AI systems in other domains.

Daniel Pittman, Kerstin Haring, Chris Gauthierdickey

Conference Proceedings

Measuring the Impact of Picture-Based Explanations on the Acceptance of an AI System for Classifying Laundry

Artificial intelligence (AI) systems have increasingly been employed in various industries, including the laundry sector, e.g., to assist the employees sorting the laundry. This study aims to investigate the influence of image-based explanations on the acceptance of an AI system, by using CNNs that were trained to classify color and type of laundry items, with the explanations being generated through Deep Taylor Decomposition, a popular Explainable AI technique. We specifically examined how providing reasonable and unreasonable visual explanations affected the confidence levels of participating employees from laundries in their respective decisions. 32 participants were recruited from a diverse range of laundries, age, experience in this sector and prior experience with AI technologies and were invited to take part in this study. Each participant was presented with a set of 20 laundry classifications made by the AI system. They were then asked to indicate whether the accompanying image-based explanation strengthened or weakened their confidence in each decision. A five-level Likert scale was utilized to measure the impact, ranging from 1 (strongly weakens confidence) to 5 (strongly strengthens confidence). By providing visual cues and contextual information, the explanations are expected to enhance participants' understanding of the AI system's decision-making process. Consequently, we hypothesize that the image-based explanations will strengthen participants' confidence in the AI system's classifications, leading to increased acceptance and trust in its capabilities. The analysis of the results indicated significant main effects for both the quality of explanation and neural network certainties variables. Moreover, the interaction between explanation quality and neural network certainties also demonstrated a notable level of significance.The outcomes of this study hold substantial implications for the integration of AI systems within the laundry industry and other related domains. By identifying the influence of image-based explanations on acceptance, organizations can refine their AI implementations, ensuring effective utilization and positive user experiences. By fostering a better understanding of how image-based explanations influence AI acceptance, this study contributes to the ongoing development and improvement of AI systems across industries. Ultimately, this research seeks to pave the way for enhanced human-AI collaboration and more widespread adoption of AI technologies. Future research in this area could explore alternative forms of visual explanations, to further examine their impact on user acceptance and confidence in AI systems.

Nico Rabethge, Dominik Bentler

Conference Proceedings

Automated generation of synthetic person activity data for AI models training

Image and video analytic methods, such as the recognition of a person's activities on the basis of given image material, are of great importance both in research and in everyday life. For such complex methods, deep learning approaches are mostly used, which require training based on a high data foundation. The main problem with data sets used for these methods is the acquisition and complex annotation of video data suitable for training a model. Further problems arising from the use of real-world data lie in the non-compliance with basic data protection issues or the representation of one-sided ethnic groups. A qualitatively and quantitatively inferior data basis also reduces the quality of the resulting model. The problems mentioned above increase the need for large amounts of data, which are correctly annotated and at the same time suitable for real world scenarios. Datasets which contain information on the used camera settings or filmed subjects are particularly rare due to the subsequent traceability of such data.The approach presented in this paper describes a workflow that realizes the generation of synthetic video data with extensive annotations in a completely automated way through several steps. The focus is on a real-time application that captures video clips by filming virtual scenarios. For the time being, the application focuses on activities performed by people, which do not interact with other objects. The basis is provided by three-dimensional character models, which are placed in the digital environment. For the recording, animations, which are also inserted into the application, are played on the models. By arranging up to 100 virtual cameras in a hemisphere around the virtual person to be filmed, it is ensured that a recording is made from as many perspectives as possible. Metadata is stored for each recording, which includes the type of activity played, the camera settings used, how character bone points change because of the animation and data on the ethnicity or physical trait of the person being filmed. The application offers numerous configuration options via a graphical user interface and a command line tool for setting up the recording and the metadata generated for each video clip. Thus, it is additionally possible to change the background and lighting of the scene, insert virtual objects or adjust the speed of the animation.With the help of a technical-functional prototype, it was shown that thousands of annotated video recordings of human activities can be created in no time. Such video data can be further processed by established models for the recognition and analysis of anatomical bone points and additionally validated with the help of the stored metadata. The developed workflow can be flexibly incorporated into different phases of model building and is thus suitable for initial training as well as for the optimization of existing training processes. In the future, the real-time application could be used for other generic image and video generation procedures. One example could be generating numerous image files of 3D-objects, which are suitable for training object classification systems.

Dominik Breck, Max Schlosser, Rico Thomanek, Christian Roschke, Matthias Vodel, Marc Ritter

Conference Proceedings

Human-Animal Teaming as a Model for Human-AI-Robot Teaming: Advantages and Challenges

Humans and animals have co-evolved for millions of years. The animal connection began with the exploitation and observation of animals by humans. Over time, regular social interactions were incorporated into the animal connection. This connection has also allowed us to utilize humans to help support and augment our skills and abilities; physically, emotionally, and cognitively. Of course, this relationship has changed over time as our connection and understanding of these animals’ capabilities has evolved as well as through the co-evolution of our species. At the same time, the future of human-autonomy teams shows a strong trend toward incorporating features to allow the human to engage with their robotic counterparts in a more natural way. Norman (2004) suggests that “products and systems that make you feel good are easier to deal with.” As the interfaces of robots, computers, and inanimate objects are designed to be more “intelligent,” humans may adapt the way they interact with, communicate, and think about such technology, treating objects more like humans. Humans (and many other animals) display a remarkably flexible and rich array of social competencies, demonstrating the ability to interpret, predict, and react appropriately to the behavior of others, as well as to engage others in a variety of complex social interactions. Developing computational systems that have these same sorts of social abilities is a critical step in designing robots, animated characters, and other computer agents that appear intelligent and capable in their interactions with humans (and each other), that can cooperate with people as capable partners, that are able to learn from natural human instruction, and that are intuitive and engaging for humans to interact with. Yet, today, many current technologies (animated agents, computers, etc.) interact with us in a manner characteristic of socially impaired people. In the best cases they know what to do, but often lack the social intelligence to do it in a socially appropriate manner. As a result, they frustrate us, and we quickly dismiss them even though they can be useful. It may instead be more useful to look at how humans interact and work with their animal counterparts. Like anthropomorphism, zoomorphism centers on attributing qualities to non-sentient beings; but in this case; it focuses on animal-like characteristics (Karanika & Hogg, 2020). In many contexts, teams are capable of solving complex problems well beyond the capacity of any one individual team member (Salas, Rosen, Burke, & Goodwin, 2009). However, not all teams are successful, and failures often come at a high cost. Why this is important is that humans often do not ascribe the same intelligence, consciousness, or abilities to animals as they do to humans and therefore may be less apt to get frustrated when it does not perform as expected. Also, understanding what different strengths and weaknesses each team member possesses will ultimately allow that team to be more successful. While animal-inspired designs have aided in improved robotic movement and manipulation, we maintain that design inspired by human-animal teaming can provide similar gains in robotic development, especially as it concerns improved human-robot interaction and teaming. As most people have far more experience interacting with animals than with robots, they are generally more able to recognize limitations in an animal’s ability to complete a task (Phillips, Ososky, Swigert, & Jentsch, 2012). In consequence, robotic designs inspired by human-animal relationships can lead to faster acceptance while fostering more effective interactions between humans and robots, as humans tap into well-established mental models, promote better understanding of near-future robots, and thus appropriately calibrate trust in near-future robotic teammates.

Heather Lum

Conference Proceedings

A method to generate adversarial examples based on color variety of adjacent pixels

Deep neural networks have improved the performance of large-scale learning tasks such as image recognition and speech recognition. However, neural networks also have vulnerabilities. Adversarial examples are generated by adding perturbations to images to cause incorrect predictions of image classifiers. The well-known perturbation attack is JSMA, which is relatively fast to generate perturbation and requires only simple procedures and is widely used in cybersecurity, anomaly detection and intrusion detection. However, there are problems with the way to perturb pixels. JSMA’s perturbations are easily perceivable by the human eyes because JSAM adds large perturbations to pixels. Some previous methods to generate adversarial examples did not assume that adversarial examples are checked by human eyes and allow larger perturbation to be adding to a single pixel. However, in situations where a deep learning model causes significant damage if it misrecognizes an input, a visual check by a human is necessary. In such cases, adversarial examples should not only cause misclassification in the image classifier system but also require less perturbation to avoid human perception of the perturbation. We propose methods to improve the JSMA problems. Specifically, it adjusts the amount of perturbation by calculating the variance between the value of the pixel to be perturbed and its surrounding pixels. If a large perturbation is added to the area of an image with a large pixel value variation, the perturbation will be imperceptible. In such case, perceivability does not increase significantly with a slightly larger perturbation. In contrast, if the large perturbation is added to the area of an image with small pixel value variation, the perturbation will be more perceptible. In such case, perturbations must be small. In our previous study, we assumed thresholds to classify the perturbations into two classes, large perturbation and small perturbation. If the variance was larger than the threshold, a larger perturbation was added; if the variance was smaller than the threshold, a smaller perturbation was added, which achieved a reduction in the amount of perturbation. However, there were still rooms of improvements of the perturbation to reduce the perceptibility. In this study, we focused on that there were differences in the perception of perturbations depending on the color of the pixel. The amount of perturbation should vary from pixel to pixel, not a fixed amount. Not only the variance of the surrounding pixels but also the variance of a larger area is calculated. By using these ratios, the amount of perturbation is varied from pixel to pixel. Experimental results using cifar-10 showed that the proposed method reduced the amount of perturbation to pixels with a misclassification success rate comparable to that of JSMA and our past method. We also confirmed that the reduced perturbation made the perturbation less perceptible.

Tomoki Kamegawa, Masaomi Kimura, Imam Mukhlash, Mohammad Iqbal

Conference Proceedings

Integrating Domain Expertise and Artificial Intelligence for Effective Supply Chain Management Planning Tasks: A Collaborative Approach

The integration of Artificial Intelligence (AI) techniques into various domains has revolutionized numerous industries, and Supply Chain Management (SCM) is no exception. This paper addresses the challenges encountered in SCM and the development of AI solutions within this context. Specifically, we focus on the application of AI in optimizing supply chain planning tasks. This includes forecasting demand, availability and feasibility checks for customer orders, supply chain network design and information flow inside the supply chain planning processes. However, the successful implementation of AI in SCM requires a deep understanding of both the domain-specific challenges and the capabilities and limitations of AI technologies. Thus, this paper proposes an overarching approach that facilitates collaboration between domain experts in SCM and AI experts, enabling them to jointly develop effective solutions.The paper begins by outlining the key challenges faced by SCM professionals, including demand volatility, complexities in inventory management, and dynamic market conditions. Subsequently, it delves into the challenges associated with developing AI solutions for SCM, including data quality, interpretability, and model transparency. To address these challenges, the proposed approach promotes close collaboration and knowledge exchange between SCM and AI experts. By leveraging the domain knowledge and experience of SCM experts, AI experts can better understand the special issues of SCM processes and tailor AI techniques to suit specific needs. In turn, SCM experts can gain insights into the capabilities and limitations of AI, allowing them to make informed decisions regarding the adoption and integration of AI in their supply chain planning operations. Furthermore, the paper discusses the importance of establishing a multidisciplinary team comprising experts from the fields of SCM, AI, and IT. This team-based approach fosters a holistic understanding of SCM challenges and ensures the development of AI solutions that align with business goals and practical constraints.In conclusion, this paper highlights the challenges in combining SCM and AI and proposes a collaborative approach to address these challenges effectively. By leveraging the expertise of both domain and AI experts, organizations can develop tailored AI solutions that enhance supply chain planning, improve decision-making processes, and drive competitive advantage. The proposed approach contributes to the successful integration of AI in SCM, ultimately leading to more efficient and resilient supply chains in the era of artificial intelligence.

Jonas Lick, Benedict Wohlers, Philipp Sahrhage, Felix Schreckenberg, Susanne Klöckner, Sebastian Von Enzberg, Arno Kühn, Roman Dumitrescu

Conference Proceedings

User Trust Towards an AI-assisted Healthcare Decision Support System under Varied Explanation Formats and Expert Opinions

While Artificial Intelligence (AI) has been increasingly applied in healthcare contexts, how AI recommendations should be explained to achieve higher user trust is yet to be determined. This study was aimed to investigate users' trust towards an AI-assisted healthcare decision support system under varied explanation formats and expert opinions. Twenty participants participated in a lab-based experiment where they were asked to complete a series of dosage adjustment tasks in chronic disease care scenarios with the help of a simulated AI-assisted decision support system. Four explanation formats and three types of expert opinions were examined. Data on subjective trust, task performance and physiological measures were collected. The results showed that explanation formats had significant effects on subjective trust, task performance and skin conductance. Expert opinion had significant effects on subjective trust and task performance. There existed an interaction effect on compliance rate between explanation format and expert opinion. It appears that AI recommendations that are explained by counterfactual reasoning way and supported by medical experts are likely to achieve higher user trust. The findings can provide references for better design of explainable AI in AI-assisted healthcare contexts.

Da Tao, Zehua Liu, Tingru Zhang, Chengxiang Liu, Tieyan Wang

Conference Proceedings

Prompts of Large Language Model for Commanding Power Grid Operation

Large Language Models (LLMs) like ChatGPT can assist people’s general workflows, where the prompt is necessary to inspire the potential of LLMs to solve problems from specified or professional domains like robotics. In the electrical engineering subject or the electric power utility industry, experienced operators and professional experts monitor power grid operation statuses and interact with the grid via human commands on the screen, and components in the grid execute the commands to keep the complex grid safe and economical operation. In this process, human experts edit commands to operate the corresponding software. Human commands are the natural language that the LLM can process. The power grid is composed of generation, transmission, distribution, and other components. Therefore, we redesign the human-computer interaction frame between practitioners and the grid via recurrent prompts to apply the LLM to generate computer programming instructions from the multi-step natural language commands. The programming instruction is executed on system components after being confirmed or revised by human experts, and the quality of generated programs will be gradually improved through human feedback. The idea of this study is originally inspired by studies on controlling individual robotic components by ChatGPT. In the future, we will apply the designed prompt templates to drive the general LLM to generate desired samples which could be used to train an LLM professional in the domain knowledge of electrical engineering to operate multiple types of software for power grid operators.

Hanjiang Dong, Jizhong Zhu, Chi-yung Chung

Conference Proceedings

Before and after lockdown: a longitudinal study of long-term human-AI relationships

Social chatbot apps with advanced capabilities for relationship development have become increasingly popular over the last few years. As millions of people around the world develop emotional bonds with AI companions, the concept of authenticity emerges as a topic of interest. This qualitative longitudinal study focuses on the experiences of people in a relationship with an AI Companion. The purpose is to understand how authenticity is constructed and identify factors that influence the development of AI relationships and contribute to their sustainability. Results indicate that human-AI relationships are shaped and transformed by factors directly related to the user, and to the sociotechnical context they are embedded in, all of which play a pivotal role in the construction and perception of authenticity.

Valeria Lopez Torres

Conference Proceedings

Interventions by Artificial Socially Intelligent Agents in Collaborative Environments: Impacts on Team Performance and Knowledge Externalization

Future Artificial Intelligence (AI) teammates will need to take on more teaming and collaborative responsibilities in human-agent teams to advance those teams' capacities and improve performance. To do so, an AI will require artificial social intelligence (ASI) in order to effectively anticipate, predict, and respond to humans in ways that take into account factors related to context, individual cognition, team structures as well as the social, interpersonal team space. Theory of Mind is a core socio-cognitive process that is fundamental to supporting these social abilities in humans, and it must be developed for agents as Artificial Theory of Mind (AToM) that can support social behavior. An agent utilizing AToM models would be able to observe and infer human behavior and update their internal models to more effectively engage with human teammates based on the context of the interaction, like humans do naturally. The research reported here explores the interactions between AI imbued with Artificial Theory of Mind and teams of human participants completing simulated Urban Search and Rescue missions. The focus of our explorations are the relationships between the advisory interventions delivered by artificial, socially intelligent agents and the mission outcomes of the teams with which they worked. The gamified Urban Search and Rescue task employed for this research consisted of two missions per team during which participants searched for, triaged, and evacuated victims of a building collapse. Each three-person team was assigned an ASI agent who interacted with them during both missions. Critically, the agents were not given omniscient knowledge of the task, such as specific locations for task-related objectives, so the advice that they delivered to teams was based entirely on their artificial theory of mind and not rote problem solving. Of primary interest to this work is the nature of the advisory interventions delivered by the agents while assisting with the rescue missions. In this paper, we focus on exploring the interventions with attention to the nature of the content and delivery, and a particular interest in the interventions associated with team communication. The results of these analyses suggest that, overall, interventions were generally associated with positive outcomes rather than negative ones. Specifically, interventions advising teams to engage in information sharing and externalizing communication tended to relate positively to outcomes. That finding indicates that even early forms of artificial social intelligence have the potential to serve as teammates as opposed to be utilized as tools, and that artificial teammates can improve team performance. Further, the correlations between communication intervention types and mission performance reflect on how artificial social intelligence can support teams to more effectively engage in teaming activities, such as communication, which can benefit team performance outcomes. These findings are an important step towards investigating the impact of agents actively engaging in teaming behaviors, demonstrating an agent’s potential benefit to teamwork by supporting team communication and, additionally, identifying what factors may have negatively impacted performance and should be avoided to improve team effectiveness.

Rhyse Bendell, Jessica Williams, Stephen Fiore, Florian Jentsch

Conference Proceedings

Artificial Social Intelligence in Action: Lessons Learned from Human-Agent Hybrid Search and Rescue

Socially intelligent artificial agents have recently shown some evidence of improving team performance when advising human teammates during the execution of time-pressured, complex missions. These agents, imbued with a form of social intelligence supported by Artificial Theory of Mind, have also demonstrated some negative outcomes associated with their approaches to delivering advice and motivating teammates to succeed. Here, we closely examine team performance outcomes associated with a simulated team Urban Search and Rescue mission in the context of interventions delivered by artificial socially intelligent agents that served as advisors to the human teammates engaged in task execution. The task studied here required some individual taskwork effectiveness as well as a notable amount of interdependent teamwork coordination. The interdependent activities provided the advising artificially intelligent teammates an opportunity to observe and intervene to improve aspects of team process. Some of the interventions delivered by the socially intelligent agents were found to positively impact performance, notably those that targeted objective data and the dissemination of information to the right individual at appropriate timepoints; however, other interventions negatively impacted team outcomes. Results showed that Motivation interventions aimed solely at bolstering the motivation of team members did not yield positive outcomes; in fact, they were found to have adverse effects on overall team performance and task execution.

Jessica Williams, Rhyse Bendell, Stephen Fiore, Florian Jentsch

Conference Proceedings

Design Process with Generative AI and Thinking Methods: Divergence of Ideas Using the Fishbone Diagram Method

In 2022, high-performance generative AI — such as Stable Diffusion and ChatGPT — were reported upon and released amid increasing momentum for the utilization of such generative AI. In the field of architecture, generative AI is expected to not only be used for task automation, but as a means of diverging ideas as well, especially in the planning stage of architectural design. However, effective application methods have not yet been reported.Therefore, this study proposes a concept-making method that combines generative AI and ways to diverge ideas in architectural design and proposes a tuning method for ChatGPT to enable more effective dialogue. In the proposed method, ChatGPT is involved as a member in group work settings that aims to create concepts and initial designs using the fishbone diagram, one of the ways to list and categorize factors and ideas to achieve goals. In addition, ChatGPT is tuned to obtain more effective factors and ideas, particularly those related to spatial composition and shapes by inputting text regarding architectural design and specific architects.The proposed method was tested via case studies that created concepts and initial designs for an actual architectural competition. The results show that external ideas obtained from generative AI inspire the fishbone diagram process. The concepts and designs created seem imaginative and appropriate for competition.

Yuhi Maeda, Jun'ichi Ito, Keita Kado

Conference Proceedings

FlexiTeams – An Interactive Visual Representation of AI-based Knowledge to Reorganize Operational Teams in Crises

Crises, such as the COVID-19 pandemic, pose unprecedented challenges for governmental or healthcare organizations as well as for the entire industry and the service sector. For instance, shifts in business areas due to increased infection control regulations led to overburdened or underchallenged units within the organizations. Thus, the flexible and highly dynamic adaptation of work processes and team organizations to the changed conditions are essential for maintaining the economic and social infrastructure. The requirements for such a reorganization are constantly changing due to the parallel process of gaining knowledge about the actual risk factors in the spread of the pandemic and require an agile reorientation, which is associated with great effort and uncertainty.For this reason, we present the FlexiTeams framework that supports decision makers to manage staff allocation and workflow organization in the context of such time-sensitive situations using conversational artificial intelligence and agent-based simulation. Agent-based modeling and simulation are established in many disciplines as a new tool for the analysis of complex systems. In social simulation, agent-based models are often used to analyze emergent effects e.g., as phenomena of social contagion. In cognitive social simulation, mechanisms of sociology and psychology are combined to generate cognitive decision-making behavior within an agent as well as group dynamic behavior between agents. This allows the study of complex socio-digital systems in which humans and (semi-)autonomous information systems cooperate in knowledge-intensive processes. However, in a crisis situation such as the COVID-19 pandemic or severe weather disasters, it is necessary not only to capture specifications of a team or to evaluate their efficiency, it is rather important to react to current situations. Indeed, it is of special interest to assemble the available work force accordingly, which may be seconded from other tasks. The flexible allocation of resources depending on a current situation is an important field of research in Distributed Artificial Intelligence (DAI). DAI deals with systems of (partially) autonomous decision makers, so-called software agents, whose behavior are largely determined by situational decision-making, negotiation and coordination during the runtime of the system. In addition to the agent-based approach, the comprehensive knowledge representation of process-oriented case-based reasoning (POCBR) is well suited for the modeling and processing of experiential knowledge about team constellations and work processes with the aim to make suggestions for adjustments in the sense of reorganizations.One major success factor to benefit in time-critical situations from the provided guidance and suggestions is to keep the human in the loop regarding both, the AI’s decisions and its simulation’s results. Thus, one part of the framework is to design a suitable interface to enable users to understand and revise the AI’s results. In this paper, we introduce the general framework, discuss its novelty and present an initial demo prototype showcasing some UI design concepts relevant to this context. For instance, an overarching dashboard is designed to represent resources, profiles, and key performance indicators (KPIs) comprising economic, social, and health status.

Dominique Bohrmann, Moritz Gobbert, Ericson Hoelzchen, Ditty Mathew, Ralph Bergmann, Thomas Ellwart, Ingo Timm, Benjamin Weyers

Conference Proceedings

The Consistency between Popular Generative Artificial Intelligence (AI) Robots in Evaluating the User Experience of Mobile Device Operating Systems

This article attempts to study the consistency, among other auxiliary comparisons, between popular generative artificial intelligence (AI) robots in the evaluation of various perceived user experience dimensions of mobile device operating system versions or, more specifically, iOS and Android versions. A handful of robots were experimented with, ending up with Dragonfly and GPT-4 being the only two eligible for in-depth investigation where the duo was individually requested to accord rating scores to the six major dimensions, namely (1) efficiency, (2) effectiveness, (3) learnability, (4) satisfaction, (5) accessibility, and (6) security, of the operating system versions. It is noteworthy that these dimensions are from the perceived user experience’s point of view instead of any “physical” technology’s standpoint. For each of the two robots, the minimum, the maximum, the range, and the standard deviation of the rating scores for each of the six dimensions were computed across all the versions. The rating score difference for each of the six dimensions between the two robots was calculated for each version. The mean of the absolute value, the minimum, the maximum, the range, and the standard deviation of the differences for each dimension between the two robots were calculated across all versions. A paired sample t-test was then applied to each dimension for the rating score differences between the two robots over all the versions. Finally, a correlation coefficient of the rating scores was computed for each dimension between the two robots across all the versions. These computational outcomes were to confirm whether the two robots awarded discrimination in evaluating each dimension across the versions, whether any of the two robots systematically underrated or overrated any dimension vis-à-vis the other robot, and whether there was consistency between the two robots in evaluating each dimension across the versions. It was found that discrimination was apparent in the evaluation of all dimensions, GPT-4 systematically underrated the dimensions satisfaction (p = 0.002 < 0.05) and security (p = 0.008 < 0.05) compared with Dragonfly, and the evaluation by the two robots was almost impeccably consistent for the six dimensions with the correlation coefficients ranging from 0.679 to 0.892 (p from 0.000 to 0.003 < 0.05). Consistency implies at least the partial trustworthiness of the evaluation of these mobile device operating system versions by either of these two popular generative AI robots based on the analogous concept of convergent validity.

Victor K Y Chan

Conference Proceedings

To What Extent Can AI Simplify Academic Paper Writing?

In the AI era, how will the work of researchers change and what will the future of the research profession be like? This paper discusses how academic paper writing can be made more efficient through AI assistance. To facilitate our discussion, we used a somewhat unusual approach. Noting that the novelty and inventive step of an invention and the originality and academic significance of an academic paper are the same, we propose a six-step model for AI-assisted academic paper writing, inspired by AI-assisted patent prior art search. On the basis of the proposed model, we present our thoughts on the future of researchers' work and the research profession in general.

Youji Kohda, Amna Javed

Conference Proceedings

A sample-based method of 3D reconstruction for plant leaf from single image or multiple images

Agricultural operations require simple, efficient and robust measurement method of three dimensional forms for the plant organs such as leaves to analyse other kinds of phenotype in detail on this basis. However, most of the existing sample-based methods reconstruct three dimensional shapes of the images for the objects of smooth surface and homogeneous materials, such as plastics, paints, ceramics, and metals, etc., rather than for the natural objects of convex-concave surfaces and varying albedo materials under the arbitrary natural lights. In this paper, it was found that the methods based on the prior model with photometric stereo superposed BRDF proposed can accurately realize the 3D modelling for plant leaf image and may reduce the cumulative error. With the differential gradient constraint and integral gradient constraint proposed, the unique solution for the normal vectors of all micro panels of the pixel projection on the leaf surface was matched by the first-order central difference equation and the iterations, and this process solved the ill-posed problem of BRDF. The experiment results showed that the average error between the height reconstructed results and the measured results of the real leaves’ height was 15% and the attenuation error was reduced by our method.

Wang Jianlun, Deng Huangtianci, Su Rina, Can He, Han Yu, He Jianlei, Hu Baoyue, Chen Husheng, Huang Sheng, Xiao Sirong, Cao Jinduo

Conference Proceedings

Computational creativity: The Innovative Thinking, Practical methods and Aesthetic Paradigms of AI-driven Design

The development of artificial intelligence has greatly unleashed AI creativity and is profoundly transforming the thinking process, practical methods, and aesthetic forms of future design innovation. This study provides an in-depth analysis of computers’ innovative thinking, design practice, and aesthetic paradigms driven by artificial intelligence, namely computational thinking in the cognitive field, computational design in the practical field, and computational aesthetics in the aesthetic field. Starting from the concept of computational thinking, the article analyzes six general processes of computational thinking, including decomposition, abstraction, algorithm, debugging, iteration, and generalization. Secondly, three common types of computational design were compared and analyzed, namely parametric design, generative design, and algorithm design. Among them, algorithm design is a generation process that generates design results through algorithm writing and rule formulation; Parametric design is an interactive process where the components of the design model are interrelated, allowing for real-time updates and modifications throughout the entire design process; Generative design is an iterative process where software generates many creative results and solutions for designers to make decisions and choices. Finally, the study analyzed the aesthetic forms and carriers of computational aesthetics. Among them, aesthetic forms include organic growth, geometric repetition, mathematical rhythm, dynamic order, heterotypic novelty, science fiction grandeur, and fractal deconstruction; Aesthetic carriers include form, structure, texture, pattern, layout, visual dynamic effects, etc. This study is a highly refinement to innovative thinking, design practice, and aesthetic paradigms in the era of artificial intelligence, highlighting important directions for future design development.

Yuqi Liu, Tiantian Li, Zhiyong Fu

Conference Proceedings

Applying Ming furniture features to modern furniture design using deep learning

Ming-style furniture is a type of classical Chinese furniture that originated during the Ming Dynasty and has developed and evolved through the Ming and Qing Dynasties to become one of the major schools of classical Chinese furniture. Traditional Ming furniture design is labour-intensive and time-consuming, and designers need to have a wealth of experience and knowledge to create high-quality pieces. However, with the rapid development of computer technology and advances in deep learning algorithms, it is now possible to use computer-aided design techniques and deep learning algorithms to extract and apply features of Ming furniture quickly and accurately.This paper proposes a new method based on deep learning and computer-aided design techniques for applying features of Ming furniture to modern furniture design. By collecting and filtering existing physical images of Ming-style furniture, we use a generative adversarial network algorithm (DCGAN) for image recognition and feature extraction, and generate modern furniture designs. The experimental results show that the algorithm can significantly improve the efficiency of designers and has good feature recognition to extract target contours and accurately obtain design features. As the number of extracted feature samples increases, the clarity of the generated images becomes higher and their generation accuracy also tends to increase. The furniture products generated by the deep learning approach have both modern aesthetics and Ming furniture characteristics, which is conducive to the inheritance and development of traditional Chinese furniture culture. The evaluation shows that the newly generated furniture products meet modern aesthetic standards. The method provides a new way of thinking and approach to the field of furniture design, with high academic and practical application value.

Yukun Xia, Yingrui Ji, Yan Gan, Zijie Ding

Conference Proceedings

Exploring the digital development path of China's cultural industry empowered by artificial intelligence technology

The digital development of cultural industry, as a national strategic plan, has become a new driving force to stimulate domestic demand and promote economic growth, and has continuously spawned a variety of new business forms and modes. Artificial intelligence（AI）as a new technology paradigm with machine intelligence and creativity, has great potential to integrate with content-heavy and highly creative cultural industries, and is of great significance in empowering the transformation of cultural industries' production, upgrading of products, and improving the quality of consumption. This paper reveals the dynamic trend of the digital development of China's cultural industry by analysing cases of the integration of AI and the cultural industry. We further propose a path for AI-enabled cultural industry development from five dimensions: content, experience, technology, operation and industry, to achieve the goal of making China's outstanding traditional culture "live" and "go out", as well as conveying the rich connotation and contemporary value of Chinese traditional culture to the world.

Chunxiao Zhu, Shijian Luo, Yu Cao, Honglei Lu, Wenrui Li

Conference Proceedings

'Design for integrating explainable AI for dynamic risk prediction in prehospital IT systems

Demographic changes in the West with an increasingly elderly population puts stress on current healthcare systems. New technologies are necessary to secure patient safety. AI development shows great promise in improving care, but the question of how necessary it is to be able to explain AI results and how to do it remains to be evaluated in future research. This study designed a prototype of eXplainable AI (XAI) in a prehospital IT system, based on an AI model for risk prediction of severe trauma to be used by Emergency Medical Services (EMS) clinicians. The design was then evaluated on seven EMS clinicians to gather information about usability and AI interaction.Through ethnography, expert interviews and literature review, knowledge was gathered for the design. Then several ideas developed through stages of prototyping were verified by experts in prehospital healthcare. Finally, a high-fidelity prototype was evaluated by the EMS clinicians. The primary design was based around a tablet, the most common hardware for ambulances. Two input pages were included, with the AI interface working as both an indicator at the top of the interface and a more detailed overlay. The overlay could be accessed at any time while interacting with the system. It included the current risk prediction, based on the colour codes of the South African Triage Scale (SATS), as well as a recommendation based on guidelines. That was followed by two rows of predictors, for or against a serious condition. These were ordered from left to right, depending on importance. Beneath this, the most important missing variables were accessible, allowing for quick input.The EMS clinicians thought that XAI was necessary for them to trust the prediction. They make the final decision, and if they can’t base it on specific parameters, they feel they can’t make a proper judgement. In addition, both rows of predictors and missing variables served as reminders of what they might have missed in patient assessment, as stated by the EMS clinicians to be a common issue. If given a prediction from the AI that was different from their own, it might cause them to think more about their decision, moving it away from the normally relatively automatic process and likely reducing the risk of bias.While focused on trauma, the overall design was created to be able to include other AI models as well. Current models for risk prediction in ambulances have so far not seen a big benefit of using artificial neural networks (ANN) compared to more transparent models. This study can help guide the future development of AI for prehospital healthcare and give insights into the potential benefits and implications of its implementation.

David Wallstén, Gregory Axton, Anna Bakidou, Eunji Lee, Bengt Arne Sjöqvist, Stefan Candefjord

Conference Proceedings

AI-Enabled Semantic Modeling for Enhanced Boardnet Integration in Automotive Design

The integration of artificial intelligence (AI) techniques in the automotive industry has revolutionized various aspects, including object identification, hazard recognition, speech recognition, and driver assistance. In this scientific paper, we propose a novel approach that leverages AI to enhance the integration of boardnet design in the automotive domain. The primary objective of the boardnet is to ensure reliable power distribution, efficient energy management, data communication, effective sensor integration, precise actuator control, and the integration of advanced features while prioritizing safety, reliability, and optimal performance of the vehicle's electrical system.Our proposed model utilizes inference-based AI techniques, incorporating both external and internal routing AI within a semantic framework. By aligning the model with a top-level ISO 26262 standard definitions ontology, we establish a systematic systems and electronics semantic framework that seamlessly integrates with existing design processes. The model accommodates the expertise of system engineers and knowledge engineers, enabling the harmonious integration of their distinct approaches.Furthermore, this paper explores the automation of design process gaps through the deduction of valuable information. By employing OWL DL 2 and logical axioms, we demonstrate the reasoning capabilities of our approach, highlighting its advantages in terms of speed, usability, and integration within the overall design process.The integration of AI and semantic modeling in boardnet design facilitates intelligent decision-making, optimization, and automation. The semantic framework enables a comprehensive understanding of the boardnet and its components, improving the efficiency and effectiveness of the design process. The proposed approach contributes to the advancement of automotive design and development practices, enhancing power distribution, energy management, data communication, sensor integration, actuator control, and the integration of advanced features.To validate the effectiveness of our approach, we conducted a series of experiments and evaluations. The results demonstrate that AI-enabled semantic modeling significantly improves the boardnet integration process. It facilitates improved power distribution, makes the energy management more pervasive, the data exchange among components seamless, and precises regulation of actuators. Moreover, the integration of advanced features becomes smoother, providing enhanced functionalities to vehicles while maintaining safety, reliability, and optimal performance.Additionally, we highlight the practical implications of our research by discussing real-world use cases. By using property classifications, inverse object properties, property chains and complex class expressions, the design process is amended by filling additional and complementary information which reduces development time. The benefits extend to increased vehicle performance, and reduced maintenance requirements.In conclusion, this paper establishes the significance and potential of AI-enabled semantic modeling for boardnet integration in automotive design. By leveraging AI techniques and semantic frameworks, engineers and researchers can achieve superior design outcomes, drive innovation, and meet the evolving demands of the automotive industry. The experimental results and real-world use cases presented herein provide a solid foundation for further exploration and adoption of AI in boardnet integration, contributing to the advancement of automotive technologies and the realization of intelligent, efficient, and reliable vehicles.

Frank Wawrzik, Johannes Koch, Sebastian Post, Christoph Grimm

Conference Proceedings

Auto3DBuilder: An automatic 3D building modeling tool from 2D drawings

This paper presents a novel 2D to 3D building modeling tool seamlessly integrated into our Smart City Lab platform. The tool, designed for simplicity and user-friendliness, enriches existing LoD1 buildings without requiring modeling expertise. Leveraging Grasshopper as a backend and utilizing RestAPI interfaces, it transforms 2D architectural drawings into detailed 3D models. We delve into the methodology, showcasing how users can effortlessly generate intricate building models. The potential applications extend to urban planning, simulations, and innovative technologies like AR, VR, and the metaverse. Acknowledging current limitations, we outline prospects for future advancements, including accommodating more sophisticated building designs and enhancing interoperability for extensive data integration. This tool marks a significant step towards extensive and interactive urban development and planning.

Amartuvshin Narangerel, Minjin Myagmarjav, Woong Hee Lee, Dongwoo Lee

Conference Proceedings

Analysing the Effectiveness of a Generative Adversarial Network Model for the Creation of New Datasets of 3D Human Body and Garment Sizes in the Clothing Industry

Apparel designers and manufacturers are now using virtual garment simulation technology to evaluate 3D prototypes in virtual environments, which reduces the waste of raw materials in the sampling process. With the immediate visualization of the 3D prototypes, designers and manufacturers can communicate with each other to adjust the virtual garments seamlessly, and thereby the production process has become simplified using simulation technologies. Nevertheless, there are several limitations to the current practice. Apparel companies do not have a universal sizing standard, which leads to problems because customers need to identify their sizes in different stores, and a high return rate is expected in this case. Additionally, the psychological preferences of the wearers are not taken into account when evaluating fit. Production teams in apparel companies are only concerned with the physical fit of their targeted customer groups; they neglect the actual will of a specific customer. For example, some may like to wear oversized garments, and a just-fit size is not what they want. It is valuable to find a method to adapt the psychographic orientations of the customers to the design and production process of a garment. Therefore, we had proposed our method for developing a virtual garment fitting prediction model to predict the garment pattern parameters with anthropometric data and psychographic orientations of subjects, and previous work had proven that the prediction model has high accuracy and stability. Nevertheless, a limitation was found in that the subject data was difficult to obtain. It would be advantageous if there were more data to test in the prediction model. Thus, this study proposes the build of generative adversarial network (GAN) models to generate new body dimension data and garment parameter data. The new datasets produced by the GAN models would be favourable for an improvement in the virtual garment fitting prediction model with more training and testing data to be processed. Moreover, the synthetic datasets can be employed by designers to do research in their garment evaluation process since they have more data on similar body dimensions and preferred garment sizes to assess. A more comprehensive appraisal of the garment fit can be attained by this approach, which accelerates the design process in the apparel production stage.

Nga Yin Dik, Wai Kei Tsang, Ah Pun Chan, Kwan Yu Lo

Conference Proceedings

The Impact of AI Transparency and Reliability on Human-AI Collaborative Decision-Making

Human-AI collaborative decision-making has become a prevalent interaction paradigm, but the lack of transparency in AI algorithms presents challenges for humans to understand the decision-making process. Such lack of comprehension can lead to issues of over-reliance or under-reliance on AI recommendations. In this study, we focused on a human-AI collaborative income predicting task and investigated the influence of AI transparency and reliability on task performance. The results revealed that when AI reliability was high (75% and 90%), transparency had no significant effects on human decision-making. However, at a lower level of reliability (60%), higher transparency levels led to increased compliance with AI suggestions, thereby demonstrating a persuasive effect. Further analysis indicated that compliance rates only improved when AI made correct decisions, rather than when AI made incorrect ones. However, transparency did not significantly impact humans' ability to correctly reject erroneous recommendations from AI, suggesting that increasing transparency alone did not enhance humans’ error detecting ability. In conclusion, when the reliability of AI is low, heightening transparency can promote appropriate dependence on AI without elevating the risk of over-reliance. Nevertheless, further research is necessary to explore effective strategies that can assist humans in identifying AI errors effectively.

Xujinfeng Wang, Yicheng Yang, Da Tao, Tingru Zhang

Conference Proceedings

Design of new routing algorithm and embedding for Hierarchical Hypercube Networks

Mesh, hypercube, HHN, bubbls-sort, star, transposition, and macro-star graphs have been proposed as interconnection networks used in high-performance parallel computer structures. A hypercube expresses a node with n binary numbers, and has an edge between 1-bit other nodes. A hypercube is an excellent network from a graph-theoretic point of view, such as node symmetry, fault tolerance, recursive scalability, and Hamiltonian cycles. However, compared to the increase in the number of nodes, the number of edges increases proportionally, so the network cost is not good. The HHN graph was proposed as a network that improved the network cost by improving the disadvantages of the hypercube. HHN graph uses hypercube as a basic module. The HHN graph is a network that has improved network cost by designing it to have a hierarchical structure based on a hypercube. HHN graphs have a simple routing algorithm with fewer branches and fewer links than hypercubes. Although HHN's routing algorithm has a simple advantage, it has a disadvantage that the path length is long via unnecessary nodes. In this study, we propose a new routing algorithm that improves the path length of the HHN graph and analyze its efficiency. The improved routing algorithm proposed in this study has the result of improving the existing algorithm by 30% on average. In addition, we analyze the embedding of one interconnection network into another is a very important issue in the design and analysis of parallel algorithms. Through such embeddings the algorithms originally developed for one architecture can be directly mapped to another architecture. This paper describes novel methods for the embedding of hierarchical Hypercube networks in the hypercube to minimize the dilation and the expansion costs.

Hyeongok Lee

Conference Proceedings

Continuous personal monitoring and personalized hydration recommendations with wearable sweat sensors to prevent occupational heat stress

Exposure to extreme heat during physical exertion may impair cognitive and physical abilities commonly known as heat stress. Industrial workers are vulnerable to the effects of extreme heat due to increasing ambient temperatures, tasks with radiant heat exposures, work intensity, and added personal protective equipment (PPE) burden. New wearable sweat sensors may help mitigate heat stress by monitoring physiological signs of dehydration and provide real-time hydration recommendations. As wearable sensors are introduced into the workplace, this study aims to understand whether continuous personal, physiological monitoring is a better indicator of heat stress risk than current, traditional industrial hygiene, environmental monitoring.

Michelle Stewart, Andrea Tineo, Benjamin Woodrow, Michael Wasik, Selina Chan

Conference Proceedings

Effects of Gain/Loss Messages on Reinforcing Motivation to Sleep

To improve sleep habits, we will create messages to raise awareness of sleep and examine the effects of messaging on sleep habits. Japanese people, especially children, and workers, sleep less than their counterparts, both men and women, in other countries. As a result, some people "sleep in on weekends," getting a lot of sleep on weekends to secure more sleep. Then, the rhythm becomes disturbed, and it becomes challenging to re-synchronize with the schedule. Therefore, it is necessary to improve sleeping habits to secure a certain amount of sleep. This study will utilize a messaging approach, gain/loss-framing messages. Then, we will investigate which message is more effective for sleep habits according to each participant's values about sleep. This experiment first administered a questionnaire to 130 college students and adults to assess their attitudes and values toward sleep. We conducted an exploratory factor analysis of 83 items of the questionnaire. As a result, factor scores were calculated for each respondent, and a total of six clusters were determined by cluster analysis. For the experiment, a total of 10 participants (college students in their 20s), five each with high factor scores, were selected from the "sleep-oriented" and "sleep-unoriented" types. The selected participants wore wristwatch-type terminals and went to bed after checking the messages sent to them. Participants received each of seven different kinds of gain/loss-framing messages per week. In questionnaires on 14 different messages, participants responded to the acceptability of the messages and changes in their attitudes toward sleep, such as going to bed early, getting up early, and reviewing their daily rhythms. A two-way ANOVA was conducted at the 5% significance level on the change in sleep awareness after confirmation of the sent message and on the evaluation of the acceptability of the sent message. We identified significant differences in sleep awareness in the main effects between clusters and in the interaction between clusters and message type. Sleep-oriented types tended to report more change in sleep awareness with loss-framing messages. In comparison, sleep-unoriented types tended to report more change in sleep awareness with gain-framing messages. Mean sleep time (minutes) during each period was calculated for each participant, and a two-way ANOVA was performed with message content and clusters as factors at a 5% significance level. We didn't find significant differences between clusters, message types, or interactions. However, sleep-oriented types tended to sleep longer than sleep-unoriented types. Furthermore, in both clusters, sleep duration tended to be longer in weeks when they received loss-framing messages than in weeks when they received gain-framing messages. The interventions in this study produced changes in sleep attitudes, but these changes differed across clusters. On the other hand, all clusters showed a trend toward longer sleep duration for loss-framing messages. In other words, changes in sleep attitudes may not be directly reflected in behavior, and we need to investigate this in the future.

Shugo Ono, Aoi Nambu, Kouki Kamada, Toru Nakata, Takashi Sakamoto, Toshikazu Kato

Conference Proceedings

Electrical parameters of conductive structures for smart textiles

The growing need for supportive and performance-enhancing garments has led to the rapid induction of smart textiles in the military sector. Smart textiles aim to reduce the weight of battery packs, electronic gadgets, connecting cables, etc. If a soldier wearing a ‘Smart Shirt’ gets injured during a war, the information on the wound and the soldier’s condition would be immediately transmitted to a medical triage unit near the battlefield [1]. The increasing adoption of smart textiles for military applications and operations is saving lives and changing the ways that militaries worldwide operate. Military clothing plays an essential role in protecting soldiers from warfare and combat elements. Textile structures were designed and made by weaving and knitting technologies using conductive yarns (Shieldex, Statex, Filix, Agis, etc.) in order to integrate into the block diagram a primary haemostasis device intended for combatants on the battlefields. The surface resistance of the fabrics with metallic yarns was measured by means of a device, consisting of two parallel linear electrodes, placed at a distance of 30 mm.The device measured resistance in Ohm for a known surface of the tested material (sq = 6,45 cm2). As such, the results were expressed in Ohm / sq. We have the following physical relations for the electrical resistance RS (1) and the electrical resistivity of a certain material ρS(2) [2]:R_S= U/I_S (1)ρ_S= R_S (D∙g)/L (2)With the following notations: U – voltage applied, IS – measured electric current intensity, L – length of the fabric, placed between the two electrodes, D – width of the fabric and g thickness of the fabric.ρ= U/I∙(D∙g)/L=R∙ (D∙g)/L [Ω.m]The electrical conductivity of the fabrics was computed with relation (3).σ= 1/ρ (3)The results of the computations show that the textile structure with AGIS LIB 40 has the highest conductivity of 32808.16 S/m, followed by the structure with AGIS 100 D yarn, of 11233.33 S/m, Agis 200D – 6916 S/m and Statex with a conductivity of 5626 S/m, respectively Shieldex with 5390.14 S/m. The Lloyd material testing equipment coupled with a data acquisition unit-DAQ (white box) was used for the simultaneous variation of elasticity and electrical conductivity of textile structures. The lowest value of the electrical resistance was obtained by the knit structure made only of conductive (yarn 1). In this case, the min./max value at the strain 5% was: 2,72 Ω/m/12,18 Ω/m and at the strain 40%: 0,56 Ω/m/37,17 Ω/m. These values are in the limit of linear electrical resistance of the yarn (76 Ω/m) [3]. The prediction of the parameter values was estimated by determining the linear regression line with the regression coefficients, R2, and the calculated correlation coefficient. The cases resistivity=f(time), resistivity=f(load), resistivity=f(strain) is represented. The only case where it seems that there are no disturbing values (noise) is the one with 30% elongation, there is also a fairly good correlation between the values.References[1] Pradhan, Anuja & Nag, Swagata. (2019). Smart Textiles for Defence Applications. Conference: Texcreative 2019 By BIET, Davangere.[2] William A. Maryniak, Toshio Uehara, Maciej A. Noras / Advanced Energy – “Surface Resistivity and Surface Resistance Measurements”, Internet resource: https://www.advancedenergy.com/globalassets/resources-root/application-notes/en-esd-surface-resistivity-application-note.pdf [3] Emilia Visileanu, Constantin Jomir, Alexandra de Raeve, Sheilla Odhiambo, Razvan Radulescu, Evaluation of the relationship between elastic and electrical characteristics of conductive textiles,Annalis of the University of Oradea, Fascicle of Textiles, Leatherwork, ISSN 1843-813X, vol.1, 2023.

Emilia Visileanu, Razvan Radulescu, Marian-catalin Grosu, Adrian Salistean

Conference Proceedings

The Role of Physical and Digital Prototyping in Designing Wearable for Rehabilitation - Case Study of a Digital Exergame

Prototypes are an excellent tool to actualize an idea or a concept. As reported by different methodologies (Double Diamond, Design Thinking), prototypes enable designers to quickly iterate and learn from their designs. Their advantages are not limited to this aspect: by iteratively increasing the level of complexity from one version of the prototype to the next one, they can help enhance the skill set of a person through a learning-by-doing approach. This iterative process allows for the identification of unknown unknowns and can lead to the development of innovative solutions in various contexts, including biomedical engineering and rehabilitation. The multiple iterations and learning processes, inherent in the rehabilitation phase are a great asset when facing biomedical projects, which require multidisciplinary knowledge. The purpose of this paper is to provide supporting evidence for the importance of prototypes in biomedical design as tools to fill the skill gap, by presenting a real-world case study performed in an academic context. A team of university students developed a novel solution for post-stroke rehabilitation, DEUHR (Digital Exergame for Upper Limb and Hand Rehabilitation), based on innovative trends in biomedical technologies, such as motion tracking sensors and exergames. The paper reports the entire process for the design of the rehabilitation system, starting from the initial concept, prototypes, tests with the users, and final outcomes.The concept for DEUHR was first developed through a series of brainstorming sessions and analysis of existing rehabilitation solutions. The team then moved on to creating low-fidelity prototypes to test and refine the interaction design and gameplay mechanics of the exergame. These low-fidelity prototypes allowed the team to quickly iterate and gather feedback from potential users, including stroke patients and rehabilitation therapists. Based on the feedback received, the team made several iterations and improvements to the prototype, gradually increasing the level of complexity and fidelity. This iterative process of prototype development allowed the authors to improve the functionality and usability of DEUHR. To evaluate the usability and effectiveness of DEUHR, a high-fidelity prototype was created in the form of a tablet-based exergame for training. New tests with both the high-fidelity prototype connected with the wearable device were made with users in order to test the functionality and usability altogether.This paper outcome consisted of a demonstrator merging the three main components of the project (the exergame, the sensing unit, and the app) which were later tested on patients. Even if the case study concerned the design of health monitoring devices, it provided valuable insights with respect to the UX design process and allowed the team to grow and expand their initial skill set to meet the requirements needed. This experience led to a rethinking of the prototyping process as an enhancing and engaging opportunity to be featured in a learning environment – possibly extending its validity also outside of the biomedical field.

Paolo Tasca, Chiara Giovannini, Fedele Cavaliere, Chiara Noli, Alessandro Celauro, Mario Covarrubias, Paolo Perego

Conference Proceedings

The Impact of Parental Treatment and Education on Social Exclusion Sensitivity in Adult Children: A Questionnaire Survey and fNIRS Study Using the Cyberball Paradigm

We investigated how attachment styles between parents and children, as well as the coping styles taught by parents to their children, affect sensitivity to social exclusion using psychological assessments based on questionnaire surveys. Additionally, we examined whether differences in sensitivity to social distress could be detected as differences in activation sites in the brain using functional near-infrared spectroscopy (fNIRS) measurements with the Cyberball Paradigm. The results suggested a potential correlation between children's own coping styles and their cognitive perception of parental guidance. However, no correlation was observed between parental guidance and children's cognition. Furthermore, in the group experiencing high levels of social distress, specific brain regions, the dorsomedial prefrontal cortex (DMPFC) and anterior prefrontal cortex (APFC), were significantly more active during the experience of social distress. Several activations in brain regions not previously reported in conventional research were also observed. These findings suggest that the way parents interact with their children and the content of parental education may have an impact on children's future sensitivity to social distress.

Takashi Sakamoto, Kouki Kamada, Atsushi Maki, Toshikazu Kato

Conference Proceedings

Antimicrobial treatments of undergarments designed for the combat-protective clothing of soldiers

Military forces around the world must be equipped with combat-protective clothing made from the best technical textiles available that must provide sufficient protection, increased comfort, and even antimicrobial protection, especially for underwear pieces. Antibacterial treatments for textile materials include the use of various substances such as chitosan, silver, collagen and so on. Chitosan is a polysaccharide that promotes changes in the permeability properties of the membrane wall causing internal osmotic imbalances and consequently inhibits the growth of microorganisms. Silver can also damage the bacterial RNA and DNA, eventually leading to the bacteria`s death. Moreover, collagen, a fibrous natural protein, has an intrinsic ability to fight infection and contributes to keeping the infection site sterile.This paper focuses on the functionalization of four variants of textile materials with different compositions to increase their antibacterial properties. The variants were treated through two different technologies: exhaustion (30 min at 40°C, 500 rpm) and padding (3 consecutive passes). V1-V4 were functionalized with colloidal silver and V1-V3 with a mixture of collagen hydrolysate and colloidal silver through exhaustion. Variants V1-V3 were also treated through the padding technique using 0.5% chitosan, 1% collagen hydrolysate and a mixture of chitosan and colloidal silver. Untreated textile variants were evaluated regarding their physical-mechanical characteristics. Moreover, the functionalized variants were characterised according to their pH, loading degree with active substances (%), wettability by drop test and contact angle methods, thermal resistance (m2K/W) and vapour resistance (m2Pa/W) according to ISO 11092. Treated textile samples were also investigated relating to their antimicrobial resistance using two methods according to ISO 20743/2013 and SR EN ISO 20645/2005. The evaluation of antibacterial resistance using the standards SR EN ISO 20645/2005 and SR EN ISO 20645/2005 demonstrated the effectiveness of treatments with active substances for approx. 95% of the tested variants.

Alina Vladu, Emilia Visileanu, Alina Popescu, Roxana Rodica Constantinescu

Conference Proceedings

Longitudinal Study of Communication in Nursing Organizations Using Wearable Sensors

Communication between medical staff is extremely important in team medical care. The authors have used AI technology to quantitatively measure communication in multiple nursing organizations and have examined good communication and teamwork. In this study, we compared the results of two separate surveys conducted in two hospital wards at different times, and examined changes in communication behavior calculated using AI technology. The subjects were the neurosurgical ward of Hospital A and the psychiatric ward of Hospital B. The survey used a business card-type electronic batch to measure communication activity for two weeks. After that, a questionnaire survey was conducted on the teamwork of nurses. The survey was conducted in 2017 (30 people) and 2018 (33 people) at Hospital A, and in 2014 (33 people) and 2020 (21 people) at Hospital B. After each survey, feedback was provided to all participants. The total communication time at Hospital A decreased by 25% for the second survey compared to the first (p <.01). That time of nurses with less than 3 years of experience (inexperienced) decreased by 19.2%, those with 3 to 9 years (mid-level) increased by 29.2%, and those with more than 9 years (veteran) increased by 5.9%. Comparing communication patterns, inexperienced and mid-level nurses spent less time in two-way communication and as listeners (p<.05), while veterans spent more time as speakers (p<.001). The communication time at Hospital B decreased by 33% less than the first survey (p<.05), 36% less for inexperienced and mid-level (p<.05), and 23% less for veterans. Comparing the time spent talking directly by years of experience, all groups spent the same amount of time talking in the first survey. In the second survey, inexperience and mid-level nurses spent significantly more time interacting with veterans (p<.05). The results suggests that the means of smooth information transmission and a chain of command were constructed, and the overall dialogue time was shortened. In addition, the teamwork scale improved in all items, suggesting that a system was created that allowed each individual to act on their own judgment, such as taking coordinated actions as necessary. According to longitudinal research, we were able to confirm changes in communication patterns and dialogue partners, and it is believed that there was a change in awareness of communication. It can be expected to lead to a better information transmission system and better team building.

Yuki Mizuno, Motoki Mizuno, Yasuyuki Yamada, Yasuyuki Hochi, Takumi Iwaasa, Kentaro Inaba, Emiko Togashi, Yumi Arai, Hidenori Hayashi

Conference Proceedings

Verification of the Effects of Exercise on the Body and Mind Using a Boxing Glove-Type Sensory Augmentation Device

The background of this study is the increased number of people lacking exercise owing to the rise in remote work since the outbreak of the new coronavirus infection. As exercise is strongly linked to mental health, a lack of physical activity leads to an increase in psychological stress among individuals. Currently, few devices are available that can accurately evaluate exercise movements and allow people to engage in casual workouts. Therefore, this study aimed to investigate the effects of boxing training on the body and mind by using a sensory augmentation device with a high amusement factor. The sensory augmentation device used in this study was designed for boxing, a high-intensity full-body exercise. Inertial sensors were placed on the wrist of the boxing glove to determine the type and power of the punching action. The device then produces sound, vibration, and light according to according to the force used to give the punching action a more spectacular appearance. We measured mental and physical states during amusement-oriented training using this boxing glove-type sensory enhancer and evaluated its effects. The results demonstrated that training with a sensory augmentation device led to heightened motor induction and increased positive emotions. This suggests that the production of sound, vibration, or light influences the reward circuits of the emotional system. Potential applications of this technology include exploring its effectiveness in various exercise movements to determine its impact on physical and mental well-being.

Yurie Kondo, Shima Okada, Masanobu Manno, Yusuke Sakaue, Masaaki Makikawa

Conference Proceedings

Sensor-based Data Acquisition via Ubiquitous Device to Detect Muscle Strength Training Activities

Maintaining a high quality of life through physical activities (PA) to prevent health decline is crucial. However, the relationship between individuals' health status, PA preferences, and motion factors is complex. PA discussions consistently show a positive correlation with healthy aging experiences, but no explicit relation to specific types of musculoskeletal exercises. Taking advantage of the increasingly widespread existence of smartphones, especially in Indonesia, this research utilizes embedded sensors for Human Activity Recognition (HAR). Based on 25 participants' data, performing nine types of selected motion, this study has successfully identified important sensor attributes that play important roles in the right and left hands for muscle strength motions as the basis for developing machine learning models with the LSTM algorithm.

Elizabeth Wianto, Hapnes Toba, Chien-Hsu Chen, Maya Malinda

Conference Proceedings