Eye movements can provide informative cues to understand human visual scan/search behavior and cognitive load during varying tasks. Visualizations of real-time gaze measures during tasks, provide an understanding of human behavior as the experiment is being conducted. Even though existing eye tracking analysis tools provide calculation and visualization of eye-tracking data, none of them support real-time visualizations of advanced gaze measures, such as ambient or focal processing, or eye-tracked measures of cognitive load. In this paper, we present an eye movements analytics dashboard that enables visualizations of various gaze measures, fixations, saccades, cognitive load, ambient-focal attention, and gaze transitions analysis by extracting eye movements from participants utilizing common off-the-shelf eye trackers. We validate the proposed eye movement visualizations by using two publicly available eye-tracking datasets. We showcase that, the proposed dashboard could be utilized to visualize advanced eye movement measures generated using multiple data sources.
{"title":"Advanced Gaze Analytics Dashboard","authors":"Gavindya Jayawardena, Vikas Ashok, Sampath Jayarathna","doi":"arxiv-2409.06628","DOIUrl":"https://doi.org/arxiv-2409.06628","url":null,"abstract":"Eye movements can provide informative cues to understand human visual\u0000scan/search behavior and cognitive load during varying tasks. Visualizations of\u0000real-time gaze measures during tasks, provide an understanding of human\u0000behavior as the experiment is being conducted. Even though existing eye\u0000tracking analysis tools provide calculation and visualization of eye-tracking\u0000data, none of them support real-time visualizations of advanced gaze measures,\u0000such as ambient or focal processing, or eye-tracked measures of cognitive load.\u0000In this paper, we present an eye movements analytics dashboard that enables\u0000visualizations of various gaze measures, fixations, saccades, cognitive load,\u0000ambient-focal attention, and gaze transitions analysis by extracting eye\u0000movements from participants utilizing common off-the-shelf eye trackers. We\u0000validate the proposed eye movement visualizations by using two publicly\u0000available eye-tracking datasets. We showcase that, the proposed dashboard could\u0000be utilized to visualize advanced eye movement measures generated using\u0000multiple data sources.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142223898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michael Adewole, Oluwaseyi Giwa, Favour Nerrise, Martins Osifeko, Ajibola Oyedeji
Human motion generation is an important area of research in many fields. In this work, we tackle the problem of motion stitching and in-betweening. Current methods either require manual efforts, or are incapable of handling longer sequences. To address these challenges, we propose a diffusion model with a transformer-based denoiser to generate realistic human motion. Our method demonstrated strong performance in generating in-betweening sequences, transforming a variable number of input poses into smooth and realistic motion sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5 seconds. We present the performance evaluation of our method using quantitative metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality, along with visual assessments of the generated outputs.
{"title":"Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening","authors":"Michael Adewole, Oluwaseyi Giwa, Favour Nerrise, Martins Osifeko, Ajibola Oyedeji","doi":"arxiv-2409.06791","DOIUrl":"https://doi.org/arxiv-2409.06791","url":null,"abstract":"Human motion generation is an important area of research in many fields. In\u0000this work, we tackle the problem of motion stitching and in-betweening. Current\u0000methods either require manual efforts, or are incapable of handling longer\u0000sequences. To address these challenges, we propose a diffusion model with a\u0000transformer-based denoiser to generate realistic human motion. Our method\u0000demonstrated strong performance in generating in-betweening sequences,\u0000transforming a variable number of input poses into smooth and realistic motion\u0000sequences consisting of 75 frames at 15 fps, resulting in a total duration of 5\u0000seconds. We present the performance evaluation of our method using quantitative\u0000metrics such as Frechet Inception Distance (FID), Diversity, and Multimodality,\u0000along with visual assessments of the generated outputs.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jad Al Aaraj, Olivia Figueira, Tu Le, Isabela Figueira, Rahmadi Trimananda, Athina Markopoulou
Internet-of-Things (IoT) devices are increasingly deployed at home, at work, and in other shared and public spaces. IoT devices collect and share data with service providers and third parties, which poses privacy concerns. Although privacy enhancing tools are quite advanced in other applications domains (eg~ advertising and tracker blockers for browsers), users have currently no convenient way to know or manage what and how data is collected and shared by IoT devices. In this paper, we present VBIT, an interactive system combining Mixed Reality (MR) and web-based applications that allows users to: (1) uncover and visualize tracking services by IoT devices in an instrumented space and (2) take action to stop or limit that tracking. We design and implement VBIT to operate at the network traffic level, and we show that it has negligible performance overhead, and offers flexibility and good usability. We perform a mixed-method user study consisting of an online survey and an in-person interview study. We show that VBIT users appreciate VBIT's transparency, control, and customization features, and they become significantly more willing to install an IoT advertising and tracking blocker, after using VBIT. In the process, we obtain design insights that can be used to further iterate and improve the design of VBIT and other systems for IoT transparency and control.
{"title":"VBIT: Towards Enhancing Privacy Control Over IoT Devices","authors":"Jad Al Aaraj, Olivia Figueira, Tu Le, Isabela Figueira, Rahmadi Trimananda, Athina Markopoulou","doi":"arxiv-2409.06233","DOIUrl":"https://doi.org/arxiv-2409.06233","url":null,"abstract":"Internet-of-Things (IoT) devices are increasingly deployed at home, at work,\u0000and in other shared and public spaces. IoT devices collect and share data with\u0000service providers and third parties, which poses privacy concerns. Although\u0000privacy enhancing tools are quite advanced in other applications domains (eg~\u0000advertising and tracker blockers for browsers), users have currently no\u0000convenient way to know or manage what and how data is collected and shared by\u0000IoT devices. In this paper, we present VBIT, an interactive system combining\u0000Mixed Reality (MR) and web-based applications that allows users to: (1) uncover\u0000and visualize tracking services by IoT devices in an instrumented space and (2)\u0000take action to stop or limit that tracking. We design and implement VBIT to\u0000operate at the network traffic level, and we show that it has negligible\u0000performance overhead, and offers flexibility and good usability. We perform a\u0000mixed-method user study consisting of an online survey and an in-person\u0000interview study. We show that VBIT users appreciate VBIT's transparency,\u0000control, and customization features, and they become significantly more willing\u0000to install an IoT advertising and tracking blocker, after using VBIT. In the\u0000process, we obtain design insights that can be used to further iterate and\u0000improve the design of VBIT and other systems for IoT transparency and control.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"173 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
"An idea is nothing more nor less than a new combination of old elements" (Young, J.W.). The widespread adoption of Large Language Models (LLMs) and publicly available ChatGPT have marked a significant turning point in the integration of Artificial Intelligence (AI) into people's everyday lives. This study explores the capability of LLMs in generating novel research ideas based on information from research papers. We conduct a thorough examination of 4 LLMs in five domains (e.g., Chemistry, Computer, Economics, Medical, and Physics). We found that the future research ideas generated by Claude-2 and GPT-4 are more aligned with the author's perspective than GPT-3.5 and Gemini. We also found that Claude-2 generates more diverse future research ideas than GPT-4, GPT-3.5, and Gemini 1.0. We further performed a human evaluation of the novelty, relevancy, and feasibility of the generated future research ideas. This investigation offers insights into the evolving role of LLMs in idea generation, highlighting both its capability and limitations. Our work contributes to the ongoing efforts in evaluating and utilizing language models for generating future research ideas. We make our datasets and codes publicly available.
{"title":"Can Large Language Models Unlock Novel Scientific Research Ideas?","authors":"Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif Ekbal","doi":"arxiv-2409.06185","DOIUrl":"https://doi.org/arxiv-2409.06185","url":null,"abstract":"\"An idea is nothing more nor less than a new combination of old elements\"\u0000(Young, J.W.). The widespread adoption of Large Language Models (LLMs) and\u0000publicly available ChatGPT have marked a significant turning point in the\u0000integration of Artificial Intelligence (AI) into people's everyday lives. This\u0000study explores the capability of LLMs in generating novel research ideas based\u0000on information from research papers. We conduct a thorough examination of 4\u0000LLMs in five domains (e.g., Chemistry, Computer, Economics, Medical, and\u0000Physics). We found that the future research ideas generated by Claude-2 and\u0000GPT-4 are more aligned with the author's perspective than GPT-3.5 and Gemini.\u0000We also found that Claude-2 generates more diverse future research ideas than\u0000GPT-4, GPT-3.5, and Gemini 1.0. We further performed a human evaluation of the\u0000novelty, relevancy, and feasibility of the generated future research ideas.\u0000This investigation offers insights into the evolving role of LLMs in idea\u0000generation, highlighting both its capability and limitations. Our work\u0000contributes to the ongoing efforts in evaluating and utilizing language models\u0000for generating future research ideas. We make our datasets and codes publicly\u0000available.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julien Albert, Martin Balfroid, Miriam Doh, Jeremie Bogaert, Luca La Fisca, Liesbet De Vos, Bryan Renard, Vincent Stragier, Emmanuel Jean
Recommender systems have become integral to our digital experiences, from online shopping to streaming platforms. Still, the rationale behind their suggestions often remains opaque to users. While some systems employ a graph-based approach, offering inherent explainability through paths associating recommended items and seed items, non-experts could not easily understand these explanations. A popular alternative is to convert graph-based explanations into textual ones using a template and an algorithm, which we denote here as ''template-based'' explanations. Yet, these can sometimes come across as impersonal or uninspiring. A novel method would be to employ large language models (LLMs) for this purpose, which we denote as ''LLM-based''. To assess the effectiveness of LLMs in generating more resonant explanations, we conducted a pilot study with 25 participants. They were presented with three explanations: (1) traditional template-based, (2) LLM-based rephrasing of the template output, and (3) purely LLM-based explanations derived from the graph-based explanations. Although subject to high variance, preliminary findings suggest that LLM-based explanations may provide a richer and more engaging user experience, further aligning with user expectations. This study sheds light on the potential limitations of current explanation methods and offers promising directions for leveraging large language models to improve user satisfaction and trust in recommender systems.
{"title":"User Preferences for Large Language Model versus Template-Based Explanations of Movie Recommendations: A Pilot Study","authors":"Julien Albert, Martin Balfroid, Miriam Doh, Jeremie Bogaert, Luca La Fisca, Liesbet De Vos, Bryan Renard, Vincent Stragier, Emmanuel Jean","doi":"arxiv-2409.06297","DOIUrl":"https://doi.org/arxiv-2409.06297","url":null,"abstract":"Recommender systems have become integral to our digital experiences, from\u0000online shopping to streaming platforms. Still, the rationale behind their\u0000suggestions often remains opaque to users. While some systems employ a\u0000graph-based approach, offering inherent explainability through paths\u0000associating recommended items and seed items, non-experts could not easily\u0000understand these explanations. A popular alternative is to convert graph-based\u0000explanations into textual ones using a template and an algorithm, which we\u0000denote here as ''template-based'' explanations. Yet, these can sometimes come\u0000across as impersonal or uninspiring. A novel method would be to employ large\u0000language models (LLMs) for this purpose, which we denote as ''LLM-based''. To\u0000assess the effectiveness of LLMs in generating more resonant explanations, we\u0000conducted a pilot study with 25 participants. They were presented with three\u0000explanations: (1) traditional template-based, (2) LLM-based rephrasing of the\u0000template output, and (3) purely LLM-based explanations derived from the\u0000graph-based explanations. Although subject to high variance, preliminary\u0000findings suggest that LLM-based explanations may provide a richer and more\u0000engaging user experience, further aligning with user expectations. This study\u0000sheds light on the potential limitations of current explanation methods and\u0000offers promising directions for leveraging large language models to improve\u0000user satisfaction and trust in recommender systems.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hongjin Lin, Naveena Karusala, Chinasa T. Okolo, Catherine D'Ignazio, Krzysztof Z. Gajos
Artificial Intelligence for Social Good (AI4SG) has emerged as a growing body of research and practice exploring the potential of AI technologies to tackle social issues. This area emphasizes interdisciplinary partnerships with community organizations, such as non-profits and government agencies. However, amidst excitement about new advances in AI and their potential impact, the needs, expectations, and aspirations of these community organizations--and whether they are being met--are not well understood. Understanding these factors is important to ensure that the considerable efforts by AI teams and community organizations can actually achieve the positive social impact they strive for. Drawing on the Data Feminism framework, we explored the perspectives of community organization members on their partnerships with AI teams through 16 semi-structured interviews. Our study highlights the pervasive influence of funding agendas and the optimism surrounding AI's potential. Despite the significant intellectual contributions and labor provided by community organization members, their goals were frequently sidelined in favor of other stakeholders, including AI teams. While many community organization members expected tangible project deployment, only two out of 14 projects we studied reached the deployment stage. However, community organization members sustained their belief in the potential of the projects, still seeing diminished goals as valuable. To enhance the efficacy of future collaborations, our participants shared their aspirations for success, calling for co-leadership starting from the early stages of projects. We propose data co-liberation as a grounding principle for approaching AI4SG moving forward, positing that community organizations' co-leadership is essential for fostering more effective, sustainable, and ethical development of AI.
{"title":"\"Come to us first\": Centering Community Organizations in Artificial Intelligence for Social Good Partnerships","authors":"Hongjin Lin, Naveena Karusala, Chinasa T. Okolo, Catherine D'Ignazio, Krzysztof Z. Gajos","doi":"arxiv-2409.06814","DOIUrl":"https://doi.org/arxiv-2409.06814","url":null,"abstract":"Artificial Intelligence for Social Good (AI4SG) has emerged as a growing body\u0000of research and practice exploring the potential of AI technologies to tackle\u0000social issues. This area emphasizes interdisciplinary partnerships with\u0000community organizations, such as non-profits and government agencies. However,\u0000amidst excitement about new advances in AI and their potential impact, the\u0000needs, expectations, and aspirations of these community organizations--and\u0000whether they are being met--are not well understood. Understanding these\u0000factors is important to ensure that the considerable efforts by AI teams and\u0000community organizations can actually achieve the positive social impact they\u0000strive for. Drawing on the Data Feminism framework, we explored the\u0000perspectives of community organization members on their partnerships with AI\u0000teams through 16 semi-structured interviews. Our study highlights the pervasive\u0000influence of funding agendas and the optimism surrounding AI's potential.\u0000Despite the significant intellectual contributions and labor provided by\u0000community organization members, their goals were frequently sidelined in favor\u0000of other stakeholders, including AI teams. While many community organization\u0000members expected tangible project deployment, only two out of 14 projects we\u0000studied reached the deployment stage. However, community organization members\u0000sustained their belief in the potential of the projects, still seeing\u0000diminished goals as valuable. To enhance the efficacy of future collaborations,\u0000our participants shared their aspirations for success, calling for\u0000co-leadership starting from the early stages of projects. We propose data\u0000co-liberation as a grounding principle for approaching AI4SG moving forward,\u0000positing that community organizations' co-leadership is essential for fostering\u0000more effective, sustainable, and ethical development of AI.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
William English, Dominic Simon, Rickard Ewetz, Sumit Jha
Path planners that can interpret free-form natural language instructions hold promise to automate a wide range of robotics applications. These planners simplify user interactions and enable intuitive control over complex semi-autonomous systems. While existing symbolic approaches offer guarantees on the correctness and efficiency, they struggle to parse free-form natural language inputs. Conversely, neural approaches based on pre-trained Large Language Models (LLMs) can manage natural language inputs but lack performance guarantees. In this paper, we propose a neuro-symbolic framework for path planning from natural language inputs called NSP. The framework leverages the neural reasoning abilities of LLMs to i) craft symbolic representations of the environment and ii) a symbolic path planning algorithm. Next, a solution to the path planning problem is obtained by executing the algorithm on the environment representation. The framework uses a feedback loop from the symbolic execution environment to the neural generation process to self-correct syntax errors and satisfy execution time constraints. We evaluate our neuro-symbolic approach using a benchmark suite with 1500 path-planning problems. The experimental evaluation shows that our neuro-symbolic approach produces 90.1% valid paths that are on average 19-77% shorter than state-of-the-art neural approaches.
{"title":"NSP: A Neuro-Symbolic Natural Language Navigational Planner","authors":"William English, Dominic Simon, Rickard Ewetz, Sumit Jha","doi":"arxiv-2409.06859","DOIUrl":"https://doi.org/arxiv-2409.06859","url":null,"abstract":"Path planners that can interpret free-form natural language instructions hold\u0000promise to automate a wide range of robotics applications. These planners\u0000simplify user interactions and enable intuitive control over complex\u0000semi-autonomous systems. While existing symbolic approaches offer guarantees on\u0000the correctness and efficiency, they struggle to parse free-form natural\u0000language inputs. Conversely, neural approaches based on pre-trained Large\u0000Language Models (LLMs) can manage natural language inputs but lack performance\u0000guarantees. In this paper, we propose a neuro-symbolic framework for path\u0000planning from natural language inputs called NSP. The framework leverages the\u0000neural reasoning abilities of LLMs to i) craft symbolic representations of the\u0000environment and ii) a symbolic path planning algorithm. Next, a solution to the\u0000path planning problem is obtained by executing the algorithm on the environment\u0000representation. The framework uses a feedback loop from the symbolic execution\u0000environment to the neural generation process to self-correct syntax errors and\u0000satisfy execution time constraints. We evaluate our neuro-symbolic approach\u0000using a benchmark suite with 1500 path-planning problems. The experimental\u0000evaluation shows that our neuro-symbolic approach produces 90.1% valid paths\u0000that are on average 19-77% shorter than state-of-the-art neural approaches.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arnav Verma, Luiz Morais, Pierre Dragicevic, Fanny Chevalier
Studies on human decision-making focused on humanitarian aid have found that cognitive biases can hinder the fair allocation of resources. However, few HCI and Information Visualization studies have explored ways to overcome those cognitive biases. This work investigates whether the design of interactive resource allocation tools can help to promote allocation fairness. We specifically study the effect of presentation format (using text or visualization) and a specific framing strategy (showing resources allocated to groups or individuals). In our three crowdsourced experiments, we provided different tool designs to split money between two fictional programs that benefit two distinct communities. Our main finding indicates that individual-framed visualizations and text may be able to curb unfair allocations caused by group-framed designs. This work opens new perspectives that can motivate research on how interactive tools and visualizations can be engineered to combat cognitive biases that lead to inequitable decisions.
{"title":"Designing Resource Allocation Tools to Promote Fair Allocation: Do Visualization and Information Framing Matter?","authors":"Arnav Verma, Luiz Morais, Pierre Dragicevic, Fanny Chevalier","doi":"arxiv-2409.06688","DOIUrl":"https://doi.org/arxiv-2409.06688","url":null,"abstract":"Studies on human decision-making focused on humanitarian aid have found that\u0000cognitive biases can hinder the fair allocation of resources. However, few HCI\u0000and Information Visualization studies have explored ways to overcome those\u0000cognitive biases. This work investigates whether the design of interactive\u0000resource allocation tools can help to promote allocation fairness. We\u0000specifically study the effect of presentation format (using text or\u0000visualization) and a specific framing strategy (showing resources allocated to\u0000groups or individuals). In our three crowdsourced experiments, we provided\u0000different tool designs to split money between two fictional programs that\u0000benefit two distinct communities. Our main finding indicates that\u0000individual-framed visualizations and text may be able to curb unfair\u0000allocations caused by group-framed designs. This work opens new perspectives\u0000that can motivate research on how interactive tools and visualizations can be\u0000engineered to combat cognitive biases that lead to inequitable decisions.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jyotirmay Nag Setu, Joshua M Le, Ripan Kumar Kundu, Barry Giesbrecht, Tobias Höllerer, Khaza Anuarul Hoque, Kevin Desai, John Quarles
Virtual Reality (VR) is quickly establishing itself in various industries, including training, education, medicine, and entertainment, in which users are frequently required to carry out multiple complex cognitive and physical activities. However, the relationship between cognitive activities, physical activities, and familiar feelings of cybersickness is not well understood and thus can be unpredictable for developers. Researchers have previously provided labeled datasets for predicting cybersickness while users are stationary, but there have been few labeled datasets on cybersickness while users are physically walking. Thus, from 39 participants, we collected head orientation, head position, eye tracking, images, physiological readings from external sensors, and the self-reported cybersickness severity, physical load, and mental load in VR. Throughout the data collection, participants navigated mazes via real walking and performed tasks challenging their attention and working memory. To demonstrate the dataset's utility, we conducted a case study of training classifiers in which we achieved 95% accuracy for cybersickness severity classification. The noteworthy performance of the straightforward classifiers makes this dataset ideal for future researchers to develop cybersickness detection and reduction models. To better understand the features that helped with classification, we performed SHAP(SHapley Additive exPlanations) analysis, highlighting the importance of eye tracking and physiological measures for cybersickness prediction while walking. This open dataset can allow future researchers to study the connection between cybersickness and cognitive loads and develop prediction models. This dataset will empower future VR developers to design efficient and effective Virtual Environments by improving cognitive load management and minimizing cybersickness.
{"title":"Mazed and Confused: A Dataset of Cybersickness, Working Memory, Mental Load, Physical Load, and Attention During a Real Walking Task in VR","authors":"Jyotirmay Nag Setu, Joshua M Le, Ripan Kumar Kundu, Barry Giesbrecht, Tobias Höllerer, Khaza Anuarul Hoque, Kevin Desai, John Quarles","doi":"arxiv-2409.06898","DOIUrl":"https://doi.org/arxiv-2409.06898","url":null,"abstract":"Virtual Reality (VR) is quickly establishing itself in various industries,\u0000including training, education, medicine, and entertainment, in which users are\u0000frequently required to carry out multiple complex cognitive and physical\u0000activities. However, the relationship between cognitive activities, physical\u0000activities, and familiar feelings of cybersickness is not well understood and\u0000thus can be unpredictable for developers. Researchers have previously provided\u0000labeled datasets for predicting cybersickness while users are stationary, but\u0000there have been few labeled datasets on cybersickness while users are\u0000physically walking. Thus, from 39 participants, we collected head orientation,\u0000head position, eye tracking, images, physiological readings from external\u0000sensors, and the self-reported cybersickness severity, physical load, and\u0000mental load in VR. Throughout the data collection, participants navigated mazes\u0000via real walking and performed tasks challenging their attention and working\u0000memory. To demonstrate the dataset's utility, we conducted a case study of\u0000training classifiers in which we achieved 95% accuracy for cybersickness\u0000severity classification. The noteworthy performance of the straightforward\u0000classifiers makes this dataset ideal for future researchers to develop\u0000cybersickness detection and reduction models. To better understand the features\u0000that helped with classification, we performed SHAP(SHapley Additive\u0000exPlanations) analysis, highlighting the importance of eye tracking and\u0000physiological measures for cybersickness prediction while walking. This open\u0000dataset can allow future researchers to study the connection between\u0000cybersickness and cognitive loads and develop prediction models. This dataset\u0000will empower future VR developers to design efficient and effective Virtual\u0000Environments by improving cognitive load management and minimizing\u0000cybersickness.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"64 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Humans activate muscles to shape the mechanical interaction with their environment, but can they harness this control mechanism to best sense the environment? We investigated how participants adapt their muscle activation to visual and haptic information when tracking a randomly moving target with a robotic interface. The results exhibit a differentiated effect of these sensory modalities, where participants' muscle cocontraction increases with the haptic noise and decreases with the visual noise, in apparent contradiction to previous results. These results can be explained, and reconciled with previous findings, when considering muscle spring like mechanics, where stiffness increases with cocontraction to regulate motion guidance. Increasing cocontraction to more closely follow the motion plan favors accurate visual over haptic information, while decreasing it avoids injecting visual noise and relies on accurate haptic information. We formulated this active sensing mechanism as the optimization of visuo-haptic information and effort. This OIE model can explain the adaptation of muscle activity to unimodal and multimodal sensory information when interacting with fixed or dynamic environments, or with another human, and can be used to optimize human-robot interaction.
{"title":"Human Impedance Modulation to Improve Visuo-Haptic Perception","authors":"Xiaoxiao Cheng, Shixian Shen, Ekaterina Ivanova, Gerolamo Carboni, Atsushi Takagi, Etienne Burdet","doi":"arxiv-2409.06124","DOIUrl":"https://doi.org/arxiv-2409.06124","url":null,"abstract":"Humans activate muscles to shape the mechanical interaction with their\u0000environment, but can they harness this control mechanism to best sense the\u0000environment? We investigated how participants adapt their muscle activation to\u0000visual and haptic information when tracking a randomly moving target with a\u0000robotic interface. The results exhibit a differentiated effect of these sensory\u0000modalities, where participants' muscle cocontraction increases with the haptic\u0000noise and decreases with the visual noise, in apparent contradiction to\u0000previous results. These results can be explained, and reconciled with previous\u0000findings, when considering muscle spring like mechanics, where stiffness\u0000increases with cocontraction to regulate motion guidance. Increasing\u0000cocontraction to more closely follow the motion plan favors accurate visual\u0000over haptic information, while decreasing it avoids injecting visual noise and\u0000relies on accurate haptic information. We formulated this active sensing\u0000mechanism as the optimization of visuo-haptic information and effort. This OIE\u0000model can explain the adaptation of muscle activity to unimodal and multimodal\u0000sensory information when interacting with fixed or dynamic environments, or\u0000with another human, and can be used to optimize human-robot interaction.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"10 5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：