Procedia Computer Science最新文献

{"title":"The Impact of Gender and Age on Thermal Comfort","authors":"Christos Mountzouris ,&nbsp;Grigorios Protopsaltis ,&nbsp;John Gialelis","doi":"10.1016/j.procs.2025.03.042","DOIUrl":"10.1016/j.procs.2025.03.042","url":null,"abstract":"<div><div>Thermal comfort is a highly subjective experience, reflecting an individual’s satisfaction with the prevailing thermal conditions in indoor spaces. Indoor climatic conditions are not the sole determinants shaping thermal experiences. Anthropogenic factors also exert a significant influence on them, underscoring the need for personalized approaches to enhance thermal comfort. This study investigated whether the anthropogenic factors of gender and age influence an individual’s thermal perception, analyzing data from multiple field studies on thermal comfort, which conducted across diverse climatic zones, geographical regions, and building types. The results demonstrated significant differences in thermal perception between males and females, with females exhibiting a greater propensity to report “cold” sensations and a reduced likelihood to report “neutral” sensations compared to males. Adolescents and young adults reported higher discomfort levels, while middle-aged and elderly exhibited a more evenly distributed balance between comfort and discomfort. Overall, the findings highlight the necessity to account for demographic diversity in thermal comfort assessments.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 314-320"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870326","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}

{"title":"A Conceptual Framework for Digital Twins of Multi-Agent Systems","authors":"Hui Min Lee ,&nbsp;Ruhollah Jamali ,&nbsp;Sanja Lazarova-Molnar","doi":"10.1016/j.procs.2025.03.043","DOIUrl":"10.1016/j.procs.2025.03.043","url":null,"abstract":"<div><div>Multi-agent Systems (MASs) are complex systems made up of agents that can be any entities with the ability to interact autonomously and make decentralized decision-making to solve complex problems. Data-driven Agent-based Modeling and Simulation (DDABMS) equips MASs with access to decisions based on near-real-time data, allowing for more informed decisions for systems’ enhancements. Digital Twins (DTs) can further enhance MASs by serving as virtual replicas that enable what-if scenarios exploration and allow continuous validation and refinement of the underlying models with real-time data from MASs. However, we discovered a gap in systematically integrating DTs with DDABMS, as existing efforts focus on specific problems and domains rather than providing a generalized framework to develop DTs with DDABMS. This paper addresses this gap by proposing a generalized framework to develop DTs for MASs with DDABMS. To demonstrate the practicability of our proposed framework for modeling and simulation of complex systems, we present an illustrative case study based on an epidemiological Susceptible-Infected-Recovered model.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 321-328"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870327","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}

{"title":"Webcam Eye-Tracking Browser Extension For General Navigation","authors":"Quinth Anthony A. Razuman,&nbsp;Brixzel John Q. Mabala,&nbsp;Malikey M. Maulana","doi":"10.1016/j.procs.2025.03.072","DOIUrl":"10.1016/j.procs.2025.03.072","url":null,"abstract":"<div><div>Webcam eye-tracking has emerged as a cost-effective alternative to traditional eye-tracking technologies, offering a promising solution for individuals with disabilities who face challenges in using standard input devices. In this study, the researchers developed a web browser extension leveraging webcam eye-tracking for web browsing and navigation. The extension was created using Webgazer.js, a webcam eye-tracking JavaScript library, and complemented by the development of four web applications optimized for webcam eye-tracking. Through user evaluations and testing, the system demonstrated encouraging results. Users found the system to be both useful and user-friendly, as evidenced by a progressive decline in error rates over time. This trend indicated successful iterative system improvements and increased user proficiency. Although variations in error rates were observed across different applications, suggesting varying levels of intuitiveness and user-friendliness, the overall findings affirmed the system’s utility and usability. This research achieved its objectives by effectively showcasing the extension’s potential as a robust tool for individuals with hand disabilities.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 561-568"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870333","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}

{"title":"Data-driven machinery faults detection techniques using Artificial Intelligence in Industry 4.0 concept","authors":"Galina Samigulina ,&nbsp;Zarina Samigulina ,&nbsp;Daulet Bekeshev ,&nbsp;Diana Butakova","doi":"10.1016/j.procs.2025.03.053","DOIUrl":"10.1016/j.procs.2025.03.053","url":null,"abstract":"<div><div>The research is devoted to the development of an intelligent technology for diagnosing industrial equipment of oil and gas facilities based on an improved FMEA methodology (Analysis of Modes, Failures of their Influence, Degree of Criticality) in combination with a unified artificial immune system (UIIS) and the principles of immunological homeostasis. The main trends in the development of bioinspired artificial intelligence technologies are considered. A unified artificial immune system is built on the basis of modified algorithms of the artificial immune system (AIS) in order to identify the most effective ones (in data processing and forecasting) for a certain set of production data. The application of the principles of immunological homeostasis to assess modified algorithms allows identifying the «homeostasis area» in which the algorithms have the best predictive properties and can form an adequate immune response. The extension of the FMEA methodology with an intelligent block based on UAIS allows to automate the information processing previously carried out manually by experts, reduce time and resources when diagnosing equipment, and eliminate errors associated with the «human factor». The technology has been approbated on real data on equipment failures at TengizChevroil company (oil and gas industry) and on experimental data on equipment from Schneider Electric (Industrial Automation Lab).</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 404-411"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870454","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}

{"title":"From Dock to Destination: Toward an End-to-End Simulation Study","authors":"Kevin Power,&nbsp;Yassine Lahlou-Kamal,&nbsp;Nikolay Aristov,&nbsp;Elenna Dugundji,&nbsp;Thomas Koch","doi":"10.1016/j.procs.2025.03.062","DOIUrl":"10.1016/j.procs.2025.03.062","url":null,"abstract":"<div><div>This study uses a discrete-event simulation model, built with open-source software, to analyze import container flows at the Port of New York/New Jersey. The model integrates input and parameter distributions derived from extensive data analysis of publicly available import records, enhanced by machine learning techniques, including Natural Language Processing for commodity classification using unstructured shipping manifest product descriptions. Initial results demonstrate the effectiveness of Gaussian Kernel Density Estimate (KDE) and Fourier models in representing container dwell times, reducing mean absolute error compared to normal distribution by up to 39.5% for dry containers and 24.8% for reefers. A fine-tuned BERT model achieves over 80% accuracy in commodity classification to the four-digit HS code level, enabling improved input data structuring for simulation. Initial scenario testing indicates increasing outbound rail freight from 15% to 25% of total containers reduces truck congestion by 11.5% and decreases median dwell time by 1.52% for dry containers and 2.55% for reefers. These findings highlight the potential for logistical adjustments to improve efficiency and reduce congestion at the Port of New York/New Jersey.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 477-484"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870463","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}

{"title":"Balancing Privacy and Security: A Comparative Analysis of AI-Driven Surveillance in the UAE and USA","authors":"Belal Alghafri,&nbsp;Abdallah Tubaishat","doi":"10.1016/j.procs.2025.03.021","DOIUrl":"10.1016/j.procs.2025.03.021","url":null,"abstract":"<div><div>AI-driven surveillance has emerged as a critical tool for enhancing public safety, enabling authorities to monitor and prevent crime and terrorism more effectively. In countries like the UAE and the USA, these systems are often implemented under the pretext of national security, offering advanced methods to track potential threats. However, the increasing reliance on AI for surveillance raises significant ethical concerns about privacy and individual freedoms. The boundary between protecting citizens and infringing on their privacy becomes increasingly blurred, potentially leading to abuses of power, diminished public trust, and a pervasive atmosphere of fear. This paper explores the complex relationship between privacy and security in AI-driven surveillance practices in the UAE and the USA. Despite their differing political and legal systems, both countries face similar challenges in managing the ethical implications of AI surveillance. While these technologies can improve accuracy and efficiency, unchecked surveillance poses risks to civil liberties, particularly regarding data collection, analysis, and utilization. The central ethical dilemma revolves around whether certain rights should be compromised for security. While some scholars argue that the benefits of AI surveillance justify its use, others contend that privacy and freedom must remain inviolable, even amid security threats. The paper also examines the distinct approaches of the UAE and the USA in implementing surveillance systems. In the UAE, a centralized authority and significant technological investments have enabled extensive state surveillance with minimal public resistance. In contrast, the USA, as a democratic nation, continues to grapple with legal and ethical debates surrounding the limitations of its surveillance programs. The study aims to compare surveillance practices, analyze legal frameworks, and evaluate the impact on citizen freedoms. It concludes with policy recommendations to ensure responsible AI use, balancing national security with fundamental human rights.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 142-149"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870894","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}

{"title":"Combined transit mode choice patterns for commuters from transit card data in Korea","authors":"Jin Ki Eom ,&nbsp;Seonhwa Jung ,&nbsp;Kwang Sub Lee","doi":"10.1016/j.procs.2025.03.022","DOIUrl":"10.1016/j.procs.2025.03.022","url":null,"abstract":"<div><div>In 2022, Korea introduced the MTC card to promote public transportation. The MTC card offers up to 30% savings on transportation costs by accumulating mileage based on walking or cycling distances and records data on first- and last-mile trips. A case study at Gangnam Station in Seoul, Korea analyzed combined transit transfer patterns during morning peak and evening peak hours at Gangnam Station by constructing multinomial logit model. The models focused on between two transit modes since the MTC data reported that the average transfer frequency of 1.32 for public transportation users in the Seoul metropolitan area. The four-transit mode combinations such as ‘Metro to Bus’, ‘Metro to Metro’, ‘Bus to Bus’, and ’ Bus to Metro’ were set as choice variables. The results show that during the morning peak hours, ‘Bus to Metro (BtoM)’ combination is mostly preferred, while the ‘Metro to Bus (MtoB)’ combination is favored in the evening. Morning commuters are more sensitive to time and costs than evening commuters. By identifying preferred transportation combinations for each time period, policymakers develop appropriate planning for public transportation services.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 150-157"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870895","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}

{"title":"ChatGPT in Education: A Review of Ethical Challenges and Approaches to Enhancing Transparency and Privacy","authors":"Ibomoiye Domor Mienye ,&nbsp;Theo G. Swart","doi":"10.1016/j.procs.2025.02.077","DOIUrl":"10.1016/j.procs.2025.02.077","url":null,"abstract":"<div><div>The integration of ChatGPT and large language models (LLMs) into education has created new possibilities for personalized learning, tutoring, and automation of administrative tasks. However, these advancements also present ethical challenges. This paper critically examines the ethical implications of deploying ChatGPT in educational settings, with a focus on data privacy, the opaque nature of AI decision-making, and the risks of biased outputs. To address these issues, we outline actionable approaches, including Explainable AI (XAI) techniques and privacy-preserving strategies, aimed at enabling transparency and protecting student data. We also outline frameworks that support human oversight and governance to maintain trust and accountability in Al-driven educational tools.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 181-190"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Sovereignty through Africa-Centric Emotional Intelligence: A Proof of Concept for AI-Enhanced Mental Health Support","authors":"Sontaga G. Forane ,&nbsp;Absalom E. Ezugwu ,&nbsp;Kevin Igwe","doi":"10.1016/j.procs.2025.02.086","DOIUrl":"10.1016/j.procs.2025.02.086","url":null,"abstract":"<div><div>Digital sovereignty is vital for enabling communities to control their technological ecosystems, particularly in areas like mental health, where cultural relevance and data autonomy are paramount. This study examines the integration of Africa-centric emotional intelligence principles into AI-driven mental health support systems, while at the same time proposing a culturally adaptive framework with a proof of concept that emphasizes both technological autonomy and cultural authenticity. Grounded in values such as empathy, communal well-being, resilience, and Ubuntu, the conceptualized approach aligns mental health interventions with the lived experience of African communities. The framework incorporates conversational agents and personalized interventions, alongside a prototype system capable of detecting and classifying mental health conditions, such as depression, anxiety, and stress. The culturally aligned design enhances user trust, engagement, and perceived usefulness, By emphasizing local data control and leveraging Indigenous systems, this work promotes digital sovereignty and addresses privacy concerns. Preliminary testing of the prototype demonstrates the feasibility of culturally attuned AI solutions, showing improved user engagement and trust. This paper emphasizes the need for mental health interventions that respect cultural identity while promoting digital autonomy. More so, it advocates for AI systems personalized to regional contexts and calls for mental health solutions that uphold cultural identity while advancing digital self-governance.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 269-278"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MASFENON: implementing a multi-agent simulation framework for interconnected networks with distributed programming","authors":"Giorgio Locicero ,&nbsp;Antonio Di Maria ,&nbsp;Salvatore Alaimo ,&nbsp;Alfredo Pulvirenti","doi":"10.1016/j.procs.2025.02.262","DOIUrl":"10.1016/j.procs.2025.02.262","url":null,"abstract":"<div><div>The complexity of networked systems, particularly interconnected networks, necessitates advanced simulation frameworks to accurately emulate real-world dynamics, especially in the context of big data and high-performance computing. Most software used for simulation and temporal inference usually falls short in large data and optimization, since it is generally used in particular contexts, like simulating the dynamics of a specific group of entities, such as cellular and community interactions. We present ”Multi-Agent Adaptive Simulation Framework for Evolution in Networks of Networks” (MASFENON). MASFENON employs a temporal multi-layered approach to simulate and analyze dynamic processes in interconnected networks. The framework leverages parallel programming techniques for matrix and linear algebra operations and distributed and reactive programming for agent and environment communication, all implemented in C++ using the Message Passing Interface (MPI) standard. MASFENON has been validated against several common network models and could simulate the behavior of real systems in the context of epidemic simulations (See [<span><span>4</span></span>]). The framework demonstrates sublinear speedup and scalability with network size. The implementation is open source and available in a regularly updated GitHub repository1. MASFENON's integration of MPI and distributed programming techniques provides a powerful and versatile tool for modeling complex network interactions and dynamics. Its capabilities extend beyond traditional models, offering new insights and applications in network science.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"255 ","pages":"Pages 73-82"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}