Procedia Computer Science最新文献_第3页

Developing Skeletal Activity Scheduler using Machine Learning 使用机器学习开发骨骼活动调度程序

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.03.054

Sagar Bhandari , Muhammad Ahsanul Habib

Understanding human mobility patterns is crucial for sustainable urban planning. This study presents a novel approach for predicting daily activity sequences using machine learning techniques, specifically Long Short-Term Memory (LSTM) networks and Explainable Boosting Machines (EBM). Utilizing data from the 2022 Halifax Travel Activity (HaliTRAC) Survey, we train these models to predict sequences of activities based on individual and household characteristics, aiming to balance predictive performance with interpretability. The LSTM model effectively captures complex temporal dependencies, while EBM provides clear insights into the significance of individual features, addressing the "black box" nature of Machine Learning models. By simplifying activity sequences into five primary activity types, the refined LSTM and EBM models achieve accuracies of 70.25% and 73.73%, respectively. Key findings highlight employment status, age, and education level as major determinants of activity patterns, with household characteristics like size playing a secondary role. This research demonstrates the potential of utilizing advanced machine learning techniques in mobility analysis, offering both accurate predictions and actionable insights. The proposed framework provides a foundation for developing transparent and reliable tools to inform transportation policies and urban development strategies.

了解人类流动模式对可持续城市规划至关重要。本研究提出了一种使用机器学习技术预测日常活动序列的新方法，特别是长短期记忆（LSTM）网络和可解释增强机器（EBM）。利用2022年哈利法克斯旅行活动（HaliTRAC）调查的数据，我们训练这些模型来预测基于个人和家庭特征的活动序列，旨在平衡预测性能和可解释性。LSTM模型有效地捕获了复杂的时间依赖性，而EBM则对单个特征的重要性提供了清晰的见解，解决了机器学习模型的“黑箱”性质。通过将活动序列简化为5种主要活动类型，改进后的LSTM和EBM模型的准确率分别达到70.25%和73.73%。主要研究结果强调，就业状况、年龄和教育水平是活动模式的主要决定因素，家庭规模等特征起次要作用。这项研究展示了在流动性分析中利用先进的机器学习技术的潜力，提供了准确的预测和可操作的见解。拟议的框架为制定透明和可靠的工具提供了基础，为交通政策和城市发展战略提供信息。

{"title":"Developing Skeletal Activity Scheduler using Machine Learning","authors":"Sagar Bhandari , Muhammad Ahsanul Habib","doi":"10.1016/j.procs.2025.03.054","DOIUrl":"10.1016/j.procs.2025.03.054","url":null,"abstract":"<div><div>Understanding human mobility patterns is crucial for sustainable urban planning. This study presents a novel approach for predicting daily activity sequences using machine learning techniques, specifically Long Short-Term Memory (LSTM) networks and Explainable Boosting Machines (EBM). Utilizing data from the 2022 Halifax Travel Activity (HaliTRAC) Survey, we train these models to predict sequences of activities based on individual and household characteristics, aiming to balance predictive performance with interpretability. The LSTM model effectively captures complex temporal dependencies, while EBM provides clear insights into the significance of individual features, addressing the \"black box\" nature of Machine Learning models. By simplifying activity sequences into five primary activity types, the refined LSTM and EBM models achieve accuracies of 70.25% and 73.73%, respectively. Key findings highlight employment status, age, and education level as major determinants of activity patterns, with household characteristics like size playing a secondary role. This research demonstrates the potential of utilizing advanced machine learning techniques in mobility analysis, offering both accurate predictions and actionable insights. The proposed framework provides a foundation for developing transparent and reliable tools to inform transportation policies and urban development strategies.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"257 ","pages":"Pages 412-419"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870455","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}

引用次数: 0

Understanding the Drivers of Cryptocurrency Acceptance: An Empirical Study of Individual Adoption 了解接受加密货币的驱动因素：个人采用的实证研究

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.151

Máté Hidegföldi, Gergely Laszlo Csizmazia, Justina Karpavičė

Cryptocurrencies offer a novel approach to finance by eliminating the need for traditional banking and enabling secure, traceable, and internet-accessible peer-to-peer transactions. However, despite their advantages, cryptocurrencies face persistent trust issues and low levels of engagement and awareness. This research aims to investigate individuals’ behavioral intentions to use cryptocurrencies and identify factors influencing technology adoption. Employing a qualitative meta-analytic approach, a new predictive model was proposed, drawing from TAM, UTAUT, and IDT theories. A survey administered in Hungary utilized Partial Least Squares Structural Equation Modelling (PLS-SEM) for data analysis, identifying social influence, facilitating conditions, and awareness as key factors impacting perceived ease of use (PEOU) and perceived usefulness (PE).

加密货币通过消除对传统银行的需求，实现安全、可追踪和互联网可访问的点对点交易，提供了一种新颖的融资方式。然而，尽管有这些优势，加密货币仍面临着持续的信任问题，参与度和认知度都很低。本研究旨在调查个人使用加密货币的行为意图，并确定影响技术采用的因素。采用定性元分析方法，提出了一个新的预测模型，借鉴TAM， UTAUT和IDT理论。在匈牙利进行的一项调查利用偏最小二乘结构方程模型（PLS-SEM）进行数据分析，确定社会影响、便利条件和意识是影响感知易用性（PEOU）和感知有用性（PE）的关键因素。

引用次数: 0

Comparative Analysis of Simulated Annealing and Tabu Search for Parallel Machine Scheduling 模拟退火和塔布搜索在并行机调度中的比较分析

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.154

Alzira Mota , Paulo Ávila , João Bastos , Luís A.C. Roque , António Pires

This paper compares the performance of Simulated Annealing and Tabu Search meta-heuristics in addressing a parallel machine scheduling problem aimed at minimizing weighted earliness, tardiness, total flowtime, and machine deterioration costs—a multi-objective optimization problem. The problem is transformed into a single-objective problem using weighting and weighting relative distance methods. Four scenarios, varying in the number of jobs and machines, are created to evaluate these metaheuristics. Computational experiments indicate that Simulated Annealing consistently yields superior solutions compared to Tabu Search in scenarios with lower dimensions despite longer run times. Conversely, Tabu Search performs better in higher-dimensional scenarios. Furthermore, it is observed that solutions generated by different weighting methods exhibit similar performance.

本文比较了模拟退火和禁忌搜索元启发式算法在解决一个多目标优化问题的并行机器调度问题中的性能，该问题旨在最小化加权早、迟、总流时间和机器劣化成本。利用加权法和加权相对距离法将该问题转化为单目标问题。为了评估这些元启发式方法，我们创建了四个场景，它们的工作和机器数量各不相同。计算实验表明，与禁忌搜索相比，模拟退火算法在低维情况下始终能产生更好的解决方案，尽管运行时间更长。相反，禁忌搜索在高维场景中表现更好。此外，观察到不同加权方法生成的解具有相似的性能。

引用次数: 0

Sovereignty in Automated Stroke Prediction and Recommendation System with Explanations and Semantic Reasoning 具有解释和语义推理的自动中风预测和推荐系统的主权

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.079

Ayan Chatterjee

Personalized approaches are required for stroke management due to the variability in symptoms, triggers, and patient characteristics. An innovative stroke recommendation system that integrates automatic predictive analysis with semantic knowledge to provide personalized recommendations for stroke management is proposed by this paper. Stroke exacerbation are predicted and the recommendations are enhanced by the system, which leverages automatic Tree-based Pipeline Optimization Tool (TPOT) and semantic knowledge represented in an OWL Ontology (StrokeOnto). Digital sovereignty is addressed by ensuring the secure and autonomous control over patient data, supporting data sovereignty and compliance with jurisdictional data privacy laws. Furthermore, classifications are explained with Local Interpretable Model-Agnostic Explanations (LIME) to identify feature importance. Tailored interventions based on individual patient profiles are provided by this conceptual model, aiming to improve stroke management. The proposed model has been verified using public stroke dataset, and the same dataset has been utilized to support ontology development and verification. In TPOT, the best Variance Threshold + DecisionTree Classifier pipeline has outperformed other supervised machine learning models with an accuracy of 95.2%, for the used datasets. The Variance Threshold method reduces feature dimensionality with variance below a specified threshold of 0.1 to enhance predictive accuracy. To implement and evaluate the proposed model in clinical settings, further development and validation with more diverse and robust datasets are required.

由于症状、触发因素和患者特征的可变性，需要个性化的方法来进行脑卒中管理。本文提出了一种新颖的脑卒中推荐系统，将自动预测分析与语义知识相结合，为脑卒中管理提供个性化推荐。该系统利用基于树的自动管道优化工具（TPOT）和OWL本体（StrokeOnto）表示的语义知识来预测中风恶化并增强建议。数字主权是通过确保对患者数据的安全和自主控制、支持数据主权和遵守管辖数据隐私法来解决的。此外，用局部可解释模型不可知论解释（LIME）来解释分类，以确定特征的重要性。该概念模型提供了基于个体患者概况的量身定制的干预措施，旨在改善卒中管理。使用公共笔划数据集验证了所提出的模型，并使用相同的数据集支持本体的开发和验证。在TPOT中，对于使用的数据集，最佳方差阈值 + 决策树分类器管道以95.2%的准确率优于其他有监督机器学习模型。方差阈值法通过降低方差小于0.1的特征维数来提高预测精度。为了在临床环境中实施和评估所提出的模型，需要使用更多样化和更可靠的数据集进一步开发和验证。

{"title":"Sovereignty in Automated Stroke Prediction and Recommendation System with Explanations and Semantic Reasoning","authors":"Ayan Chatterjee","doi":"10.1016/j.procs.2025.02.079","DOIUrl":"10.1016/j.procs.2025.02.079","url":null,"abstract":"<div><div>Personalized approaches are required for stroke management due to the variability in symptoms, triggers, and patient characteristics. An innovative stroke recommendation system that integrates automatic predictive analysis with semantic knowledge to provide personalized recommendations for stroke management is proposed by this paper. Stroke exacerbation are predicted and the recommendations are enhanced by the system, which leverages automatic Tree-based Pipeline Optimization Tool <strong>(TPOT)</strong> and semantic knowledge represented in an <strong>OWL Ontology (StrokeOnto). Digital sovereignty</strong> is addressed by ensuring the secure and autonomous control over patient data, supporting data sovereignty and compliance with jurisdictional data privacy laws. Furthermore, classifications are explained with Local Interpretable Model-Agnostic Explanations <strong>(LIME)</strong> to identify feature importance. Tailored interventions based on individual patient profiles are provided by this conceptual model, aiming to improve stroke management. The proposed model has been verified using public stroke dataset, and the same dataset has been utilized to support ontology development and verification. In TPOT, the best <strong>Variance Threshold + DecisionTree Classifier</strong> pipeline has outperformed other supervised machine learning models with an accuracy of <strong>95.2%,</strong> for the used datasets. The Variance Threshold method reduces feature dimensionality with variance below a specified threshold of 0.1 to enhance predictive accuracy. To implement and evaluate the proposed model in clinical settings, further development and validation with more diverse and robust datasets are required.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 201-210"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550880","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}

引用次数: 0

Neoteric Threat Intelligence Ensuring Digital Sovereignty and Trust through ML-Infused Proactive Defense Analytics for NEXT-G and Beyond Ecosystems 通过机器学习注入的NEXT-G和超越生态系统的主动防御分析，确保数字主权和信任的现代威胁情报

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.062

Sudhakar Kumar , Sunil K. Singh , Rakesh Kumar , Chandra Kumari Subba , Kwok Tai Chui , Brij B. Gupta

In the domain of Cyber-Physical Systems (CPS) and the Internet of Things (IoT), this research presents a novel approach to Neoteric Threat Intelligence ensuring Digital Sovereignty and Trust through ML-Infused Proactive Defense Analytics for NEXT-G and Beyond Ecosystems. As Sixth Generation and Beyond (6G and B) wireless networks undergo rapid evolution, our framework is designed to proactively anticipate and counter security incidents by utilizing advanced machine learning algorithms. This approach effectively addresses the shortcomings of conventional models, ensuring that digital assets and communications remain secure, trustworthy, and under rightful control. The study delves into the theoretical integration of this paradigm within the NextG network architecture, reinforcing digital sovereignty through a dynamic and adaptable defense mechanism. In-depth technical examinations include advanced machine learning algorithms, adaptive defenses, and scalability considerations. By critically analyzing and comparing existing security approaches, this study significantly advances technical knowledge and practical applications for wireless network security, supporting defenses against the evolving and complex threats characteristic of the 6G and Beyond era.

在网络物理系统（CPS）和物联网（IoT）领域，本研究提出了一种新方法，通过为NEXT-G和超越生态系统注入ml的主动防御分析，确保近代威胁情报的数字主权和信任。随着第六代及以后（6G和B）无线网络的快速发展，我们的框架旨在通过利用先进的机器学习算法来主动预测和应对安全事件。这种方法有效地解决了传统模型的缺点，确保数字资产和通信保持安全、可信和合法控制。该研究深入研究了该范式在NextG网络架构中的理论整合，通过动态和适应性防御机制加强数字主权。深入的技术检查包括先进的机器学习算法、自适应防御和可扩展性考虑。通过批判性地分析和比较现有的安全方法，本研究显着推进了无线网络安全的技术知识和实际应用，支持防御6G及以后时代不断发展和复杂的威胁特征。

{"title":"Neoteric Threat Intelligence Ensuring Digital Sovereignty and Trust through ML-Infused Proactive Defense Analytics for NEXT-G and Beyond Ecosystems","authors":"Sudhakar Kumar , Sunil K. Singh , Rakesh Kumar , Chandra Kumari Subba , Kwok Tai Chui , Brij B. Gupta","doi":"10.1016/j.procs.2025.02.062","DOIUrl":"10.1016/j.procs.2025.02.062","url":null,"abstract":"<div><div>In the domain of Cyber-Physical Systems (CPS) and the Internet of Things (IoT), this research presents a novel approach to Neoteric Threat Intelligence ensuring Digital Sovereignty and Trust through ML-Infused Proactive Defense Analytics for NEXT-G and Beyond Ecosystems. As Sixth Generation and Beyond (6G and B) wireless networks undergo rapid evolution, our framework is designed to proactively anticipate and counter security incidents by utilizing advanced machine learning algorithms. This approach effectively addresses the shortcomings of conventional models, ensuring that digital assets and communications remain secure, trustworthy, and under rightful control. The study delves into the theoretical integration of this paradigm within the NextG network architecture, reinforcing digital sovereignty through a dynamic and adaptable defense mechanism. In-depth technical examinations include advanced machine learning algorithms, adaptive defenses, and scalability considerations. By critically analyzing and comparing existing security approaches, this study significantly advances technical knowledge and practical applications for wireless network security, supporting defenses against the evolving and complex threats characteristic of the 6G and Beyond era.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 39-47"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550981","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}

引用次数: 0

Sovereignty-Aware Intrusion Detection on Streaming Data: Automatic Machine Learning Pipeline and Semantic Reasoning 流数据的主权感知入侵检测：自动机器学习管道和语义推理

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.066

Ayan Chatterjee , Sundar Gopalakrishnan , Ayan Mondal

Intrusion Detection Systems (IDS) are critical in safeguarding network infrastructures against malicious attacks. Traditional IDSs often struggle with knowledge representation, real-time detection, and accuracy, especially when dealing with high-throughput data. This paper proposes a novel IDS framework that leverages machine learning models, streaming data, and semantic knowledge representation to enhance intrusion detection accuracy and scalability. Additionally, the study incorporates the concept of Digital Sovereignty, ensuring that data control, security, and privacy are maintained according to national and regional regulations. The proposed system integrates Apache Kafka for real-time data processing, an automatic machine learning pipeline (e.g., Tree-based Pipeline Optimization Tool (TPOT)) for classifying network traffic, and OWL-based semantic reasoning for advanced threat detection. The proposed system, evaluated on NSL-KDD and CIC-IDS-2017 datasets, demonstrated qualitative outcomes such as local compliance, reduced data storage needs due to real-time processing, and improved adaptability to local data laws. Experimental results reveal significant improvements in detection accuracy, processing efficiency, and Sovereignty alignment.

入侵检测系统（IDS）是保护网络基础设施免受恶意攻击的关键。传统的ids通常在知识表示、实时检测和准确性方面存在问题，特别是在处理高吞吐量数据时。本文提出了一种新的入侵检测框架，利用机器学习模型、流数据和语义知识表示来提高入侵检测的准确性和可扩展性。此外，该研究还纳入了数字主权的概念，确保根据国家和地区法规维护数据控制、安全和隐私。该系统集成了用于实时数据处理的Apache Kafka，用于对网络流量进行分类的自动机器学习管道（例如，基于树的管道优化工具（TPOT）），以及用于高级威胁检测的基于owl的语义推理。该系统在NSL-KDD和CIC-IDS-2017数据集上进行了评估，显示了定性结果，如本地合规性，由于实时处理减少了数据存储需求，以及提高了对本地数据法规的适应性。实验结果表明，该方法显著提高了检测精度、处理效率和主权一致性。

{"title":"Sovereignty-Aware Intrusion Detection on Streaming Data: Automatic Machine Learning Pipeline and Semantic Reasoning","authors":"Ayan Chatterjee , Sundar Gopalakrishnan , Ayan Mondal","doi":"10.1016/j.procs.2025.02.066","DOIUrl":"10.1016/j.procs.2025.02.066","url":null,"abstract":"<div><div>Intrusion Detection Systems (IDS) are critical in safeguarding network infrastructures against malicious attacks. Traditional IDSs often struggle with knowledge representation, real-time detection, and accuracy, especially when dealing with high-throughput data. This paper proposes a novel IDS framework that leverages machine learning models, streaming data, and semantic knowledge representation to enhance intrusion detection accuracy and scalability. Additionally, the study incorporates the concept of Digital Sovereignty, ensuring that data control, security, and privacy are maintained according to national and regional regulations. The proposed system integrates Apache Kafka for real-time data processing, an automatic machine learning pipeline (e.g., Tree-based Pipeline Optimization Tool (TPOT)) for classifying network traffic, and OWL-based semantic reasoning for advanced threat detection. The proposed system, evaluated on NSL-KDD and CIC-IDS-2017 datasets, demonstrated qualitative outcomes such as local compliance, reduced data storage needs due to real-time processing, and improved adaptability to local data laws. Experimental results reveal significant improvements in detection accuracy, processing efficiency, and Sovereignty alignment.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 78-87"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551018","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}

引用次数: 0

Ensuring Digital Sovereignty in Cross-chain EHR Sharing: A Relay-as-a-Service Approach for Secure Healthcare Interoperability 确保跨链EHR共享中的数字主权：用于安全医疗互操作性的中继即服务方法

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.02.063

Dharavath Ramesh , Thakur Santosh , Munesh Chandra Trivedi , Chi Hieu Le

Electronic Health Records (EHRs) stored in cloud environments often face privacy challenges in healthcare data management due to the divide between patient ownership and institutional control. Blockchain technology offers a promising solution with its features of immutability and traceability. However, existing blockchain-based approaches for EHR privacy preservation are limited to single institutions and fail to address the critical need for cross-chain compatibility and digital sovereignty. To bridge this gap, we propose two novel strategies: Polkadot-based Cross-chain for EHR-preserving Blockchain (PCEB) and Relay-as-a-Service-based Cross-chain for EHR-preserving Blockchain (RaSCEB). PCEB utilizes Polkadot's relay communication to securely share EHR data across multiple healthcare networks while preserving patient privacy and ensuring digital sovereignty. RaSCEB introduces Relay-as-a-Service (RaaS) to enable seamless EHR sharing across blockchain ecosystems, empowering patients with control over their data while maintaining regulatory compliance and sovereignty over their digital health records. Both approaches are validated through comprehensive security analysis and performance evaluations. We also present an interoperability framework tailored for permissioned blockchain networks, emphasizing trust derived from consensus mechanisms. Our work addresses the urgent need for cross-chain compatibility in EHR privacy preservation and advances interoperability solutions while safeguarding digital sovereignty in healthcare and beyond.

由于患者所有权和机构控制之间的差异，存储在云环境中的电子健康记录（EHRs）在医疗保健数据管理中经常面临隐私挑战。区块链技术以其不变性和可追溯性的特点提供了一个很有前途的解决方案。然而，现有的基于区块链的EHR隐私保护方法仅限于单一机构，无法解决跨链兼容性和数字主权的关键需求。为了弥补这一差距，我们提出了两种新的策略：基于polkadod的ehr保存区块链交叉链（PCEB）和基于relay -as-a- service的ehr保存区块链交叉链（RaSCEB）。PCEB利用Polkadot的中继通信在多个医疗保健网络之间安全地共享EHR数据，同时保护患者隐私并确保数字主权。RaSCEB引入了中继即服务（RaaS），以实现区块链生态系统之间的无缝EHR共享，使患者能够控制他们的数据，同时保持对其数字健康记录的合规性和主权。通过全面的安全分析和性能评估验证了这两种方法。我们还提出了一个为许可区块链网络量身定制的互操作性框架，强调来自共识机制的信任。我们的工作解决了电子病历隐私保护中跨链兼容性的迫切需求，并推进了互操作性解决方案，同时保护了医疗保健及其他领域的数字主权。

{"title":"Ensuring Digital Sovereignty in Cross-chain EHR Sharing: A Relay-as-a-Service Approach for Secure Healthcare Interoperability","authors":"Dharavath Ramesh , Thakur Santosh , Munesh Chandra Trivedi , Chi Hieu Le","doi":"10.1016/j.procs.2025.02.063","DOIUrl":"10.1016/j.procs.2025.02.063","url":null,"abstract":"<div><div>Electronic Health Records (EHRs) stored in cloud environments often face privacy challenges in healthcare data management due to the divide between patient ownership and institutional control. Blockchain technology offers a promising solution with its features of immutability and traceability. However, existing blockchain-based approaches for EHR privacy preservation are limited to single institutions and fail to address the critical need for cross-chain compatibility and digital sovereignty. To bridge this gap, we propose two novel strategies: Polkadot-based Cross-chain for EHR-preserving Blockchain (PCEB) and Relay-as-a-Service-based Cross-chain for EHR-preserving Blockchain (RaSCEB). PCEB utilizes Polkadot's relay communication to securely share EHR data across multiple healthcare networks while preserving patient privacy and ensuring digital sovereignty. RaSCEB introduces Relay-as-a-Service (RaaS) to enable seamless EHR sharing across blockchain ecosystems, empowering patients with control over their data while maintaining regulatory compliance and sovereignty over their digital health records. Both approaches are validated through comprehensive security analysis and performance evaluations. We also present an interoperability framework tailored for permissioned blockchain networks, emphasizing trust derived from consensus mechanisms. Our work addresses the urgent need for cross-chain compatibility in EHR privacy preservation and advances interoperability solutions while safeguarding digital sovereignty in healthcare and beyond.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 48-57"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551085","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}

引用次数: 0

Company perspectives of generative artificial intelligence in industrial work 工业生产中生成式人工智能的公司视角

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.085

Susanna Aromaa , Päivi Heikkilä , Marko Jurvansuu , Selen Pehlivan , Teijo Väärä , Marko Jurmu

The use of artificial intelligence (AI) technologies in the manufacturing industry is rapidly increasing. During this transformation, it can be difficult to understand how AI will change the way work is done. This study explores how generative AI could change manufacturing work. Data collection was conducted using interviews and a questionnaire with seven representatives from three industrial companies. They identified several application areas for GenAI in the industrial work context, such as design, planning, training, problem solving, coding and data management. They also expressed positive attitudes but raised concerns about trust, safety, acceptability and interoperability. Changes in work were identified as being more related to cognitive aspects such as changing the way of thinking and altering the interaction with people and machines. Therefore, human-AI design efforts should focus especially on cognitive ergonomics. Findings from this study can be used in the manufacturing industry when adopting AI, as well as in identifying research topics in the human-AI research community.

人工智能（AI）技术在制造业中的应用正在迅速增加。在这种转变过程中，很难理解人工智能将如何改变工作方式。本研究探讨了生成式人工智能如何改变制造业工作。数据收集是通过与来自三家工业公司的七名代表的访谈和问卷调查进行的。他们确定了GenAI在工业工作环境中的几个应用领域，如设计、规划、培训、解决问题、编码和数据管理。他们也表达了积极的态度，但对信任、安全、可接受性和互操作性提出了关切。工作中的变化被认为与认知方面更相关，比如改变思维方式，改变与人与机器的互动。因此，人类与人工智能的设计工作应该特别关注认知人机工程学。这项研究的结果可以用于制造业采用人工智能，也可以用于确定人类人工智能研究社区的研究课题。

{"title":"Company perspectives of generative artificial intelligence in industrial work","authors":"Susanna Aromaa , Päivi Heikkilä , Marko Jurvansuu , Selen Pehlivan , Teijo Väärä , Marko Jurmu","doi":"10.1016/j.procs.2025.01.085","DOIUrl":"10.1016/j.procs.2025.01.085","url":null,"abstract":"<div><div>The use of artificial intelligence (AI) technologies in the manufacturing industry is rapidly increasing. During this transformation, it can be difficult to understand how AI will change the way work is done. This study explores how generative AI could change manufacturing work. Data collection was conducted using interviews and a questionnaire with seven representatives from three industrial companies. They identified several application areas for GenAI in the industrial work context, such as design, planning, training, problem solving, coding and data management. They also expressed positive attitudes but raised concerns about trust, safety, acceptability and interoperability. Changes in work were identified as being more related to cognitive aspects such as changing the way of thinking and altering the interaction with people and machines. Therefore, human-AI design efforts should focus especially on cognitive ergonomics. Findings from this study can be used in the manufacturing industry when adopting AI, as well as in identifying research topics in the human-AI research community.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"253 ","pages":"Pages 217-226"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480192","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}

引用次数: 0

Integrating Chipless RFID Technology to Provide Seamless Data Interoperability for Textile Industry Circularity 集成无芯片RFID技术为纺织工业循环提供无缝数据互操作性

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.101

Maximilian Scholz, Omid Fatahi Valilai

The textile industry faces tremendous challenges when it comes to waste management and recycling. The current methods for textile companies and drop-off centres for sorting the textiles for recycling is largely through manual labour, which is inefficient and involves high costs. The bottleneck due to slow process for visual inspection creates bottlenecks for effective sorting. One idea to solve this problem is to use an embedded data mechanism in textile tags via radio frequency identification (RFID) chips. Considering the requirements of recycling processes, there is an essential need for RFID technologies which are compatible with recyclability of textile processes. Therefore, the need and demand for a sustainable solution for traceability and recycling via chipless RFID technologies is highly motivated. Moreover, the technology should be economically viable for industries for adoption. This study explores a new technological concept that offers a solution for the current problem of creating a circular economy in the textile industry with traceability of data. So, the study focuses on analysing how chipless RFID technology may be integrated into textiles with 3D printing technology. The research investigates 3D printing technology for providing the ability to create a fast, inexpensive, and detailed chipless RFID labelling solution for textile materials. Finally, the paper investigates the consumer populations readiness to adopt the technology by identifying pain points and outlining the integration of this technology into the textile industry.

纺织工业在废物管理和回收方面面临巨大挑战。纺织公司和回收中心目前对纺织品进行分类回收的方法主要是通过手工劳动，这种方法效率低下，成本高。由于目视检查过程缓慢造成的瓶颈为有效分拣造成了瓶颈。解决这个问题的一个想法是通过射频识别（RFID）芯片在纺织品标签中使用嵌入式数据机制。考虑到回收过程的要求，与纺织过程的可回收性相兼容的RFID技术是必不可少的。因此，通过无芯片RFID技术对可追溯性和回收的可持续解决方案的需求是非常积极的。此外，该技术应该在经济上可行，供各行业采用。本研究探索了一种新的技术概念，为当前纺织行业创建具有数据可追溯性的循环经济问题提供了解决方案。因此，该研究的重点是分析如何将无芯片RFID技术与3D打印技术集成到纺织品中。这项研究调查了3D打印技术，为纺织材料提供了一种快速、廉价、详细的无芯片RFID标签解决方案。最后，本文通过识别痛点并概述该技术与纺织行业的整合来调查消费者群体对采用该技术的准备程度。

{"title":"Integrating Chipless RFID Technology to Provide Seamless Data Interoperability for Textile Industry Circularity","authors":"Maximilian Scholz, Omid Fatahi Valilai","doi":"10.1016/j.procs.2025.01.101","DOIUrl":"10.1016/j.procs.2025.01.101","url":null,"abstract":"<div><div>The textile industry faces tremendous challenges when it comes to waste management and recycling. The current methods for textile companies and drop-off centres for sorting the textiles for recycling is largely through manual labour, which is inefficient and involves high costs. The bottleneck due to slow process for visual inspection creates bottlenecks for effective sorting. One idea to solve this problem is to use an embedded data mechanism in textile tags via radio frequency identification (RFID) chips. Considering the requirements of recycling processes, there is an essential need for RFID technologies which are compatible with recyclability of textile processes. Therefore, the need and demand for a sustainable solution for traceability and recycling via chipless RFID technologies is highly motivated. Moreover, the technology should be economically viable for industries for adoption. This study explores a new technological concept that offers a solution for the current problem of creating a circular economy in the textile industry with traceability of data. So, the study focuses on analysing how chipless RFID technology may be integrated into textiles with 3D printing technology. The research investigates 3D printing technology for providing the ability to create a fast, inexpensive, and detailed chipless RFID labelling solution for textile materials. Finally, the paper investigates the consumer populations readiness to adopt the technology by identifying pain points and outlining the integration of this technology into the textile industry.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"253 ","pages":"Pages 393-402"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480301","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}

引用次数: 0

Comparison of Material Fatigue Testing Strategies regarding Failure-Free Load Level of Steel Specimens using Bootstrapping and Statistical Models 基于自举模型和统计模型的钢试件无故障水平材料疲劳试验策略比较

Procedia Computer Science

Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.095

Nikolaus Haselgruber , Gerhard Oertelt , Kristopher Boss

The analysis of material fatigue data is an important step in the development of complex technical products to achieve a design which reliably withstands field load but avoids over-engineered and further unnecessary weight, energy consumption, and consequently, life cycle costs. The application of statistical methods helps to consider both, the variability of real-world load situations and the variability of material load capacity. However, to provide effective and accurate results, not only analysis methods but also data generation techniques should be selected with care. In this paper, we compare several material fatigue evaluation strategies, all consisting of a data generation/test part and an analysis part. E.g., stair-case, load-step and pearl-string as test procedures and Dixon-Mood analysis, lifetime-stress regression or the random fatigue limit model as analysis methods are investigated. The sensitivity on parameters which have to be set and the accuracy regarding load capacity as well as the required testing effort are compared. Load-step provides the most accurate estimation of the failure-free load level but is the most expensive method. Pearl-string and DoE provide similar results with much less effort and moderately higher uncertainty compared to load-step.

材料疲劳数据的分析是开发复杂技术产品的重要步骤，以实现可靠地承受现场载荷的设计，同时避免过度设计和进一步不必要的重量，能量消耗，从而减少生命周期成本。统计方法的应用有助于同时考虑实际载荷情况的可变性和材料载荷能力的可变性。然而，为了提供有效和准确的结果，不仅需要谨慎选择分析方法，还需要谨慎选择数据生成技术。在本文中，我们比较了几种材料疲劳评估策略，它们都由数据生成/测试部分和分析部分组成。研究了楼梯架、荷载阶梯和珍珠串等测试方法，以及Dixon-Mood分析、寿命-应力回归或随机疲劳极限模型等分析方法。对必须设置的参数的灵敏度和关于负载能力的准确性以及所需的测试工作进行了比较。负载步进法提供了对无故障负载水平最准确的估计，但也是最昂贵的方法。与负载步进相比，珍珠串和DoE提供了类似的结果，花费的精力更少，不确定性更高。

{"title":"Comparison of Material Fatigue Testing Strategies regarding Failure-Free Load Level of Steel Specimens using Bootstrapping and Statistical Models","authors":"Nikolaus Haselgruber , Gerhard Oertelt , Kristopher Boss","doi":"10.1016/j.procs.2025.01.095","DOIUrl":"10.1016/j.procs.2025.01.095","url":null,"abstract":"<div><div>The analysis of material fatigue data is an important step in the development of complex technical products to achieve a design which reliably withstands field load but avoids over-engineered and further unnecessary weight, energy consumption, and consequently, life cycle costs. The application of statistical methods helps to consider both, the variability of real-world load situations and the variability of material load capacity. However, to provide effective and accurate results, not only analysis methods but also data generation techniques should be selected with care. In this paper, we compare several material fatigue evaluation strategies, all consisting of a data generation/test part and an analysis part. E.g., stair-case, load-step and pearl-string as test procedures and Dixon-Mood analysis, lifetime-stress regression or the random fatigue limit model as analysis methods are investigated. The sensitivity on parameters which have to be set and the accuracy regarding load capacity as well as the required testing effort are compared. Load-step provides the most accurate estimation of the failure-free load level but is the most expensive method. Pearl-string and DoE provide similar results with much less effort and moderately higher uncertainty compared to load-step.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"253 ","pages":"Pages 323-335"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480303","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}

引用次数: 0