{"title":"Pattern-sensitive Local Differential Privacy for Finite-Range Time-series Data in Mobile Crowdsensing","authors":"Zhetao Li, Xiyu Zeng, Yong Xiao, Chengxin Li, Wentai Wu, Haolin Liu","doi":"10.1109/tmc.2024.3445973","DOIUrl":"https://doi.org/10.1109/tmc.2024.3445973","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TMC.2024.3458185
Minwoo Kim;Jonggyu Jang;Youngchol Choi;Hyun Jong Yang
The growth in artificial intelligence (AI) technology has attracted substantial interests in latency-aware task offloading of mobile edge computing (MEC)—namely, minimizing service latency. Additionally, the use of MEC systems poses an additional problem arising from limited battery resources of MDs. This paper tackles the pressing challenge of latency-aware distributed task offloading optimization, where user association (UA), resource allocation (RA), full-task offloading, and battery of mobile devices (MDs) are jointly considered. In existing studies, joint optimization of overall task offloading and UA is seldom considered due to the complexity of combinatorial optimization problems, and in cases where it is considered, linear objective functions such as power consumption are adopted. Revolutionizing the realm of MEC, our objective includes all major components contributing to users’ quality of experience, including latency and energy consumption. To achieve this, we first formulate an NP-hard combinatorial problem, where the objective function comprises three elements: communication latency, computation latency, and battery usage. We derive a closed-form RA solution of the problem; next, we provide a distributed pricing-based UA solution. We simulate the proposed algorithm for various resource-intensive tasks. Our numerical results show that the proposed method Pareto-dominates baseline methods. More specifically, the results demonstrate that the proposed method can outperform baseline methods by 1.62 times shorter latency with 41.2% less energy consumption .
随着人工智能（AI）技术的发展，人们对移动边缘计算（MEC）的延迟感知任务卸载（即最大限度地减少服务延迟）产生了浓厚的兴趣。此外，由于 MD 的电池资源有限，MEC 系统的使用还带来了一个额外的问题。本文将共同考虑用户关联（UA）、资源分配（RA）、全任务卸载和移动设备（MDs）电池等问题，以应对延迟感知分布式任务卸载优化这一紧迫挑战。在现有研究中，由于组合优化问题的复杂性，很少考虑整体任务卸载和用户关联的联合优化，即使考虑了，也是采用线性目标函数，如功耗。我们的目标包括影响用户体验质量的所有主要因素，包括时延和能耗，这是 MEC 领域的一次革命。为此，我们首先提出了一个 NP 难度的组合问题，其中目标函数包括三个要素：通信延迟、计算延迟和电池使用。我们推导出了该问题的闭式 RA 解决方案；接下来，我们提供了一种基于分布式定价的 UA 解决方案。我们针对各种资源密集型任务模拟了所提出的算法。我们的数值结果表明，所提出的方法在帕累托优势上优于基准方法。更具体地说，结果表明所提出的方法比基准方法的延迟时间短 1.62 倍，能耗低 41.2%。
{"title":"Distributed Task Offloading and Resource Allocation for Latency Minimization in Mobile Edge Computing Networks","authors":"Minwoo Kim;Jonggyu Jang;Youngchol Choi;Hyun Jong Yang","doi":"10.1109/TMC.2024.3458185","DOIUrl":"10.1109/TMC.2024.3458185","url":null,"abstract":"The growth in artificial intelligence (AI) technology has attracted substantial interests in latency-aware task offloading of mobile edge computing (MEC)—namely, minimizing service latency. Additionally, the use of MEC systems poses an additional problem arising from limited battery resources of MDs. This paper tackles the pressing challenge of latency-aware distributed task offloading optimization, where user association (UA), resource allocation (RA), full-task offloading, and battery of mobile devices (MDs) are jointly considered. In existing studies, joint optimization of overall task offloading and UA is seldom considered due to the complexity of combinatorial optimization problems, and in cases where it is considered, linear objective functions such as power consumption are adopted. Revolutionizing the realm of MEC, our objective includes all major components contributing to users’ quality of experience, including latency and energy consumption. To achieve this, we first formulate an NP-hard combinatorial problem, where the objective function comprises three elements: communication latency, computation latency, and battery usage. We derive a closed-form RA solution of the problem; next, we provide a distributed pricing-based UA solution. We simulate the proposed algorithm for various resource-intensive tasks. Our numerical results show that the proposed method Pareto-dominates baseline methods. More specifically, the results demonstrate that the proposed method can outperform baseline methods by \u0000<italic>1.62 times shorter latency</i>\u0000 with \u0000<italic>41.2% less energy consumption</i>\u0000.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/tmc.2024.3457793
Penglin Dai, Biao Han, Ke Li, Xincao Xu, Huanlai Xing, Kai Liu
{"title":"Joint Optimization of Device Placement and Model Partitioning for Cooperative DNN Inference in Heterogeneous Edge Computing","authors":"Penglin Dai, Biao Han, Ke Li, Xincao Xu, Huanlai Xing, Kai Liu","doi":"10.1109/tmc.2024.3457793","DOIUrl":"https://doi.org/10.1109/tmc.2024.3457793","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Human activity recognition (HAR) is a crucial task in IoT systems with applications ranging from surveillance and intruder detection to home automation and more. Recently, non-invasive HAR utilizing WiFi signals has gained considerable attention due to advancements in ubiquitous WiFi technologies. However, recent studies have revealed significant privacy risks associated with WiFi signals, raising concerns about bio-information leakage. To address these concerns, the decentralized paradigm, particularly federated learning (FL), has emerged as a promising approach for training HAR models while preserving data privacy. Nevertheless, FL models may struggle in end-user environments due to substantial domain discrepancies between the source training data and the target end-user environment. This discrepancy arises from the sensitivity of WiFi signals to environmental changes, resulting in notable domain shifts. As a consequence, FL-based HAR approaches often face challenges when deployed in real-world WiFi environments. Albeit there are pioneer attempts on federated domain adaptation, they typically require non-trivial communication and computation cost, which is prohibitively expensive especially considering edge-based hardware equipment of end-user environment. In this paper, we propose a model to democratize the WiFi-based HAR system by enhancing recognition accuracy in unannotated end-user environments while prioritizing data privacy. Our model leverages the hypothesis transfer and a lightweight hypothesis ensemble to mitigate negative transfer. We prove a tighter theoretical upper bound compared to existing multi-source federated domain adaptation models. Extensive experiments shows our model improves the average accuracy by approximately 10 absolute percentage points in both cross-person and cross-environment settings comparing several state-of-the-art baselines.
人类活动识别（HAR）是物联网系统中的一项重要任务，其应用范围从监控和入侵者检测到家庭自动化等等。最近，由于无处不在的 WiFi 技术的进步，利用 WiFi 信号的非侵入式人类活动识别（HAR）受到了广泛关注。然而，最近的研究揭示了与 WiFi 信号相关的重大隐私风险，引发了对生物信息泄露的担忧。为了解决这些问题，去中心化范例，特别是联合学习（FL），已成为一种既能训练 HAR 模型，又能保护数据隐私的有前途的方法。然而，由于源训练数据和目标终端用户环境之间存在巨大的领域差异，FL 模型在终端用户环境中可能会举步维艰。这种差异源于 WiFi 信号对环境变化的敏感性，从而导致明显的领域偏移。因此，基于 FL 的 HAR 方法在现实世界的 WiFi 环境中部署时往往面临挑战。尽管有先驱者在联合域适应方面进行了尝试，但它们通常需要非同小可的通信和计算成本，尤其是考虑到终端用户环境中基于边缘的硬件设备，这种成本高得令人望而却步。在本文中，我们提出了一种基于 WiFi 的 HAR 系统民主化模型，在优先考虑数据隐私的同时，提高未标注终端用户环境中的识别准确率。我们的模型利用假设转移和轻量级假设集合来减轻负转移。与现有的多源联合域适应模型相比，我们证明了更严格的理论上限。广泛的实验表明，与几种最先进的基线相比，我们的模型在跨人和跨环境设置中将平均准确率提高了约 10 个绝对百分点。
{"title":"Democratizing Federated WiFi-Based Human Activity Recognition Using Hypothesis Transfer","authors":"Bing Li;Wei Cui;Le Zhang;Qi Yang;Min Wu;Joey Tianyi Zhou","doi":"10.1109/TMC.2024.3457788","DOIUrl":"10.1109/TMC.2024.3457788","url":null,"abstract":"Human activity recognition (HAR) is a crucial task in IoT systems with applications ranging from surveillance and intruder detection to home automation and more. Recently, non-invasive HAR utilizing WiFi signals has gained considerable attention due to advancements in ubiquitous WiFi technologies. However, recent studies have revealed significant privacy risks associated with WiFi signals, raising concerns about bio-information leakage. To address these concerns, the decentralized paradigm, particularly federated learning (FL), has emerged as a promising approach for training HAR models while preserving data privacy. Nevertheless, FL models may struggle in end-user environments due to substantial domain discrepancies between the source training data and the target end-user environment. This discrepancy arises from the sensitivity of WiFi signals to environmental changes, resulting in notable domain shifts. As a consequence, FL-based HAR approaches often face challenges when deployed in real-world WiFi environments. Albeit there are pioneer attempts on federated domain adaptation, they typically require non-trivial communication and computation cost, which is prohibitively expensive especially considering edge-based hardware equipment of end-user environment. In this paper, we propose a model to democratize the WiFi-based HAR system by enhancing recognition accuracy in unannotated end-user environments while prioritizing data privacy. Our model leverages the hypothesis transfer and a lightweight hypothesis ensemble to mitigate negative transfer. We prove a tighter theoretical upper bound compared to existing multi-source federated domain adaptation models. Extensive experiments shows our model improves the average accuracy by approximately 10 absolute percentage points in both cross-person and cross-environment settings comparing several state-of-the-art baselines.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PHCG: PLC Honeypoint Communication Generator for Industrial IoT","authors":"Hao Liu, Yinghai Zhou, Binxing Fang, Yanbin Sun, Ning Hu, Zhihong Tian","doi":"10.1109/tmc.2024.3455564","DOIUrl":"https://doi.org/10.1109/tmc.2024.3455564","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-09DOI: 10.1109/tmc.2024.3456584
Zhihao Wang, Dingde Jiang, Shahid Mumtaz
{"title":"Network-wide Data Collection Based on In-band Network Telemetry for Digital Twin Networks","authors":"Zhihao Wang, Dingde Jiang, Shahid Mumtaz","doi":"10.1109/tmc.2024.3456584","DOIUrl":"https://doi.org/10.1109/tmc.2024.3456584","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Budget-Constrained Digital Twin Synchronization and Its Application on Fidelity-Aware Queries in Edge Computing","authors":"Yuchen Li, Weifa Liang, Zichuan Xu, Wenzheng Xu, Xiaohua Jia","doi":"10.1109/tmc.2024.3455357","DOIUrl":"https://doi.org/10.1109/tmc.2024.3455357","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/tmc.2024.3455417
Yongkang Gong, Haipeng Yao, Zehui Xiong, C. L. Philip Chen, Dusit Niyato
{"title":"Blockchain-Aided Digital Twin Offloading Mechanism in Space-Air-Ground Networks","authors":"Yongkang Gong, Haipeng Yao, Zehui Xiong, C. L. Philip Chen, Dusit Niyato","doi":"10.1109/tmc.2024.3455417","DOIUrl":"https://doi.org/10.1109/tmc.2024.3455417","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","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：