Efficient order assignment in last-mile delivery benefits customers, couriers, and the platform. State-of-the-practice order assignment is based on the static delivery area partition, which cannot adapt well to the dynamic order quantity and destination distributions on different days. State-of-the-art methods focus on balancing order amounts or the payoff among couriers dynamically, neglecting the courier's workload in delivering orders. This paper explores the courier's heterogeneous behaviors for delivering orders to different destinations to measure the courier's workload and then achieve more efficient order assignments under the fair workload constraint. We design a workload-constrained order assignment system, called WORD , to reduce the cost of the last-mile delivery, i.e., the couriers’ total travel distance and overdue order rate. Specifically, the heterogeneous behaviors for delivering orders are first utilized for workload calculation. Then a two-stage order assignment framework is designed, including a sort-based initialization algorithm for initializing the assignment under the fair workload constraint and a coalition-game-based improvement algorithm for improving the assignment. Extensive evaluation results with real-world logistics data from one of the largest logistics companies in China show that WORD reduces the cost of the order assignment by up to 51.9% under the fair workload constraint compared to the state-of-the-art methods.
{"title":"Towards Workload-Constrained Efficient Order Assignment in Last-Mile Delivery","authors":"Wenjun Lyu;Xiaolong Jin;Haotian Wang;Yiwei Song;Shuai Wang;Yunhuai Liu;Tian He;Desheng Zhang","doi":"10.1109/TMC.2024.3469236","DOIUrl":"https://doi.org/10.1109/TMC.2024.3469236","url":null,"abstract":"Efficient order assignment in last-mile delivery benefits customers, couriers, and the platform. State-of-the-practice order assignment is based on the static delivery area partition, which cannot adapt well to the dynamic order quantity and destination distributions on different days. State-of-the-art methods focus on balancing order amounts or the payoff among couriers dynamically, neglecting the courier's workload in delivering orders. This paper explores the courier's heterogeneous behaviors for delivering orders to different destinations to measure the courier's workload and then achieve more efficient order assignments under the fair workload constraint. We design a workload-constrained order assignment system, called \u0000<italic>WORD</i>\u0000, to reduce the cost of the last-mile delivery, i.e., the couriers’ total travel distance and overdue order rate. Specifically, the heterogeneous behaviors for delivering orders are first utilized for workload calculation. Then a two-stage order assignment framework is designed, including a sort-based initialization algorithm for initializing the assignment under the fair workload constraint and a coalition-game-based improvement algorithm for improving the assignment. Extensive evaluation results with real-world logistics data from one of the largest logistics companies in China show that \u0000<italic>WORD</i>\u0000 reduces the cost of the order assignment by up to 51.9% under the fair workload constraint compared to the state-of-the-art methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"557-570"},"PeriodicalIF":7.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10696971","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1109/TMC.2024.3468382
Mehdi Naderi Soorki;Hossein Aghajari;Sajad Ahmadinabi;Hamed Bakhtiari Babadegani;Christina Chaccour;Walid Saad
Long-range (LoRa) wireless networks have been widely proposed as efficient wireless access networks for battery-constrained Internet of Things (IoT) devices. However, applying the LoRa-based IoT network in search-and-rescue (SAR) operations will have limited coverage caused by high signal attenuation due to terrestrial blockages, especially in highly remote areas. To overcome this challenge, using unmanned aerial vehicles (UAVs) as a flying LoRa gateway to transfer messages from ground LoRa nodes to the ground rescue station can be a promising solution. In this paper, an artificial intelligence-empowered SAR operation framework using a UAV-assisted LoRa network in different unknown search environments is designed and implemented. The problem of the flying LoRa (FL) gateway control policy is modeled as a partially observable Markov decision process to move the UAV towards the LoRa transmitter carried by a lost person in the known remote search area. A deep reinforcement learning (RL)-based policy is designed to determine the adaptive FL gateway trajectory in a given search environment. Then, as a general solution, a deep meta-RL framework is used for SAR in any new and unknown environments. The proposed deep meta-RL framework integrates the information of the prior FL gateway experience in the previous SAR environments to the new environment and then rapidly adapts the UAV control policy model for SAR operation in a new and unknown environment. To analyze the performance of the proposed framework in real-world scenarios, the proposed SAR system is experimentally tested in three environments: a university campus, a wide plain, and a slotted canyon at Mongasht mountain ranges, Iran. Experimental results show that if the deep meta-RL-based control policy is applied instead of the deep RL-based one, the number of SAR time slots decreases from 141 to 50. Moreover, in the slotted canyon environment, the UAV energy consumption under the deep meta-RL policy is respectively 57% and 23% less than the deep RL and Actor-Critic RL policies.
{"title":"Catch Me If You Can: Deep Meta-RL for Search-and-Rescue Using LoRa UAV Networks","authors":"Mehdi Naderi Soorki;Hossein Aghajari;Sajad Ahmadinabi;Hamed Bakhtiari Babadegani;Christina Chaccour;Walid Saad","doi":"10.1109/TMC.2024.3468382","DOIUrl":"https://doi.org/10.1109/TMC.2024.3468382","url":null,"abstract":"Long-range (LoRa) wireless networks have been widely proposed as efficient wireless access networks for battery-constrained Internet of Things (IoT) devices. However, applying the LoRa-based IoT network in search-and-rescue (SAR) operations will have limited coverage caused by high signal attenuation due to terrestrial blockages, especially in highly remote areas. To overcome this challenge, using unmanned aerial vehicles (UAVs) as a flying LoRa gateway to transfer messages from ground LoRa nodes to the ground rescue station can be a promising solution. In this paper, an artificial intelligence-empowered SAR operation framework using a UAV-assisted LoRa network in different unknown search environments is designed and implemented. The problem of the flying LoRa (FL) gateway control policy is modeled as a partially observable Markov decision process to move the UAV towards the LoRa transmitter carried by a lost person in the known remote search area. A deep reinforcement learning (RL)-based policy is designed to determine the adaptive FL gateway trajectory in a given search environment. Then, as a general solution, a deep meta-RL framework is used for SAR in any new and unknown environments. The proposed deep meta-RL framework integrates the information of the prior FL gateway experience in the previous SAR environments to the new environment and then rapidly adapts the UAV control policy model for SAR operation in a new and unknown environment. To analyze the performance of the proposed framework in real-world scenarios, the proposed SAR system is experimentally tested in three environments: a university campus, a wide plain, and a slotted canyon at Mongasht mountain ranges, Iran. Experimental results show that if the deep meta-RL-based control policy is applied instead of the deep RL-based one, the number of SAR time slots decreases from 141 to 50. Moreover, in the slotted canyon environment, the UAV energy consumption under the deep meta-RL policy is respectively 57% and 23% less than the deep RL and Actor-Critic RL policies.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"763-778"},"PeriodicalIF":7.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938472","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 : 2024-09-25DOI: 10.1109/TMC.2024.3468003
Guillem Femenias;Felip Riera-Palou
Cell-free massive MIMO (CF-mMIMO) is emerging as a technological pillar for future sixth generation (6G) mobile networks, promising consistently high spectral and energy efficiencies across the coverage area. Despite the reported advantages of CF-mMIMO over traditional cellular-based massive MIMO (mMIMO), the extensive deployment of access points (APs) and the associated fronthaul links present significant economic and logistical challenges. This paper proposes a transitional framework to facilitate the gradual integration of CF-mMIMO into existing cellular infrastructures, allowing mobile network operators to progressively realize the benefits of a distributed network topology. A comprehensive analysis of the spectral, energy, and computational efficiencies in heterogeneous network scenarios, incorporating both macrocellular and cell-free components, is presented. Our contributions include a unified assessment framework encompassing spectral, energy and computational aspects, a novel channel virtualization mechanism for effective downlink precoding, and a realistic industry-backed power consumption model for joint network operation. The potential performance gains are demonstrated and guidelines for the incremental deployment of CF-mMIMO are provided through detailed numerical results, ensuring a balanced trade-off between integration costs and operational benefits. This approach aims to leverage the capabilities of emerging network architectures to achieve a seamless evolution towards fully distributed 6G networks.
{"title":"From Cells to Freedom: 6G's Evolutionary Shift With Cell-Free Massive MIMO","authors":"Guillem Femenias;Felip Riera-Palou","doi":"10.1109/TMC.2024.3468003","DOIUrl":"https://doi.org/10.1109/TMC.2024.3468003","url":null,"abstract":"Cell-free massive MIMO (CF-mMIMO) is emerging as a technological pillar for future sixth generation (6G) mobile networks, promising consistently high spectral and energy efficiencies across the coverage area. Despite the reported advantages of CF-mMIMO over traditional cellular-based massive MIMO (mMIMO), the extensive deployment of access points (APs) and the associated fronthaul links present significant economic and logistical challenges. This paper proposes a transitional framework to facilitate the gradual integration of CF-mMIMO into existing cellular infrastructures, allowing mobile network operators to progressively realize the benefits of a distributed network topology. A comprehensive analysis of the spectral, energy, and computational efficiencies in heterogeneous network scenarios, incorporating both macrocellular and cell-free components, is presented. Our contributions include a unified assessment framework encompassing spectral, energy and computational aspects, a novel channel virtualization mechanism for effective downlink precoding, and a realistic industry-backed power consumption model for joint network operation. The potential performance gains are demonstrated and guidelines for the incremental deployment of CF-mMIMO are provided through detailed numerical results, ensuring a balanced trade-off between integration costs and operational benefits. This approach aims to leverage the capabilities of emerging network architectures to achieve a seamless evolution towards fully distributed 6G networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"812-829"},"PeriodicalIF":7.7,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938370","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 : 2024-09-25DOI: 10.1109/TMC.2024.3467339
Zhao Li;Lijuan Zhang;Chengyu Liu;Siwei Le;Jie Chen;Kang G. Shin;Zheng Yan;Jia Liu
With the rapid development of wireless communication technologies, Internet of Things (IoT) has emerged as one of the most important application scenarios. Due to the high density of IoT devices and the limited spectrum resources, along with the miniaturization and sustainability requirements of these devices, the development of low-cost interference management (IM) methods has become crucial for widespread use of IoT. Interference has long been known to harm network performance. Since a desired signal can be distorted by interference, and thus be incorrectly decoded at the destination, we argue that interference can also be transformed intentionally to extract the desired data from interfering signal(s). Based on this observation, we propose Interference ReCycling (IRC) for the IoT. Under IRC, a recycling signal is generated using the interference a victim IoT device is subjected to, and then sent by the device’s associated gateway. Under the influence of the recycling signal, the desired data of the interfered/victim IoT transmission-pair can be recovered from the interference at the IoT device. We also show that the interfered user’s spectral efficiency (SE) with IRC can be optimized further by properly distributing the transmit power used for the desired signal’s transmission and the recycling signal. We validate the feasibility of IRC by implementing the method on the Universal Software Radio Peripheral (USRP) platform. Our theoretical analysis, experimental and numerical evaluation have shown that the proposed IRC can fully exploit interference, and hence can significantly improve the SE of the victim IoT device compared to other existing IM methods.
{"title":"Interference Recycling: Effective Utilization of Interference for Enhancing Data Transmission","authors":"Zhao Li;Lijuan Zhang;Chengyu Liu;Siwei Le;Jie Chen;Kang G. Shin;Zheng Yan;Jia Liu","doi":"10.1109/TMC.2024.3467339","DOIUrl":"https://doi.org/10.1109/TMC.2024.3467339","url":null,"abstract":"With the rapid development of wireless communication technologies, Internet of Things (IoT) has emerged as one of the most important application scenarios. Due to the high density of IoT devices and the limited spectrum resources, along with the miniaturization and sustainability requirements of these devices, the development of low-cost interference management (IM) methods has become crucial for widespread use of IoT. Interference has long been known to harm network performance. Since a desired signal can be distorted by interference, and thus be incorrectly decoded at the destination, we argue that interference can also be transformed intentionally to extract the desired data from interfering signal(s). Based on this observation, we propose \u0000<italic>Interference ReCycling</i>\u0000 (IRC) for the IoT. Under IRC, a recycling signal is generated using the interference a victim IoT device is subjected to, and then sent by the device’s associated gateway. Under the influence of the recycling signal, the desired data of the interfered/victim IoT transmission-pair can be recovered from the interference at the IoT device. We also show that the interfered user’s spectral efficiency (SE) with IRC can be optimized further by properly distributing the transmit power used for the desired signal’s transmission and the recycling signal. We validate the feasibility of IRC by implementing the method on the Universal Software Radio Peripheral (USRP) platform. Our theoretical analysis, experimental and numerical evaluation have shown that the proposed IRC can fully exploit interference, and hence can significantly improve the SE of the victim IoT device compared to other existing IM methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"859-874"},"PeriodicalIF":7.7,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938474","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 : 2024-09-24DOI: 10.1109/TMC.2024.3466844
Ke Luo;Kongyange Zhao;Tao Ouyang;Xiaoxi Zhang;Zhi Zhou;Hao Wang;Xu Chen
Benefiting from hardware upgrades and deep learning techniques, more and more end devices can independently support a variety of intelligent applications. Further powered by edge computing technologies, the end-edge collaboration paradigm becomes one mainstream approach for achieving advanced edge intelligence (EI). To fully exploit the system resources, it is desirable to coordinate diverse EI services efficiently. Thus, we present a novel framework to jointly optimize the cost-performance trade-off for two distinct but typical EI services, where end devices simultaneously perform federated learning (FL) model training and conduct model inference with the assistance of edge offloading. However, balancing the long-term cost-performance trade-off is highly non-trivial, especially in the absence of knowledge of future system dynamics. Moreover, the capacity heterogeneity further increases the difficulty of service coordination among resource-limited end devices. To overcome these challenges, we first analyze the optimality of inference offloading decisions with and without FL model training and quantify their mutual effects due to local resource contention. By incorporating the loss estimation of FL training model, we then propose a novel proactive policy with theoretical guarantees, which proactively controls the stopping of FL training procedure to balance well the trade-offs between FL model performance and resource costs while fulfilling the inference performance requirements. Extensive results show the efficiency and robustness of our proposed algorithm for EI service coordination in dynamic end-edge collaboration scenarios.
{"title":"Efficient Coordination of Federated Learning and Inference Offloading at the Edge: A Proactive Optimization Paradigm","authors":"Ke Luo;Kongyange Zhao;Tao Ouyang;Xiaoxi Zhang;Zhi Zhou;Hao Wang;Xu Chen","doi":"10.1109/TMC.2024.3466844","DOIUrl":"https://doi.org/10.1109/TMC.2024.3466844","url":null,"abstract":"Benefiting from hardware upgrades and deep learning techniques, more and more end devices can independently support a variety of intelligent applications. Further powered by edge computing technologies, the end-edge collaboration paradigm becomes one mainstream approach for achieving advanced edge intelligence (EI). To fully exploit the system resources, it is desirable to coordinate diverse EI services efficiently. Thus, we present a novel framework to jointly optimize the cost-performance trade-off for two distinct but typical EI services, where end devices simultaneously perform federated learning (FL) model training and conduct model inference with the assistance of edge offloading. However, balancing the long-term cost-performance trade-off is highly non-trivial, especially in the absence of knowledge of future system dynamics. Moreover, the capacity heterogeneity further increases the difficulty of service coordination among resource-limited end devices. To overcome these challenges, we first analyze the optimality of inference offloading decisions with and without FL model training and quantify their mutual effects due to local resource contention. By incorporating the loss estimation of FL training model, we then propose a novel proactive policy with theoretical guarantees, which proactively controls the stopping of FL training procedure to balance well the trade-offs between FL model performance and resource costs while fulfilling the inference performance requirements. Extensive results show the efficiency and robustness of our proposed algorithm for EI service coordination in dynamic end-edge collaboration scenarios.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 1","pages":"407-421"},"PeriodicalIF":7.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777767","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}
Unmanned Aerial Vehicle (UAV)-assisted Low Earth Orbit (LEO) satellite edge computing (ULSE) networks can address the challenge communications issues in areas with harsh terrain and achieve global wireless coverage to provide services for mobile user devices (MUDs). This paper studies the LEO-UAV task offloading problem where MUDs compete for limited resources in the ULSE networks. We formulate the optimization problem with the goal of minimizing the cost of all MUDs while meeting resource constraint and satellite coverage time constraint. We first theoretically prove that this problem is NP-hard. We then reformulate the problem as a LEO-UAV task offloading game (LUTO-Game), and show that there is at least one Nash equilibrium solution for the LUTO-Game. We propose a joint UAV and LEO satellite task offloading (JULTO) algorithm to obtain the Nash equilibrium offloading strategy, and analyze the performance of the worst-case offloading strategy obtained by the JULTO algorithm. Finally, extensive experiments, including convergence analysis and comparison experiments, are carried out to validate the effectiveness of our JULTO algorithm.
{"title":"Multi-User Task Offloading in UAV-Assisted LEO Satellite Edge Computing: A Game-Theoretic Approach","authors":"Ying Chen;Jie Zhao;Yuan Wu;Jiwei Huang;Xuemin Sherman Shen","doi":"10.1109/TMC.2024.3465591","DOIUrl":"https://doi.org/10.1109/TMC.2024.3465591","url":null,"abstract":"Unmanned Aerial Vehicle (UAV)-assisted Low Earth Orbit (LEO) satellite edge computing (ULSE) networks can address the challenge communications issues in areas with harsh terrain and achieve global wireless coverage to provide services for mobile user devices (MUDs). This paper studies the LEO-UAV task offloading problem where MUDs compete for limited resources in the ULSE networks. We formulate the optimization problem with the goal of minimizing the cost of all MUDs while meeting resource constraint and satellite coverage time constraint. We first theoretically prove that this problem is NP-hard. We then reformulate the problem as a LEO-UAV task offloading game (LUTO-Game), and show that there is at least one Nash equilibrium solution for the LUTO-Game. We propose a joint UAV and LEO satellite task offloading (JULTO) algorithm to obtain the Nash equilibrium offloading strategy, and analyze the performance of the worst-case offloading strategy obtained by the JULTO algorithm. Finally, extensive experiments, including convergence analysis and comparison experiments, are carried out to validate the effectiveness of our JULTO algorithm.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 1","pages":"363-378"},"PeriodicalIF":7.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142789036","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}
Network function virtualization (NFV)-enabled space information network (SIN) has emerged as a promising method to facilitate global coverage and seamless service. This paper proposes a novel NFV-enabled SIN to provide end-to-end communication and computation services for ground users. Based on the multi-functional time expanded graph (MF-TEG), we jointly optimize the user association, virtual network function (VNF) deployment, and flow routing strategy (U-VNF-R) to maximize the total processed data received by users. The original problem is a mixed-integer linear program (MILP) that is intractable for classical computers. Inspired by quantum computing techniques, we propose a hybrid quantum-classical Benders’ decomposition (HQCBD) algorithm. Specifically, we convert the master problem of the Benders’ decomposition into the quadratic unconstrained binary optimization (QUBO) model and solve it with quantum computers. To further accelerate the optimization, we also design a multi-cut strategy based on the quantum advantages in parallel computing. Numerical results demonstrate the effectiveness and efficiency of the proposed algorithm and U-VNF-R scheme.
{"title":"Quantum-Assisted Joint Virtual Network Function Deployment and Maximum Flow Routing for Space Information Networks","authors":"Yu Zhang;Yanmin Gong;Lei Fan;Yu Wang;Zhu Han;Yuanxiong Guo","doi":"10.1109/TMC.2024.3466857","DOIUrl":"https://doi.org/10.1109/TMC.2024.3466857","url":null,"abstract":"Network function virtualization (NFV)-enabled space information network (SIN) has emerged as a promising method to facilitate global coverage and seamless service. This paper proposes a novel NFV-enabled SIN to provide end-to-end communication and computation services for ground users. Based on the multi-functional time expanded graph (MF-TEG), we jointly optimize the user association, virtual network function (VNF) deployment, and flow routing strategy (U-VNF-R) to maximize the total processed data received by users. The original problem is a mixed-integer linear program (MILP) that is intractable for classical computers. Inspired by quantum computing techniques, we propose a hybrid quantum-classical Benders’ decomposition (HQCBD) algorithm. Specifically, we convert the master problem of the Benders’ decomposition into the quadratic unconstrained binary optimization (QUBO) model and solve it with quantum computers. To further accelerate the optimization, we also design a multi-cut strategy based on the quantum advantages in parallel computing. Numerical results demonstrate the effectiveness and efficiency of the proposed algorithm and U-VNF-R scheme.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"830-844"},"PeriodicalIF":7.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938475","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 : 2024-09-23DOI: 10.1109/TMC.2024.3466227
Jie Zhang;Song Guo;Xiaosong Ma;Wenchao Xu;Qihua Zhou;Jingcai Guo;Zicong Hong;Jun Shan
Personalized federated learning (pFL) is to collaboratively train non-identical machine learning models for different clients to adapt to their heterogeneously distributed datasets. State-of-the-art pFL approaches pay much attention on exploiting clients’ inter-similarities to facilitate the collaborative learning process, meanwhile, can barely escape from the irrelevant knowledge pooling that is inevitable during the aggregation phase, and thus hindering the optimization convergence and degrading the personalization performance. To tackle such conflicts between facilitating collaboration and promoting personalization, we propose a novel pFL framework, dubbed pFedC, to first decompose the global aggregated knowledge into several compositional branches, and then selectively reassemble the relevant branches for supporting conflicts-aware collaboration among contradictory clients. Specifically, by reconstructing each local model into a shared feature extractor and multiple decomposed task-specific classifiers, the training on each client transforms into a mutually reinforced and relatively independent multi-task learning process, which provides a new perspective for pFL. Besides, we conduct a purified knowledge aggregation mechanism via quantifying the combination weights for each client to capture clients’ common prior, as well as mitigate potential conflicts from the divergent knowledge caused by the heterogeneous data. Extensive experiments over various models and datasets demonstrate the effectiveness and superior performance of the proposed algorithm.
{"title":"Model Decomposition and Reassembly for Purified Knowledge Transfer in Personalized Federated Learning","authors":"Jie Zhang;Song Guo;Xiaosong Ma;Wenchao Xu;Qihua Zhou;Jingcai Guo;Zicong Hong;Jun Shan","doi":"10.1109/TMC.2024.3466227","DOIUrl":"https://doi.org/10.1109/TMC.2024.3466227","url":null,"abstract":"Personalized federated learning (pFL) is to collaboratively train non-identical machine learning models for different clients to adapt to their heterogeneously distributed datasets. State-of-the-art pFL approaches pay much attention on exploiting clients’ inter-similarities to facilitate the collaborative learning process, meanwhile, can barely escape from the irrelevant knowledge pooling that is inevitable during the aggregation phase, and thus hindering the optimization convergence and degrading the personalization performance. To tackle such conflicts between facilitating collaboration and promoting personalization, we propose a novel pFL framework, dubbed pFedC, to first decompose the global aggregated knowledge into several compositional branches, and then selectively reassemble the relevant branches for supporting conflicts-aware collaboration among contradictory clients. Specifically, by reconstructing each local model into a shared feature extractor and multiple decomposed task-specific classifiers, the training on each client transforms into a mutually reinforced and relatively independent multi-task learning process, which provides a new perspective for pFL. Besides, we conduct a purified knowledge aggregation mechanism via quantifying the combination weights for each client to capture clients’ common prior, as well as mitigate potential conflicts from the divergent knowledge caused by the heterogeneous data. Extensive experiments over various models and datasets demonstrate the effectiveness and superior performance of the proposed algorithm.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 1","pages":"379-393"},"PeriodicalIF":7.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777507","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 : 2024-09-23DOI: 10.1109/TMC.2024.3461879
Yu Liang;Sheng Zhang;Jie Wu
Massively deployed cameras form a tightly connected network which generates video streams continuously. Benefiting from advances in computer vision, automated real-time analytics of video streams can be of practical value in various scenarios. As cameras become more dense, cross-camera video analytics has emerged. Combining video contents from multiple cameras for analytics is certainly more promising than single-camera analytics, which can realize cross-camera pedestrian tracking and cross-camera complex behavior recognition. Some works focused on optimization of cross-camera video analytic applications, but most of them ignore specific network situation between cameras and edge servers. Furthermore, most of them ignore the super resolution technique, which is proven to be a source of efficiency. In this paper, we first verify the potential gain of super resolution on cross-camera video analytic tasks. Then, we design and implement a cross-camera real-time video streaming analytic system, ${mathsf {Scrava}}$ , which leverages super resolution to augment low-resolution videos and simultaneously reduce bandwidth consumption. ${mathsf {Scrava}}$ enables real-time cross-camera video analytics and enhances video segments with the SR module under poor network conditions. We take cross-camera pedestrian tracking as an example, and experimentally verifies the effectiveness of super resolution on real-time cross-camera video analytics. Compared with using low-resolution video segments, ${mathsf {Scrava}}$ can improve the F1 score by 47.16%, verifying the feasibility of exploiting super resolution to improve the performance of real-time cross-camera video analytic systems.
{"title":"Scrava: Super Resolution-Based Bandwidth-Efficient Cross-Camera Video Analytics","authors":"Yu Liang;Sheng Zhang;Jie Wu","doi":"10.1109/TMC.2024.3461879","DOIUrl":"https://doi.org/10.1109/TMC.2024.3461879","url":null,"abstract":"Massively deployed cameras form a tightly connected network which generates video streams continuously. Benefiting from advances in computer vision, automated real-time analytics of video streams can be of practical value in various scenarios. As cameras become more dense, cross-camera video analytics has emerged. Combining video contents from multiple cameras for analytics is certainly more promising than single-camera analytics, which can realize cross-camera pedestrian tracking and cross-camera complex behavior recognition. Some works focused on optimization of cross-camera video analytic applications, but most of them ignore specific network situation between cameras and edge servers. Furthermore, most of them ignore the super resolution technique, which is proven to be a source of efficiency. In this paper, we first verify the potential gain of super resolution on cross-camera video analytic tasks. Then, we design and implement a cross-camera real-time video streaming analytic system, \u0000<inline-formula><tex-math>${mathsf {Scrava}}$</tex-math></inline-formula>\u0000, which leverages super resolution to augment low-resolution videos and simultaneously reduce bandwidth consumption. \u0000<inline-formula><tex-math>${mathsf {Scrava}}$</tex-math></inline-formula>\u0000 enables real-time cross-camera video analytics and enhances video segments with the SR module under poor network conditions. We take cross-camera pedestrian tracking as an example, and experimentally verifies the effectiveness of super resolution on real-time cross-camera video analytics. Compared with using low-resolution video segments, \u0000<inline-formula><tex-math>${mathsf {Scrava}}$</tex-math></inline-formula>\u0000 can improve the F1 score by 47.16%, verifying the feasibility of exploiting super resolution to improve the performance of real-time cross-camera video analytic systems.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 1","pages":"293-305"},"PeriodicalIF":7.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142789077","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 : 2024-09-23DOI: 10.1109/TMC.2024.3465564
Siyu Chen;Hongbo Jiang;Jingyang Hu;Tianyue Zheng;Mengyuan Wang;Zhu Xiao;Daibo Liu;Jun Luo
Recent years, point-of-sale (POS) terminals are no longer limited to wired connections, with many relying on Wi-Fi for data transmission. Although Wi-Fi offers the convenience of wireless connectivity, it introduces significant security vulnerabilities. This work presents a non-intrusive method for eavesdropping POS passwords via Wi-Fi sensing, named ${mathsf {BeamThief}}$ . Instead of conventional Wi-Fi Channel State Information (CSI) readings, our approach employs Wi-Fi Beamforming Feedback Information (BFI) for an eavesdropping attack. Compared to CSI, which can only be extracted through intruding into the Access Point (AP) or from a limited selection of commercial Wi-Fi cards (e.g., Intel-5300), BFI readings can be more readily obtained from a broad array of commercial Wi-Fi devices. A key technological contribution of ${mathsf {BeamThief}}$ is the development of an analysis model for predicting finger motion trajectories. This model is based on the physical relationship between BFI readings and finger motion, thus eliminating the need for extensive labeled training data. Furthermore, we employ Maximum Ratio Combining (MRC) to enhance the BFI series, ensuring performance across various scenarios. We implement ${mathsf {BeamThief}}$ using everyday commercial Wi-Fi devices and conduct a series of experiments to assess the impact of this attack. Experimental results demonstrate that ${mathsf {BeamThief}}$ achieves an accuracy rate 79 $%$ in inferring 6-digit POS passwords within the top-100 attempts.
{"title":"Echoes of Fingertip: Unveiling POS Terminal Passwords Through Wi-Fi Beamforming Feedback","authors":"Siyu Chen;Hongbo Jiang;Jingyang Hu;Tianyue Zheng;Mengyuan Wang;Zhu Xiao;Daibo Liu;Jun Luo","doi":"10.1109/TMC.2024.3465564","DOIUrl":"https://doi.org/10.1109/TMC.2024.3465564","url":null,"abstract":"Recent years, point-of-sale (POS) terminals are no longer limited to wired connections, with many relying on Wi-Fi for data transmission. Although Wi-Fi offers the convenience of wireless connectivity, it introduces significant security vulnerabilities. This work presents a non-intrusive method for eavesdropping POS passwords via Wi-Fi sensing, named \u0000<inline-formula><tex-math>${mathsf {BeamThief}}$</tex-math></inline-formula>\u0000. Instead of conventional Wi-Fi Channel State Information (CSI) readings, our approach employs Wi-Fi Beamforming Feedback Information (BFI) for an eavesdropping attack. Compared to CSI, which can only be extracted through intruding into the Access Point (AP) or from a limited selection of commercial Wi-Fi cards (e.g., Intel-5300), BFI readings can be more readily obtained from a broad array of commercial Wi-Fi devices. A key technological contribution of \u0000<inline-formula><tex-math>${mathsf {BeamThief}}$</tex-math></inline-formula>\u0000 is the development of an analysis model for predicting finger motion trajectories. This model is based on the physical relationship between BFI readings and finger motion, thus eliminating the need for extensive labeled training data. Furthermore, we employ Maximum Ratio Combining (MRC) to enhance the BFI series, ensuring performance across various scenarios. We implement \u0000<inline-formula><tex-math>${mathsf {BeamThief}}$</tex-math></inline-formula>\u0000 using everyday commercial Wi-Fi devices and conduct a series of experiments to assess the impact of this attack. Experimental results demonstrate that \u0000<inline-formula><tex-math>${mathsf {BeamThief}}$</tex-math></inline-formula>\u0000 achieves an accuracy rate 79\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 in inferring 6-digit POS passwords within the top-100 attempts.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"662-676"},"PeriodicalIF":7.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938518","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：