IEEE Transactions on Mobile Computing最新文献

{"title":"Joint DNN Model Deployment, Selection, and Configuration for Heterogeneous Inference Services Toward Edge Intelligence","authors":"Hebin Huang;Junbin Liang;Geyong Min","doi":"10.1109/TMC.2025.3586793","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586793","url":null,"abstract":"Edge intelligence is an emerging paradigm in edge computing that deploys Deep Neural Network (DNN) models on edge servers with limited storage and computation capacities to provide inference services for high mobility and real-time applications, such as autonomous driving or smart surveillance, with varying accuracy and delay requirements. Adapting application configurations (e.g., image resolution or video frame rate) while selecting different DNN models and deployment locations can provide high-accuracy, low-delay inference services that meet user requirements. However, the configurations and DNN models of various inference services are highly heterogeneous. As balancing inference accuracy, resource cost, and delay is a multi-objective programming problem, it is a great challenge to obtain the optimal solution. To address this challenge, we propose a novel online framework to jointly optimize the configuration adaption, DNN model selection, and deployment for heterogeneous inference services. Specifically, we first formulate this joint optimization problem as an integer linear programming problem and prove it is NP-hard. Then, we further model the problem as a Partial Observable Markov Decision Process (POMDP) and solve it by developing a Heterogeneous-Agent Reinforcement Learning (HARL) based algorithm, named Heterogeneous Inference Service ProvidER (HISPER). It allows agents to have different action spaces corresponding to different types of configurations and DNN models. Finally, extensive experiments demonstrate that the proposed algorithm outperforms other state-of-the-art counterparts.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12726-12741"},"PeriodicalIF":9.2,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223671","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":"Source Routing for LEO Mega-Constellations Based on Bloom Filter","authors":"Hefan Zhang;Zhiyuan Wang;Wenhao Lu;Shan Zhang;Hongbin Luo","doi":"10.1109/TMC.2025.3586626","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586626","url":null,"abstract":"Low-earth-orbit (LEO) mega-constellations with inter-satellite links (ISLs) are becoming the Internet backbone in space. Satellites within LEO often need the capability to enforce data forwarding paths. For example, they may need to bypass the satellites over the untrusted areas for the data of mission-critical applications or minimize latency for the data of time-sensitive applications. However, typical source/segment routing techniques (e.g., SRv6) suffer from scalability issue, since they record source-route-style forwarding information via the list-based structure. This results in great payload and forwarding overhead. To overcome this drawback, we propose a source/segment routing architecture for LEO mega-constellations, which is named as Link-identified Routing (LiR). LiR leverages in-packet bloom filter (BF) to record source-route-style forwarding information. BF could efficiently record multiple elements via a probabilistic data structure, but overlooks the order of the encoded elements. To address this, LiR identifies each unidirectional ISL, and represents the path by encoding ISL identifiers into BF. We investigate how to optimize BF configuration and ISL encoding policy to address false positives caused by BF. We implement LiR in Linux kernel and develop a container-based emulator for performance evaluation. Results show that LiR significantly outperforms SRv6 in terms of packet forwarding and data delivery efficiency.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12487-12504"},"PeriodicalIF":9.2,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223679","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":"Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices","authors":"Jun Liu;Yunming Liao;Hongli Xu;Yang Xu;Jianchun Liu;Chen Qian","doi":"10.1109/TMC.2025.3586644","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586644","url":null,"abstract":"Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resource constraints and system heterogeneity. Existing works rely on parameter-efficient fine-tuning methods, e.g., low-rank adaptation (LoRA)¹, but with major limitations. Herein, based on the inherent characteristics of FedFT, we observe that LoRA layers with higher ranks added close to the output help to save resource consumption while achieving comparable fine-tuning performance. Then we propose a novel LoRA-based FedFT framework, termed LEGEND, which faces the difficulty of determining the number of LoRA layers (called, LoRA depth) and the rank of each LoRA layer (called, rank distribution). We analyze the coupled relationship between LoRA depth and rank distribution, and design an efficient LoRA configuration algorithm for heterogeneous devices, thereby promoting fine-tuning efficiency. Extensive experiments are conducted on a physical platform with 80 commercial devices. The results show that LEGEND can achieve a speedup of 1.5-2.8× and save communication costs by about 42.3% when achieving the target accuracy, compared to the advanced solutions.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12533-12549"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221219","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":"Reducing Transmission Cost of Distributed Principal Components Analysis in Wireless Networks With Accuracy Guaranteed","authors":"Yiyi Zhang;Peng Guo;Xuefeng Liu;Chao Cai;Kui Zhang;Jiang Liu","doi":"10.1109/TMC.2025.3586615","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586615","url":null,"abstract":"As a classic data processing tool, Principal Component Analysis (PCA) has been widely applied in various data analysis applications. To mitigate the high computational complexity of PCA on Big Data, distributed PCA methods have been extensively studied, which disperse the computational tasks across multiple computation units while guaranteeing the accuracy. For the scenarios of distributed PCA in wireless networks, as the data is originally dispersed across different locations, it is further required to reduce the communication cost of distributed PCA in networks, which however has been seldom studied. Reducing the communication cost of distributed PCA in wireless networks requires not only appropriately partitioning the computation of PCA, ensuring accuracy, but also effectively assigning the partitioned computations and routing strategies to the nodes. In this paper, we propose CD-PCA, a communication-efficient distributed PCA (CD-PCA) scheme. This scheme implements a transmission-benefit equipartition strategy for the network to facilitate high-accuracy distributed computation and designs novel routing strategies for nodes to execute the distributed PCA within each partitioned region. Extensive simulation results demonstrate that the proposed CD-PCA scheme can reduce transmission costs by over 30% on average compared to related methods and baseline approaches.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12711-12725"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223684","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":"Adaptive Computation Offloading Scheme Based on a Collaborative Architecture With Heterogeneous MEC Nodes: A DRL Approach","authors":"Haixing Wu;Jiameng Zheng;Shunfu Jin","doi":"10.1109/TMC.2025.3586623","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586623","url":null,"abstract":"Mobile edge computing (MEC) has become an effective paradigm to support computation-intensive applications by providing services in close proximity to user devices (UDs). In MEC networks, computation offloading technology is devoted to balancing system load and prolonging UDs’ battery life. However, most existing studies on computation offloading take the impractical assumption of the MEC scenario with homogeneous users, ignoring security requirement from certain users. Moreover, with users mobility and task arrivals correlation, most existing computing offloading approaches suffer from inefficient or suboptimal decision making in practical MEC environments. To tackle these issues, by integrating task arrivals correlation within a time slot and environment dynamics between time slots, we propose an adaptive computation offloading scheme based on a collaborative architecture with heterogeneous MEC nodes. First, considering additional security requirement from very important people (VIP) users, we present a novel collaborative architecture by separating edge/cloud servers into public and private nodes. Then, with the architecture, we develop a dynamic computation offloading (DCO) algorithm to realize adaptive computation offloading scheme in MEC environment with mobile users. Particularly, the algorithm involves three stages. 1) By extending Poisson process into Markovian arrival process (MAP), we construct an MAP-based system model to capture the behavior of time-dependent task arrivals and then analyze the system model to derive the system delay in steady state. 2) For the purpose of minimizing the system delay in each time slot, we formulate a computation offloading problem in MEC environment with mobile users. 3) Under a deep reinforcement learning (DRL) framework, by taking the system delay as environmental feedback, we solve the formulated problem and provide offloading decisions in each time slot. We evaluate the performance of DCO algorithm by comparing it with other benchmark algorithms in various application scenarios. Results demonstrate that the proposed DCO algorithm outperforms the compared algorithms in response performance.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12692-12710"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223678","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":"LSNN Model: A Lightweight Spiking Neural Network-Based Depression Classification Model for Wearable EEG Sensors","authors":"Qinglin Zhao;Lixin Zhang;Haojie Zhang;Hua Jiang;Kunbo Cui;Zhongqing Wu;Jingyu Liu;Mingqi Zhao;Fuze Tian;Bin Hu","doi":"10.1109/TMC.2025.3586591","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586591","url":null,"abstract":"Depression detection via wearable Electroencephalogram (EEG) sensor-assisted diagnosis system demands computationally efficient models compatible with resource-constrained edge devices. Spiking Neural Networks (SNNs) offer inherent advantages for processing the spatio-temporal patterns of EEG through event-driven neuromorphic computing. In this study, we innovatively present LSNNet, a lightweight SNN model specifically designed for wearable EEG sensors. The model exhibits low computational complexity with 7.18 K parameters and 67.68 M Floating-Point Operations (FLOPs). It requires only 246.88 KB of Random Access Memory (RAM) and 57.33 KB of Read-Only Memory (ROM) for on-board execution, and has been validated on both the single-core STM32U535CET6 and the multi-core GAP8 microcontrollers. Despite its minimal computational and memory requirements, LSNNet achieves impressive performance metrics, with a classification accuracy of 89.2%, specificity of 92.4%, and sensitivity of 86.4% in independent tests conducted on EEG data collected from 73 depressed patients and 108 healthy controls using our three-lead EEG sensor. Especially, when running on the GAP8 microcontroller, the LSNNet model has a low power consumption of 21.43 mW and a satisfactory inference time of 0.63 s while maintaining a classification accuracy of 87.5% (only with a reduction of 1.98% ). These results underscore the potential of integrating wearable EEG sensors with the LSNNet model for depression detection in the Internet of Things (IoT) era.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12640-12654"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223683","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":"ARSys: An Efficient and Cross-Platform Development, Deployment, and Runtime System for Mobile Augmented Reality","authors":"Chengfei Lv;Chaoyue Niu;Yu Cai;Xiaotang Jiang;Fan Wu;Guihai Chen","doi":"10.1109/TMC.2025.3586797","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586797","url":null,"abstract":"Augmented reality (AR) offers users immersive experiences to interact with digital contents in their physical space. However, practical AR applications are challenged by the tight coupling of algorithm and engineering during the development and deployment phases as well as the execution requirements of hybrid AR subtasks on heterogeneous and resource-constraint mobile devices. In this work, we build an end-to-end, cross-platform, and efficient AR system, called ARSys. The infrastructure in ARSys adopts the new principle of integrated design, unifies and refines AR fundamental capabilities, supports streaming media processing, model inference, and real-time rendering by exposing high-performance tensor compute engine to top, and constructs a Python multi-instance virtual machine as the cross-platform AR task execution container. The runtime mechanism of ARSys schedules AR tasks in a pipeline parallelism way and allocates subtasks to hardware backends by optimizing the slowest node. The development workbench and the deployment platform in ARSys allow the decoupling of algorithms written in Python from engineering components in C/C++ and further support remote debugging and quick validation of AR algorithms. We extensively evaluate ARSys in practical AR applications across high-end, mid-end, and low-end Android and iOS devices, demonstrating higher development, deployment, and runtime efficiency than existing MediaPipe-oriented framework. ARSys has been integrated into Mobile Taobao for production use.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12655-12671"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223677","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":"RF-DEGO: A Range Free Localization Algorithm for Non Uniform Node Distributions and Obstacle Environments","authors":"Haibin Sun;Yongzheng Zhang","doi":"10.1109/TMC.2025.3586636","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586636","url":null,"abstract":"Range-free localization algorithms have attracted considerable attention for outdoor wireless sensor network (WSN) positioning because they are less susceptible to environmental factors when estimating inter node distances and require only a few beacon nodes with known locations to rapidly determine all node positions. Among these, the connectivity based DV Hop algorithm has become widely used due to its simplicity and ease of implementation. However, its localization accuracy is limited and it is easily degraded by non uniform node distributions and obstacle environments. To address these shortcomings, this paper proposes a novel range free localization algorithm (RF-DEGO). First, a new distance estimation formula is derived from node connectivity and the probability distribution of distances. Next, the estimated distances are corrected using the local node density along communication paths, and paths identified as detouring around obstacles receive a further correction. Finally, an enhanced hierarchical Grey Wolf Optimization algorithm computes the node positions. Extensive simulation experiments under various network scenarios and parameter settings show that the proposed algorithm outperforms several existing localization methods in both accuracy and computation time, demonstrating superior overall performance and strong competitiveness.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12517-12532"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223685","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":"Achievable Rate Maximization for Multi-IRS Assisted AAV-NOMA Networks","authors":"Dingcheng Yang;Kangqing Wu;Yu Xu;Fahui Wu;Tiankui Zhang","doi":"10.1109/TMC.2025.3586768","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586768","url":null,"abstract":"The evolution towards Internet of Things (IoT) in the forthcoming sixth generation (6G) is facing massive amounts of transmitted data and harsh wireless transmission environment, which severely degrade the quality of communication. To overcome these difficulties, a novel multiple intelligent reflecting surfaces (IRSs) assisted autonomous aerial vehicle (AAV) network framework with non-orthogonal multiple access (NOMA) is proposed in this article, where the AAV applies the NOMA scheme to deliver the information to the ground users assisted by multiple IRSs. We aim to maximize the achievable rate of the considered network while guaranteeing the minimum communication rate of each user, by jointly optimizing the multi-IRS phase shifts, AAV transmit power, AAV trajectory, and NOMA decoding order. To handle the coupled variables and integer constraints, we decompose the original problem into three subproblems based on the block coordinate descent (BCD) framework. Specifically, we first obtain the multi-IRS phase shifts by applying the semidefinite relaxation (SDR) technique. Next, the AAV transmit power allocation is derived by exploiting the concave convex procedure (CCCP) method. The AAV trajectory and NOMA decoding order are finally obtained by invoking the penalty-based method and the successive convex approximation (SCA) technique. Based on these, an alternating optimization algorithm is proposed. The numerical results show that: 1) the NOMA scheme enhances the utilization of the spectrum and enhances the access capacity of the communication system; 2) the multi-IRS cooperative structure increases the reflective channels and effectively improves the air-ground transmission environment, thus enhancing the system achievable rate; 3) the proposed multi-IRS assisted AAV NOMA algorithm achieves a significant network rate improvement compared to other benchmark schemes.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12580-12594"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223686","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":"Enabling Effective OOD Detection via Plug-and-Play Network for Mobile Visual Applications","authors":"Zixiao Wang;Qi Dong;Tianzhang Xing;Zhidan Liu;Zhenjiang Li;Xiaojiang Chen","doi":"10.1109/TMC.2025.3586625","DOIUrl":"https://doi.org/10.1109/TMC.2025.3586625","url":null,"abstract":"Mobile devices have increasingly integrated with numerous deep learning-based visual applications, such as object classification and recognition models. While these models perform well in controlled environments, their effectiveness declines in real-world environment due to out-of-distribution (OOD) data not seen during training. Existing methods for detecting OOD data often compromise normal data recognition and require extensive training on unattainable OOD data. To address these issues, we propose <inline-formula><tex-math>$mathtt {POD}$</tex-math></inline-formula>, a framework designed to enhance mobile visual applications by providing high-precision OOD detection without affecting original model performance. In the offline phase, <inline-formula><tex-math>$mathtt {POD}$</tex-math></inline-formula> generates OOD detectors from any classification model by analyzing model’s neuron responses to various data types. In the online phase, it continuously adjusts decision boundaries by integrating results from both the original model and the detector. Evaluated on two public datasets and one self-collected dataset across various popular classification models, <inline-formula><tex-math>$mathtt {POD}$</tex-math></inline-formula> significantly improves OOD detection performance while maintaining the accuracy of original models.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 11","pages":"12471-12486"},"PeriodicalIF":9.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223680","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}