IEEE Transactions on Mobile Computing最新文献_第8页

Graph-Based Indoor 3D Pedestrian Location Tracking With Inertial-Only Perception 基于纯惯性感知的室内三维行人位置跟踪

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526196

Shiyu Bai;Weisong Wen;Dongzhe Su;Li-Ta Hsu

{"title":"Graph-Based Indoor 3D Pedestrian Location Tracking With Inertial-Only Perception","authors":"Shiyu Bai;Weisong Wen;Dongzhe Su;Li-Ta Hsu","doi":"10.1109/TMC.2025.3526196","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526196","url":null,"abstract":"Pedestrian location tracking in emergency responses and environmental surveys of indoor scenarios tend to rely only on their own mobile devices, reducing the usage of external services. Low-cost and small-sized inertial measurement units (IMU) have been widely distributed in mobile devices. However, they suffer from high-level noises, leading to drift in position estimation over time. In this work, we present a graph-based indoor 3D pedestrian location tracking with inertial-only perception. The proposed method uses onboard inertial sensors in mobile devices alone for pedestrian state estimation in a simultaneous localization and mapping (SLAM) mode. It starts with a deep vertical odometry-aided 3D pedestrian dead reckoning (PDR) to predict the position in 3D space. Environment-induced behaviors, such as corner-turning and stair-taking, are regarded as landmarks. Multi-hypothesis loop closures are formed using statistical methods to handle ambiguous data association. A factor graph optimization fuses 3D PDR and behavior loop closures for state estimation. Experiments in different scenarios are performed using a smartphone to evaluate the performance of the proposed method, which can achieve better location tracking than current learning-based and filtering-based methods. Moreover, the proposed method is also discussed in different aspects, including the accuracy of offline optimization and proposed height regression, and the reliability of the multi-hypothesis behavior loop closures. The video (<uri>YouTube</uri>) or (<uri>BiliBili</uri>) is also shared to display our research.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4481-4495"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786333","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}

引用次数: 0

A High Reliable Routing Protocol Based on Spatial-Temporal Graph Model for Multiple Unmanned Underwater Vehicles Network 基于时空图模型的多无人潜航器网络高可靠路由协议

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526158

Cangzhu Xu;Shanshan Song;Xiujuan Wu;Guangjie Han;Miao Pan;Gaochao Xu;Jun-Hong Cui

{"title":"A High Reliable Routing Protocol Based on Spatial-Temporal Graph Model for Multiple Unmanned Underwater Vehicles Network","authors":"Cangzhu Xu;Shanshan Song;Xiujuan Wu;Guangjie Han;Miao Pan;Gaochao Xu;Jun-Hong Cui","doi":"10.1109/TMC.2025.3526158","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526158","url":null,"abstract":"Increasing demands for versatile applications have spurred the rapid development of Unmanned Underwater Vehicle (UUV) networks. Nevertheless, multi-UUV movements exacerbates the spatial-temporal variability, leading to serious intermittent connectivity of underwater acoustic channel. Such phenomena challenge the identification of reliable paths for high-dynamic network routing. Existing routing protocols overlook the effects of UUV movements on forwarding path, typically selecting forwarders based solely on the current network state, which lead to instability in packet transmission. To address these challenges, we propose a Routing protocol based on Spatial-Temporal Graph model with Q-learning for multi-UUV networks (STGR), achieving high reliable and energy effective transmission. Specifically, a distributed Spatial-Temporal Graph model (STG) is proposed to depict the evolving variation characteristics (neighbor relationships, link quality, and connectivity duration) among underwater nodes over periodic intervals. Then we design a Q-learning-based forwarder selection algorithm integrated with STG to calculate reward function, ensuring adaptability to the ever-changing conditions. We have performed extensive simulations of STGR on the Aqua-Sim-tg platform and compared with the state-of-the-art routing protocols in terms of Packet Delivery Rate (PDR), latency, energy consumption and energy balance with different network settings. The results show that STGR yields 24.32 percent higher PDR on average than them in multi-UUV networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4434-4450"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786330","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}

引用次数: 0

A Security-Enhanced Ultra-Lightweight and Anonymous User Authentication Protocol for Telehealthcare Information Systems 一种安全增强的远程医疗信息系统超轻量级匿名用户认证协议

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526519

Dake Zeng;Akhtar Badshah;Shanshan Tu;Muhammad Waqas;Zhu Han

{"title":"A Security-Enhanced Ultra-Lightweight and Anonymous User Authentication Protocol for Telehealthcare Information Systems","authors":"Dake Zeng;Akhtar Badshah;Shanshan Tu;Muhammad Waqas;Zhu Han","doi":"10.1109/TMC.2025.3526519","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526519","url":null,"abstract":"The surge in smartphone and wearable device usage has propelled the advancement of the Internet of Things (IoT) applications. Among these, e-healthcare stands out as a fundamental service, enabling the remote access and storage of patient-related data on a centralized medical server (MS), and facilitating connections between authorized individuals such as doctors, patients, and nurses over the public Internet. However, the inherent vulnerability of the public Internet to diverse security threats underscores the critical need for a robust and secure user authentication protocol to safeguard these essential services. This research presents a novel, resource-efficient user authentication protocol specifically designed for healthcare systems. Our proposed protocol leverages the lightweight authenticated encryption with associated data (AEAD) primitive <sc>Ascon combined with hash functions and XoR, specifically tailored for encrypted communication in resource-constrained IoT devices, emphasizing resource efficiency. Additionally, the proposed protocol establishes secure session keys between users and MS, facilitating future encrypted communications and preventing unauthorized attackers from illegally obtaining users’ private data. Furthermore, comprehensive security validation, including informal security analyses, demonstrates the protocol's resilience against a spectrum of security threats. Extensive analysis reveals that our proposed protocol significantly reduces computational and communication resource requirements during the authentication phase in comparison to similar authentication protocols, underscoring its efficiency and suitability for deployment in healthcare systems.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4529-4542"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786384","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}

引用次数: 0

FastTuner: Fast Resolution and Model Tuning for Multi-Object Tracking in Edge Video Analytics FastTuner：边缘视频分析中多目标跟踪的快速分辨率和模型调整

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526573

Renjie Xu;Keivan Nalaie;Rong Zheng

{"title":"FastTuner: Fast Resolution and Model Tuning for Multi-Object Tracking in Edge Video Analytics","authors":"Renjie Xu;Keivan Nalaie;Rong Zheng","doi":"10.1109/TMC.2025.3526573","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526573","url":null,"abstract":"Multi-object tracking (MOT) is the “killer app” of edge video analytics. Deploying MOT pipelines for live video analytics poses a significant system challenge due to their computation-intensive nature. In this paper, we propose FastTuner, a model-agnostic framework that aims to accelerate MOT pipelines by adapting frame resolutions and backbone models. Unlike prior works that utilize a separate and time-consuming online profiling procedure to identify the optimal configuration, FastTuner incorporates multi-task learning to perform configuration selection and object tracking through a shared model. Multi-resolution training is employed to further improve the tracking accuracy across different resolutions. Furthermore, two workload placement schemes are designed for the practical deployment of FastTuner in edge video analytics systems. Extensive experiments demonstrate that FastTuner can achieve 1.1%–9.2% higher tracking accuracy and 2.5%–25.5% higher speed compared to the state-of-the-art methods, and accelerate end-to-end processing by 1.7%–22.5% in a real-world testbed consisting of an embedded device and an edge server.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 6","pages":"4747-4761"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925191","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}

引用次数: 0

Lightweight Configuration Adaptation With Multi-Teacher Reinforcement Learning for Live Video Analytics 轻量级配置适应与多教师强化学习实时视频分析

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526359

Yuanhong Zhang;Weizhan Zhang;Muyao Yuan;Liang Xu;Caixia Yan;Tieliang Gong;Haipeng Du

{"title":"Lightweight Configuration Adaptation With Multi-Teacher Reinforcement Learning for Live Video Analytics","authors":"Yuanhong Zhang;Weizhan Zhang;Muyao Yuan;Liang Xu;Caixia Yan;Tieliang Gong;Haipeng Du","doi":"10.1109/TMC.2025.3526359","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526359","url":null,"abstract":"The proliferation of video data and advancements in Deep Neural Networks (DNNs) have greatly boosted live video analytics, driven by the growing video capture capabilities of mobile devices. However, resource limitations necessitate the transmission of endpoint-collected videos to servers for inference. To meet real-time requirements and ensure accurate inference, it is essential to adjust video configurations at the endpoint. Traditional methods rely on deterministic strategies, posing difficulties in adapting to dynamic networks and video content. Meanwhile, emerging learning-based schemes suffer from trial-and-error exploration mechanisms, resulting in a concerning long-tail effect on upload latency. In this paper, we propose a novel lightweight and robust configuration adaptation policy (LCA), which fuses heuristic and RL-based agents using multi-teacher knowledge distillation (MKD) theory. First, we propose a content-sensitive and bandwidth-adaptive RL agent and introduce a Lyapunov-based optimization agent for ensuring latency robustness. To leverage both agents’ strengths, we design a feature-guided multi-teacher distillation network to transfer their advantages to the student. The experimental results across two vision tasks (pose estimation and semantic segmentation) demonstrate that LCA significantly reduces transmission latency compared to prior work (average reduction of 47.11%-89.55%, 95-percentile reduction of 27.63%-88.78%) and computational overhead while maintaining comparable inference accuracy.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4466-4480"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786354","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}

引用次数: 0

HBF MU-MIMO With Interference-Aware Beam Pair Link Allocation for Beyond-5G mm-Wave Networks 超5g毫米波网络中具有干扰感知的HBF MU-MIMO波束对链路分配

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526547

Aleksandar Ichkov;Alexander Wietfeld;Marina Petrova;Ljiljana Simić

{"title":"HBF MU-MIMO With Interference-Aware Beam Pair Link Allocation for Beyond-5G mm-Wave Networks","authors":"Aleksandar Ichkov;Alexander Wietfeld;Marina Petrova;Ljiljana Simić","doi":"10.1109/TMC.2025.3526547","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526547","url":null,"abstract":"Hybrid beamforming (HBF) multi-user multiple-input multiple-output (MU-MIMO) is a key technology for unlocking the directional millimeter-wave (mm-wave) nature for spatial multiplexing beyond current codebook-based 5G-NR networks. In order to suppress co-scheduled users’ interference, HBF MU-MIMO is predicated on having sufficient radio frequency chains and accurate channel state information (CSI), which can otherwise lead to performance losses due to imperfect interference cancellation. In this work, we propose <italic>IABA, a 5G-NR standard-compliant beam pair link (BPL) allocation scheme for mitigating spatial interference in practical HBF MU-MIMO networks. <italic>IABA solves the network sum throughput optimization via either a <italic>distributed or a <italic>centralized BPL allocation using dedicated CSI reference signals for candidate BPL monitoring. We present a comprehensive study of practical multi-cell mm-wave networks and demonstrate that HBF MU-MIMO without interference-aware BPL allocation experiences strong residual interference which limits the achievable network performance. Our results show that <italic>IABA offers significant performance gains over the default interference-agnostic 5G-NR BPL allocation, and even allows HBF MU-MIMO to outperform the fully digital MU-MIMO baseline, by facilitating allocation of secondary BPLs other than the strongest BPL found during initial access. We further demonstrate the scalability of <italic>IABA with increased gNB antennas and densification for beyond-5G mm-wave networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4248-4262"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783237","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}

引用次数: 0

Enhancing Remote Sensing Image Scene Classification With Satellite-Terrestrial Collaboration and Attention-Aware Transmission Policy 基于星地协同和注意感知传输策略的遥感影像场景分类

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526142

Anqi Lu;Youbing Hu;Zhiqiang Cao;Jie Liu;Lingzhi Li;Zhijun Li

{"title":"Enhancing Remote Sensing Image Scene Classification With Satellite-Terrestrial Collaboration and Attention-Aware Transmission Policy","authors":"Anqi Lu;Youbing Hu;Zhiqiang Cao;Jie Liu;Lingzhi Li;Zhijun Li","doi":"10.1109/TMC.2025.3526142","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526142","url":null,"abstract":"Advancements in Earth observation sensors on low Earth orbit (LEO) satellites have significantly increased the volume of remote sensing images. This growth has led to challenges such as higher storage demands, downlink bandwidth stress, and transmission delays, particularly for real-time remote sensing image scene classification (RSISC). To address this, we propose a novel Satellite-Terrestrial Collaborative Scene Classification (STCSC) framework that integrates transmission and computation. The framework employs an attention-aware policy on the satellite, which adaptively determines the sequence of images and selection of image blocks for transmission, as well as these blocks’ sampling rates. This policy is based on image complexity and the real-time data transmission rate, prioritizing blocks crucial for downstream tasks. On the ground, a classification model processes the received image blocks, balancing classification accuracy and transmission delay. Moreover, we have developed a comprehensive simulation system to validate the performance of our framework, including simulations of the satellite, transmission, and ground modules. Simulation results demonstrate that our STCSC framework can reduce transmission delay by 76.6% while enhancing classification accuracy on the ground by 0.6%. Additionally, our attention-aware policy is compatible with any ground classification model.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4496-4509"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786349","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}

引用次数: 0

An Improved Ultra-Lightweight Anonymous Authenticated Key Agreement Protocol for Wearable Devices 一种改进的可穿戴设备超轻量匿名认证密钥协议

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526076

Xin Ai;Akhtar Badshah;Shanshan Tu;Muhammad Waqas;Iftekhar Ahmad

{"title":"An Improved Ultra-Lightweight Anonymous Authenticated Key Agreement Protocol for Wearable Devices","authors":"Xin Ai;Akhtar Badshah;Shanshan Tu;Muhammad Waqas;Iftekhar Ahmad","doi":"10.1109/TMC.2025.3526076","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526076","url":null,"abstract":"For wearable devices with constrained computational resources, it is typically required to offload processing tasks to more capable servers. However, this practice introduces vulnerabilities to data confidentiality and integrity due to potential malicious network attacks, unreliable servers, and insecure communication channels. A robust mechanism that ensures anonymous authentication and key agreement is therefore imperative for safeguarding the authenticity of computing entities and securing data during transmission. Recently, Guo et al. proposed an anonymous authentication key agreement and group proof protocol specifically designed for wearable devices. This protocol, benefiting from the strengths of previous research, is designed to thwart a variety of cyber threats. However, inaccuracies in their protocol lead to issues with authenticity verification, ultimately preventing the establishment of secure session keys between communication entities. To address these design flaws, an improved ultra-lightweight protocol was proposed, employing cryptographic hash functions to ensure authentication and privacy during data transmission in wearable devices. Supported by rigorous security validations and analyses, the proposed protocol significantly boosts both security and efficiency, marking a substantial advancement over prior methodologies.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4543-4557"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786332","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}

引用次数: 0

Generative Diffusion-Based Contract Design for Efficient AI Twin Migration in Vehicular Embodied AI Networks 基于生成扩散的车载人工智能网络双元高效迁移契约设计

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526230

Yue Zhong;Jiawen Kang;Jinbo Wen;Dongdong Ye;Jiangtian Nie;Dusit Niyato;Xiaozheng Gao;Shengli Xie

{"title":"Generative Diffusion-Based Contract Design for Efficient AI Twin Migration in Vehicular Embodied AI Networks","authors":"Yue Zhong;Jiawen Kang;Jinbo Wen;Dongdong Ye;Jiangtian Nie;Dusit Niyato;Xiaozheng Gao;Shengli Xie","doi":"10.1109/TMC.2025.3526230","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526230","url":null,"abstract":"Embodied Artificial Intelligence (AI) bridges the cyberspace and the physical space, driving advancements in autonomous systems like the <underline>Vehicular <underline>Embodied <underline>AI <underline>NETwork (VEANET). VEANET integrates advanced AI capabilities into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AVs), are autonomous entities that can perceive their environment and take actions to achieve specific goals, actively interacting with the physical world. Embodied Agent Twins (EATs) are digital models of these embodied agents, with various Embodied Agent AI Twins (EAATs) for intelligent applications in cyberspace. In VEANETs, EAATs act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving using generative AI models. Due to limited onboard computational resources, AVs offload EAATs to nearby RoadSide Units (RSUs). However, the mobility of AVs and limited RSU coverage necessitates dynamic migrations of EAATs, posing challenges in selecting suitable RSUs under information asymmetry. To address this, we construct a multi-dimensional contract theoretical model between AVs and alternative RSUs. Considering that AVs may exhibit irrational behavior, we utilize prospect theory instead of expected utility theory to model the actual utilities of AVs. Finally, we employ a Generative Diffusion Model (GDM)-based algorithm to identify the optimal contract designs, thus enhancing the efficiency of EAAT migrations. Numerical results demonstrate the superior efficiency of the proposed GDM-based scheme in facilitating EAAT migrations compared with traditional deep reinforcement learning methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4573-4588"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786331","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}

引用次数: 0

Bi-DeepViT: Binarized Transformer for Efficient Sensor-Based Human Activity Recognition 基于传感器的高效人体活动识别的二值化变压器

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-01-06 DOI: 10.1109/TMC.2025.3526166

Fei Luo;Anna Li;Salabat Khan;Kaishun Wu;Lu Wang

{"title":"Bi-DeepViT: Binarized Transformer for Efficient Sensor-Based Human Activity Recognition","authors":"Fei Luo;Anna Li;Salabat Khan;Kaishun Wu;Lu Wang","doi":"10.1109/TMC.2025.3526166","DOIUrl":"https://doi.org/10.1109/TMC.2025.3526166","url":null,"abstract":"Transformer architectures are popularized in both vision and natural language processing tasks, and they have achieved new performance benchmarks because of their long-term dependencies modeling, efficient parallel processing, and increased model capacity. While transformers offer powerful capabilities, their demanding computational requirements clash with the real-time and energy-efficient needs of edge-oriented human activity recognition. It is necessary to compress the transformer to reduce its memory consumption and accelerate the inference. In this paper, we investigated the binarization of a transformer-DeepViT for efficient human activity recognition. For feeding sensor signals into DeepViT, we first processed sensor signals to spectrograms by using wavelet transform. Then we applied three methods to binarize DeepViT and evaluated it on three public benchmark datasets for sensor-based human activity recognition. Compared to the full-precision DeepViT, the fully binarized one (Bi-DeepViT) reduced about 96.7% model size and 99% BOPs (Bit Operations) with only a little accuracy compromised. Furthermore, we explored the effects of binarizing various components and latent binarization of DeepViT to understand their impact on the model. We also validated the performance of Bi-DeepViTs on two wireless sensing datasets. The result shows that a certain partial binarization can improve the performance of DeepViT. Our work is the first to apply a binarized transformer in HAR.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 5","pages":"4419-4433"},"PeriodicalIF":7.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786350","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}

引用次数: 0