IEEE Transactions on Consumer Electronics最新文献_第3页

A Holistic and Personalized Home Energy Management System With Non-Intrusive Load Monitoring 具有非侵入式负荷监测的整体和个性化家庭能源管理系统

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-21 DOI: 10.1109/TCE.2024.3483938

Christos L. Athanasiadis;Theofilos A. Papadopoulos;Georgios C. Kryonidis;Dimitrios I. Doukas

{"title":"A Holistic and Personalized Home Energy Management System With Non-Intrusive Load Monitoring","authors":"Christos L. Athanasiadis;Theofilos A. Papadopoulos;Georgios C. Kryonidis;Dimitrios I. Doukas","doi":"10.1109/TCE.2024.3483938","DOIUrl":"https://doi.org/10.1109/TCE.2024.3483938","url":null,"abstract":"This paper introduces a holistic, multi-objective home energy management system (HEMS) designed to optimize residential electrical and thermal demands. By incorporating dynamic electricity tariffs and integrating solar production with storage units, the system aims to minimize energy costs while ensuring thermal comfort through energy-efficient solutions. Environmental sustainability and the impact on the distribution grid are also considered within the formulated optimization problem. A non-intrusive load monitoring tool is employed to schedule the operation of flexible appliances tailored to user habits, achieving a mean absolute error below 14W and an \u0000<inline-formula> <tex-math>$rm {F_{1}}$ </tex-math></inline-formula>\u0000 score exceeding 0.8 for the most energy-intensive appliances across three public datasets. Analysis of five operating scenarios highlights the impact of each objective on system performance. The proposed HEMS outperforms baseline solutions, substantially reducing operational and environmental costs up to 42% and 27%, respectively. Moreover, it diminishes user discomfort by up to 86% and alleviates stress on the grid by 33%.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6725-6737"},"PeriodicalIF":4.3,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918112","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

ResFNN: Residual Structure-Based Feedforward Neural Network for Action Quality Assessment in Sports Consumer Electronics 基于残差结构的前馈神经网络用于体育消费电子产品的动作质量评估

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-17 DOI: 10.1109/TCE.2024.3482560

Honghao Gao;Si Yu;Muddesar Iqbal;Mohsen Guizani

{"title":"ResFNN: Residual Structure-Based Feedforward Neural Network for Action Quality Assessment in Sports Consumer Electronics","authors":"Honghao Gao;Si Yu;Muddesar Iqbal;Mohsen Guizani","doi":"10.1109/TCE.2024.3482560","DOIUrl":"https://doi.org/10.1109/TCE.2024.3482560","url":null,"abstract":"With the development of artificial intelligence (AI) and sports consumer electronics, AI-empowered Olympic sport technologies are being implemented more extensively. Action quality assessment (AQA), a sport action recognition and video refereeing technology, aims to automatically score action performance in videos obtained from sports consumer electronics deployed in arenas. It has gained much attention for its wide range of applications, such as sports event scoring, specific skill assessment, and rehabilitation medicine. General methods score action performance by directly regressing the initial video features to score, which neglects the possibility that the initial features are insufficiently effective. To address this issue, we propose a residual structure-based feedforward neural network (ResFNN) that enables efficient action feature learning to attain improved score assessment performance. First, the input videos are downsampled to clips and passed through inflated 3D convolutional networks (ConvNets) to obtain initial action video features. These features contain spatiotemporal information about the human actions occurring in the videos. Second, these features are aggregated and learned through our ResFNN. The ResFNN is composed of feedforward neural network residual blocks, which have strong function fitting and feature conversion capabilities. Therefore, the network learns features well and obtains more effective features. Third, a score distribution regression method is applied to obtain the underlying score distribution. This step establishes a more accurate mapping between the videos and scores. Finally, our method is demonstrated to outperform the majority of the existing methods through experiments conducted on the AQA-7, MTL-AQA, and JIGSAWS datasets.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6653-6663"},"PeriodicalIF":4.3,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918401","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

Harnessing Multimodal Data and Deep Learning for Comprehensive Gait Analysis in Pediatric Cerebral Palsy 利用多模态数据和深度学习进行小儿脑瘫的综合步态分析

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-17 DOI: 10.1109/TCE.2024.3482689

Jing Yang;Liangyu Li;Lip Yee Por;Sami Bourouis;Sami Dhahbi;Abdullah Ayub Khan

{"title":"Harnessing Multimodal Data and Deep Learning for Comprehensive Gait Analysis in Pediatric Cerebral Palsy","authors":"Jing Yang;Liangyu Li;Lip Yee Por;Sami Bourouis;Sami Dhahbi;Abdullah Ayub Khan","doi":"10.1109/TCE.2024.3482689","DOIUrl":"https://doi.org/10.1109/TCE.2024.3482689","url":null,"abstract":"Cerebral palsy (CP) is a leading cause of motor dysfunction in children, significantly impacting gait and mobility. Accurate and early diagnosis of gait abnormalities in pediatric CP patients is crucial for effective intervention and management. However, making an early-stage CP diagnosis based only on a single vision modality such as an MRI has many difficulties. Because of the baby’s obstinate movements, the possibility of early recovery, the lack of a single vision modality, and the noisy or absent brain magnetic resonance imaging (MRI) slices, the task is getting harder and harder. This study employed a robust framework that leverages data from multiple sensor modalities, including wearable inertial measurement units (IMUs), pressure-sensitive mats, and motion capture systems integrated with MRI to generate multimodal data. This multimodal data was then processed using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to capture both spatial and temporal dynamics of gait patterns. In the experimentation, we achieved remarkable results with an accuracy of 95.33%, an AUC of 96.2%, an F1 score of 95.28%, and a misclassification rate of 0.0467. Also, the comparative analysis with state-of-the-art demonstrates that the proposed approach significantly outperforms traditional methods in identifying subtle gait abnormalities, providing a more detailed and accurate assessment of gait deviations in pediatric cerebral palsy patients.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 3","pages":"5401-5410"},"PeriodicalIF":4.3,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844399","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

Your IP Camera Can Be Abused for Payments: A Study of IoT Exploitation for Financial Services Leveraging Shodan and Criminal Infrastructures 你的IP摄像头可能被滥用于支付：利用Shodan和犯罪基础设施的金融服务物联网开发研究

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-17 DOI: 10.1109/TCE.2024.3482708

Yuba R. Siwakoti;Manish Bhurtel;Danda B. Rawat;Adam Oest;RC Johnson

{"title":"Your IP Camera Can Be Abused for Payments: A Study of IoT Exploitation for Financial Services Leveraging Shodan and Criminal Infrastructures","authors":"Yuba R. Siwakoti;Manish Bhurtel;Danda B. Rawat;Adam Oest;RC Johnson","doi":"10.1109/TCE.2024.3482708","DOIUrl":"https://doi.org/10.1109/TCE.2024.3482708","url":null,"abstract":"The Internet of Things (IoT) devices are being abused by exploiting their vulnerabilities. Despite the significant efforts to improve IoT security, IoT devices are still at higher risk of exploitation than computer systems. First, this paper identifies vulnerable IoT devices by applying a sampling strategy incorporating Common Vulnerabilities and Exposures (CVE) entries, Shodan’s exposure, and public research documents. Then, we investigated IoT abuses in financial crimes for 17 months (October 2021 to February 2023) by mapping IoT devices exposed by Shodan with proxies found in the darknet, underground forums, and Telegram channels. After investigation, we conclude with reasonable confidence that exposed IoT devices are taken over and abused as proxies in criminal activities such as credential stuffing attacks and financial crimes like illegal money transfers, cryptocurrency trading and stealing, and credit card fraud. Our study reveals that cameras (IP, network, security) are mostly abused IoT devices as proxies, followed by NAS storage.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"7562-7573"},"PeriodicalIF":4.3,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918455","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

Eco-Driving With Partial Wireless Charging Lane at Signalized Intersection: A Reinforcement Learning Approach 信号交叉口部分无线充电车道生态驾驶：一种强化学习方法

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-16 DOI: 10.1109/TCE.2024.3482101

Xinxing Ren;Chun Sing Lai;Zekun Guo;Gareth Taylor

{"title":"Eco-Driving With Partial Wireless Charging Lane at Signalized Intersection: A Reinforcement Learning Approach","authors":"Xinxing Ren;Chun Sing Lai;Zekun Guo;Gareth Taylor","doi":"10.1109/TCE.2024.3482101","DOIUrl":"https://doi.org/10.1109/TCE.2024.3482101","url":null,"abstract":"Consumer electronics such as advanced GPS, vehicular sensors, inertial measurement units (IMUs), and wireless modules integrate vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) within Internet of Things (IoT), enabling connected autonomous electric vehicles (CAEVs) to optimize energy optimization through eco-driving. In scenarios with traffic light intersections and partial wireless charging lanes (WCL), an eco-driving algorithm must consider net and gross energy consumption, safety, and traffic efficiency. We introduced a deep reinforcement learning (DRL) based eco-driving control approach, employing a twin-delayed deep deterministic policy gradient (TD3) agent for real-time acceleration planning. This approach uses reward functions for acceleration, velocity, safety, and efficiency, incorporating a dynamic velocity range model which not only enables the vehicle to smoothly pass the signalized intersections but also uses partial WCL efficiently and time-adaptively while ensuring traffic efficiency in diverse traffic scenarios. Tested in Simulation of Urban Mobility (SUMO) across various intersections with partial WCL, our method significantly lowered net and gross energy consumption by up to 44.01% and 17.19%, respectively, compared to conventional driving, while adhering to traffic and safety norms.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6547-6559"},"PeriodicalIF":4.3,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720214","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918309","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}

引用次数: 0

Enhancing Image Security via Block Cyclic Construction and DNA-Based LFSR 基于块循环构造和dna的LFSR增强图像安全性

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-15 DOI: 10.1109/TCE.2024.3481260

Subhrajyoti Deb;Abhilash Das;Bhaskar Biswas;Joy Lal Sarkar;Surbhi Bhatia Khan;Saeed Alzahrani;Shalli Rani

{"title":"Enhancing Image Security via Block Cyclic Construction and DNA-Based LFSR","authors":"Subhrajyoti Deb;Abhilash Das;Bhaskar Biswas;Joy Lal Sarkar;Surbhi Bhatia Khan;Saeed Alzahrani;Shalli Rani","doi":"10.1109/TCE.2024.3481260","DOIUrl":"https://doi.org/10.1109/TCE.2024.3481260","url":null,"abstract":"The rapidly growing multimedia image data driven by real-time messaging technologies is particularly evident in applications such as autonomous vehicle tracking, smart cities, surveillance systems and many more. Considering images, data privacy and security are of paramount importance. Yet, many existing methods need to pay more attention to the specific challenges posed by chaotic maps, such as limited parameter coverage and insufficient chaotic behaviour. We present a novel method for image encryption that combines a cyclic block function during the confusion phase and a DNA-based Linear Feedback Shift Register (LFSR) in the diffusion phase to render the final cipher image. This process involves diagonal cyclic shifting and swapping of pixel blocks to minimize pixel correlation. DNA cryptography-based LFSR is particularly efficacious in high-quality pseudorandom number generation due to its robust statistical effects. Besides that, DNA-based operations improve the encryption speed, making the process more efficient. The proposed cryptosystem is validated through several methods, including histogram analysis, correlation assessment, entropy measurement, key sensitivity evaluation, and \u0000<inline-formula> <tex-math>$chi ^{2}$ </tex-math></inline-formula>\u0000 testing. Our algorithm offers superior security and efficiency, outperforming established schemes in terms of security and robustness.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 3","pages":"5516-5523"},"PeriodicalIF":4.3,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844294","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

Handheld Laser Rangefinder-Based Location Estimation via Regularity of Fractionally Integrated Signals 基于分数积分信号规律的手持式激光测距仪定位估计

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-14 DOI: 10.1109/TCE.2024.3480894

Yunqi Wang;Zhanbin Zhang;Guoli Yang;Bingo Wing-Kuen Ling;Meilin Wang

{"title":"Handheld Laser Rangefinder-Based Location Estimation via Regularity of Fractionally Integrated Signals","authors":"Yunqi Wang;Zhanbin Zhang;Guoli Yang;Bingo Wing-Kuen Ling;Meilin Wang","doi":"10.1109/TCE.2024.3480894","DOIUrl":"https://doi.org/10.1109/TCE.2024.3480894","url":null,"abstract":"This paper proposes to estimate the location of an object via computing the regularity of the fractionally integrated signals. The features are extracted from the regularity and the random forest is employed for performing the regression. More precisely, the acquired signal is first denoised via a linear phase filter. Second, the fractional ordered integration of the denoised signal is computed. Here, the fractional orders are chosen as 0.4 and 0.5. Then, the regularity of the fractionally integrated signal is computed. Next, the features related to the location of the objects are extracted. Finally, the random forest is employed for estimating the location of the objects. The computer numerical simulation results indicate that the relative errors of our proposed method are 0.0029, 0.0125 and 0.0125 when the target is placed at distances of 3001m to 3500m, 3501m to 4000m as well as 4001m to 4500m from the acquisition device, respectively. In addition, other indicators such as the Pearson correlation coefficient (\u0000<inline-formula> <tex-math>$rho $ </tex-math></inline-formula>\u0000), the mean absolute relative distortion (MARD), the mean absolute error (MAE), the mean squares error (MSE) and the root MSE (RMSE) yielded by our proposed method are superior to those of existing methods. This demonstrates the effectiveness of our proposed method.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6589-6599"},"PeriodicalIF":4.3,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918159","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

Swarm Learning Empowered Federated Deep Learning for Seamless Smartphone-Based Activity Recognition 基于智能手机的无缝活动识别的群学习授权联邦深度学习

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-11 DOI: 10.1109/TCE.2024.3479078

Harun Jamil;Yang Jian;Faisal Jamil;Shabir Ahmad

{"title":"Swarm Learning Empowered Federated Deep Learning for Seamless Smartphone-Based Activity Recognition","authors":"Harun Jamil;Yang Jian;Faisal Jamil;Shabir Ahmad","doi":"10.1109/TCE.2024.3479078","DOIUrl":"https://doi.org/10.1109/TCE.2024.3479078","url":null,"abstract":"In the landscape of smartphone-based human activity recognition (S-HAR), adopting Federated Deep Learning (FDL) introduces challenges, notably in communication inefficiencies and data confidentiality. These issues stem from the requisite submission of learning model parameters by multiple clients to FDL’s global model. To surmount these challenges, the innovative Swarm Learning (SL) paradigm emerges as a solution, presenting a modular approach that fuses distributed computing with blockchain-based coordination. This amalgamation eliminates the dependence on a centralized infrastructure. This study introduces an avant-garde Swarm-Federated Deep Learning framework (SHAR-SFDL) that seamlessly incorporates SL into the FDL framework. SHAR-SFDL orchestrates the collaboration of smartphone users in creating local SL models through blockchain-enabled synergy. The aggregation of these local models into a global FDL model across diverse SL groups is achieved through a groundbreaking method involving model credibility prediction and weight comparison. Notably, the proposed SHAR-SFDL framework showcases a substantial advancement in model performance and a remarkable reduction in edge-to-global communication overhead. Regarding performance evaluation, the proposed model outperformed the other state-of-the-art techniques regarding true and false positive rates across different group densities. Specifically, the TP rates for SHAR-SFDL were 0.891 (High), 0.945 (Medium), and 0.969 (Low), while the corresponding FP rates were 0.035 (High), 0.009 (Medium), and 0.015 (Low).","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6919-6935"},"PeriodicalIF":4.3,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938376","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

Adaptive Learning-Based Cloud-Edge Collaborative Secure Resource Management for Blockchain-Empowered Demand Response 基于自适应学习的云边缘协作安全资源管理，用于区块链授权的需求响应

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-11 DOI: 10.1109/TCE.2024.3478794

Tingzhe Pan;Chao Li;Xin Jin;Wei Zhou;Jiale Liu;Xinlei Cai

{"title":"Adaptive Learning-Based Cloud-Edge Collaborative Secure Resource Management for Blockchain-Empowered Demand Response","authors":"Tingzhe Pan;Chao Li;Xin Jin;Wei Zhou;Jiale Liu;Xinlei Cai","doi":"10.1109/TCE.2024.3478794","DOIUrl":"https://doi.org/10.1109/TCE.2024.3478794","url":null,"abstract":"The rapid development of renewable energy and controllable loads such as consumer electronics requires more user side resources to participate in demand response. Blockchain-empowered demand response can effectively reduce the trust cost among various market entities. However, considering the efficient transaction processing and low-delay interaction requirements of the system, how to jointly optimize blockchain consensus throughput and consensus delay through secure resource management under the decentralization constraint is a key issue. The paper proposes an adaptive learning-based cloud-edge collaborative secure resource management method for blockchain-empowered demand response. Firstly, a blockchain-empowered secure demand response framework is constructed to achieve information exchange among multiple entities. Secondly, under a decentralization constraint in long term, the joint optimization problem of consensus throughput and consensus delay is formulated. The one-slot joint optimization problem is decoupled from long-term decentralization constraint through Lyapunov optimization theory. Finally, a block and channel resource collaboration management optimization algorithm based on security bound violation penalty-driven adaptive DQN is proposed. Based on the security bound violation penalty, the probabilities of exploration and exploitation in the learning process are adaptively adjusted to avoid falling into local optimum. Simulations show that the proposed algorithm performs well in consensus throughput, consensus delay, and decentralization degree.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6568-6579"},"PeriodicalIF":4.3,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918568","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

Nuclear Norm-Based Transfer Learning for Instantaneous Multi-Person Indoor Localization 基于核规范的瞬时多人室内定位迁移学习

IF 4.3 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2024-10-10 DOI: 10.1109/TCE.2024.3477613

Zhiyuan He;Ke Deng;Jiangchao Gong;Desheng Wang;Zhijun Wang;Mahmoud M. Salim

{"title":"Nuclear Norm-Based Transfer Learning for Instantaneous Multi-Person Indoor Localization","authors":"Zhiyuan He;Ke Deng;Jiangchao Gong;Desheng Wang;Zhijun Wang;Mahmoud M. Salim","doi":"10.1109/TCE.2024.3477613","DOIUrl":"https://doi.org/10.1109/TCE.2024.3477613","url":null,"abstract":"Passive indoor localization is emerging as a transformative technology in consumer electronics, notably improving applications in smart buildings, indoor navigation, and dynamic beamforming. Our proposed CSI-ResNet transcends traditional single-target approaches by achieving a multi-target localization accuracy of 99.21% with a precision of 0.6 meters using single-timestamp CSI, surpassing existing methodologies. To mitigate model degradation from WiFi hardware phase errors and the conflation of human and locational features, we implement precise phase compensation and targeted band-stop filtering. Additionally, we have developed a pre-training methodology anchored in nuclear norms that optimizes the network for low-rank representations, significantly enhancing its transferability and ensuring consistently high performance across three transfer scenarios, with accuracy metrics reaching 86.30%, 97.03%, and 93.97% respectively. Furthermore, A robust dataset across varied settings was curated, validating our model’s effectiveness and providing extensive resources for advancing CSI-based localization predictions.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6700-6712"},"PeriodicalIF":4.3,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918514","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