IEEE Transactions on Consumer Electronics最新文献

{"title":"Industry Insights Into Kinematics and Injury Risk for Far-Side Occupants During Electric Vehicle Side Pole Impact Accidents","authors":"Fang Wang;Yuanpeng Lv;Chunguang Long;Lin Hu;Zhangchi Liu;Yu Liu;Zhou Zhou","doi":"10.1109/TCE.2025.3557871","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557871","url":null,"abstract":"With the rapid growth in the number of electric vehicles equipped with advanced consumer electronics, the rate of impact accidents has also been rising year by year. Side pole impact tests are an important method for evaluating the collision safety of these modern electric vehicles. The purpose of this study is to gain industry insights into the kinematics and injury risk for far-side occupants in electric vehicle side pole impacts. This study uses a full-scale finite element model of an electric vehicle and a human body finite element model to conduct an in-depth analysis of the occupant’s kinematic response and the risk of injury to the head, neck, chest, and internal organs under various conditions by changing the relative position and impact angle between the rigid pole and the vehicle. The results show that the seatbelt fails to effectively restrict the upper body movement of the occupants, leading to the occupants slipping out of the seatbelt; the position of the impact significantly affects the injury risk to the occupants, with the highest probability of injury occurring during an A pillar impact and a lowest probability during a C pillar impact. In 28%–40% of the cases, the risk of far-side occupants sustaining serious head and brain abbreviated injury scale AIS 3+ injuries exceeds 40%, and in 22% of the cases, the probability of occupants sustaining diffuse axonal injuries based on which metric is higher than 40%; there is no correlation between the head injury criterion HIC15 and the impact angle, but a weak correlation exists between HIC15 and maximum principal strain (MPS); a strong positive correlation is found between the impact angle and brain injury criterion BrIC/MPS. The predicted MPS of nearly 40% and 80% of the far-side occupants’ anterior longitudinal ligament and posterior longitudinal ligament exceeds the injury threshold, respectively, while in all cases, the predicted MPS of the occupants’ capsular ligament and interspinous ligament exceeds the injury threshold, which indicates an extremely high risk of ligament injury. The peak strains of the internal organs of all far-side occupants exceed the threshold, indicating that the occurrence of these internal organ injuries mainly stems from a viscous mechanism, and the peak strains have a strong positive correlation with the impact angle.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"2407-2420"},"PeriodicalIF":10.9,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868258","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":"Text Generation of Speech Imagery Based on an Enhanced CTA-BiLSTM Model Utilizing EEG Signals","authors":"Hongguang Pan;Xin Chu;Rui Miao;Mei Wang;Yiran Wang;Zhuoyi Li","doi":"10.1109/TCE.2025.3557912","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557912","url":null,"abstract":"Recent studies have demonstrated the potential application of speech imagery neural signals in brain–computer interface (BCI) technology. Text generation based on speech imagery offers a natural communication method for individuals with speech disabilities. However, the limitations in imagined content and the immaturity of text generation technology currently constitute an obstacle to its applications. Therefore, this study proposes an enhanced CTA-BiLSTM model for efficient text generation utilizing speech imagery electroencephalography (EEG) signals, significantly enhancing the accuracy and fluency of text generation. Firstly, distinct from the prevailing imagination of characters and words, this study has assembled a sentence-level EEG dataset from ten subjects to facilitate communication. Subsequently, addressing the temporal dynamics characteristics and sequence dependencies of sentence signals, we employ dynamic time warping (DTW) and hidden Markov models (HMM) for accurate temporal alignment and signal annotation to generate fine-grained sentence labels. Finally, the proposed CTA-BiLSTM model leverages channel-time attention mechanism to dynamically adjust weights across channels and time, emphasizing critical features. Concurrently, the bidirectional long short-term memory (BiLSTM) network captures and utilizes long-term dependencies in the EEG signals, thereby enhancing the accuracy of the model in decoding complex temporal patterns. The experimental results demonstrate that the average sentence decoding accuracy can reach 67.50% on the self-built dataset, realizing a better evaluation accuracy and validating its potential for application.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"3442-3453"},"PeriodicalIF":10.9,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868110","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":"Dual Backbone Multi-Attention Hierarchical Fusion and Feature Enhancement Network for Crowd Counting","authors":"Chunling Zheng;Zhenyu Chen;Xingyu Gao;Lei Lyu","doi":"10.1109/TCE.2025.3557449","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557449","url":null,"abstract":"In recent years, significant progress has been made in crowd counting with the development of convolutional neural networks (CNNs). However, while CNNs excel at extracting local features, their limited receptive fields restrict their ability to model global context. In contrast, Transformers can effectively model long-distance dependencies, but are inferior to CNN in capturing local detail features. Local details and global context information are crucial to handle large-scale changes in crowds. To address this problem, we propose a novel dual backbone network (DBNet) that integrates CNN and Transformer architectures, aiming to capture and aggregate both global semantic information and local detail features at multiple levels. Specifically, the dual backbone structure is designed to extract fine-grained local features while modeling long-range contextual relationships. Additionally, we introduce a multi-attention hierarchical fusion module (MAHF) that integrates global and local features from the two backbones while suppressing background noise. To further enhance accuracy in the presence of multi-scale variations, we also employ a Feature Enhancement Module (FEM), which enables the network to more effectively identify edge features and facilitates more effective multi-scale feature modeling. Extensive experiments on ShanghaiTech, UCF-QNRF, and JHU-Crowd++ datasets demonstrate that DBNet achieves competitive performance, validating the effectiveness of our approach.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"3279-3293"},"PeriodicalIF":10.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144867682","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":"A Resource Optimization Approach Based on Deep Integration of Vision-Motion System for Sustainable Agriculture","authors":"Minghao Cheng;Nan Zhou;Mughair Aslam Bhatti;Di Li;Shiyong Wang;Areej Alasiry;Mehrez Marzougui;Zeeshan Zeeshan","doi":"10.1109/TCE.2025.3552586","DOIUrl":"https://doi.org/10.1109/TCE.2025.3552586","url":null,"abstract":"The integration of vision and motion systems represents a critical phase in the intelligent transformation of consumer electronics aimed at enhancing productivity. However, owing to the operational modes and distributional characteristics inherent in existing systems, achieving large-scale, stable, and consistent agricultural applications on consumer electronics remains a significant challenge. To address this problem, this paper proposes a unified resource optimization approach for different configurations of agricultural consumer electronics to achieve deep integration of vision and motion systems. The optimization is mainly at two levels: on the one hand, we design a velocity observer for the vision-motion integrated system represented by the visual servoing system, which makes native changes to the characteristics of the visual servoing’s non-real-time instruction issuance. By converting long-time commands with uncertain period to short-time commands with certain period, the design difficulty of real-time trajectory planning of the real underlying motion controller is simplified. On the other hand, in image-based visual servoing (IBVS) system, the mixture parameter of the image Jacobian matrix also affect the control performance of the visual servoing system. For most IBVS-based agricultural applications, there is a lack of a systematic approach to ensure that the mixture parameter is adaptively and continuously varied. To solve this problem, this paper proposes a fuzzy logic-based method to adaptively adjust this parameter and ensure its continuity by introducing a suitable membership function. The experimental results of visual servoing based on the consumer electronics show that our proposed method can significantly improve the integrated vision-motion controllability, and can trade-off the convergence efficiency and feature retention constraints to effectively improve the overall efficiency of the system operation.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"6900-6909"},"PeriodicalIF":10.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868130","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":"Efficient Gaussian Process Classification-Based Physical-Layer Authentication With Configurable Fingerprints for 6G-Enabled IoT","authors":"Rui Meng;Fangzhou Zhu;Xiqi Cheng;Xiaodong Xu;Bizhu Wang;Chen Dong;Bingxuan Xu;Xiaofeng Tao;Ping Zhang","doi":"10.1109/TCE.2025.3557239","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557239","url":null,"abstract":"The future 6G-enabled IoT will facilitate seamless global connectivity among ubiquitous wireless devices, but this advancement also introduces heightened security risks such as spoofing attacks. Physical-Layer Authentication (PLA) has emerged as a promising, inherently secure, and energy-efficient technique for authenticating IoT terminals. Nonetheless, the direct application of state-of-the-art PLA schemes to 6G-enabled IoT encounters two major hurdles: inaccurate channel fingerprints and the inefficient utilization of prior fingerprint information. To tackle these challenges, we leverage Reconfigurable Intelligent Surfaces (RISs) to enhance fingerprint accuracy. Additionally, we integrate active learning and Gaussian Processes (GPs) to propose an Efficient Gaussian Process Classification (EGPC)-based PLA scheme, aiming for reliable and lightweight authentication. Following Bayes’ theorem, we model configurable fingerprints using GPs and employ the expectation propagation method to identify unknown fingerprints. Given the difficulty of obtaining sufficient labeled fingerprint samples to train PLA models, we propose three fingerprint selection algorithms. These algorithms select unlabeled fingerprints and query their identities using upper-layer authentication mechanisms. Among these methods, the optimal algorithm reduces the number of training fingerprints needed through importance sampling and eliminates the requirement for PLA model retraining through joint distribution calculation. Simulations results reveal that, in comparison with non-RIS-based approaches, the RIS-aided PLA framework decreases the authentication error rate by 98.69%. In addition, our designed fingerprint selection algorithms achieve a reduction in the authentication error rate of up to 86.93% compared to baseline active learning schemes.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"2603-2617"},"PeriodicalIF":10.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144867782","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":"End-to-End Human Motion Recognition With Multidomain Dual Attention Transformer Fusion Network and Millimeter-Wave Radar","authors":"Chao Fang;Yong Wang;Mu Zhou;Wei He;Qian Zhang;Yu Pang;Bao Peng","doi":"10.1109/TCE.2025.3557084","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557084","url":null,"abstract":"Human-computer interaction technology, by improving user experience and ease of use, drives innovation and growth in consumer electronics. As a noninvasive and noncontact sensing device, millimeter-wave radar has attracted great attention in human motion recognition for human-computer interaction. However, previous motion recognition models are generally based on radar echo data, i.e., images and point cloud, and single domain radar information, resulting in the loss of raw radar data information and a limited ability to capture the complementary global features. In this paper, a novel end-to-end joint global-local dual attention transformer model for human motion recognition using mmWave radar is proposed to address the above problem. First, we introduce a learnable complex transformation module to process raw radar signals for different inputs. Then, we design two important feature extraction modules, named dual residual attention module (DRAM) and dual coupled filter module (DCFM), to accurately extract the valuable motion information of the radar signal. Furthermore, a position encoding is utilized to obtain the time information of inputs feature and a transformer module is designed to get long-range context global information. Finally, the experimental results show that our proposed method achieves an average accuracy of 99.17% on the human gesture dataset and an average accuracy of 99.72% on the arm motion dataset, which demonstrates that our model has both high recognition accuracy and strong robustness.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"3252-3265"},"PeriodicalIF":10.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144867681","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":"Demand-Aware Terminal Collaboration in Vehicular Edge Computing: A Task-Driven Hierarchical DRL","authors":"Sijun Wu;Liang Yang","doi":"10.1109/TCE.2025.3557204","DOIUrl":"https://doi.org/10.1109/TCE.2025.3557204","url":null,"abstract":"With the increase of users in the Internet of Vehicles (IoV), various heterogeneous user demands are also increasing. The current contradiction in the development of Vehicle Edge Computing (VEC) is how to satisfy all kinds of heterogeneous task requirements in the dynamically changing channel environment. This paper proposes an efficient collaborative scheme for demand-aware terminals, based on spectrum-sharing techniques and Deep Reinforcement Learning (DRL) algorithms, to dynamically satisfy the demands of heterogeneous tasks. Specifically, the delay and energy consumption of two types of tasks are modeled and a multi-objective optimization problem is constructed based on different task requirements. Thereafter, we propose a heuristic algorithm to determine the suboptimal solution for optimization variables such as unloading volume. Furthermore, to realize the purpose of dynamically allocating resources according to the channel state, this paper constructs a multi-intelligence body reinforcement learning framework. Moreover, a task-driven hierarchical DRL algorithm is proposed to solve the problem considering that the optimization variables possess discrete and continuous variables. Finally, the scheme’s effectiveness is verified through extensive simulation experiments and comparison with other benchmark schemes.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"3849-3861"},"PeriodicalIF":10.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868390","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":"Optimal Strategy for Task Offloading and Resource Pricing Behavior Based on Blockchain","authors":"Xue Zhai;Shanchen Pang;Nuanlai Wang;Haiyuan Gui;Xiao He","doi":"10.1109/TCE.2025.3551825","DOIUrl":"https://doi.org/10.1109/TCE.2025.3551825","url":null,"abstract":"End-edge-cloud computing improves efficiency and reduces latency by allocating mobile device tasks between edge nodes and cloud servers. However, task allocation and resource pricing in complex multi-user, multi-task environments remain challenging. This paper proposes an end-edge-cloud task offloading strategy based on blockchain technology, utilizing Stackelberg game theory for resource pricing (BMSGRP). We designed a multi-level Stackelberg game model with cloud servers as the leaders, edge servers as the sub-leaders, and mobile devices as the followers. By proving the monotonicity of the overall system benefit model, we derived the unique equilibrium solution. Then, we use blockchain technology to construct a decentralized resource transaction ledger, recording the task offloading and resource pricing results of various devices. We employ the an improved consensus mechanism based on reputation scoring (mRS-DBFT) to ensure the security and transparency of data and transactions. Finally, we evaluated the performance of this strategy through simulation experiments across various scenarios. The results indicate that our method significantly improves system efficiency compared with local task execution and random offloading.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"7290-7303"},"PeriodicalIF":10.9,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868273","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":"A Simple Integration Architecture of Photovoltaic Plant for Consumer Electronics in LVDC Systems","authors":"Ali Faisal Murtaza;Afaq Hussain;Hadeed Ahmed Sher;Abdulhakeem Alsaleem;Filippo Spertino","doi":"10.1109/TCE.2025.3574805","DOIUrl":"https://doi.org/10.1109/TCE.2025.3574805","url":null,"abstract":"Low voltage direct current (LVDC) system with photovoltaic (PV) source typically contains multiple converters that are used to control the power flow from the PV array to DC loads leading to less end-to-end efficiency, control complexity, reliability issues, voltage regulation challenges, compactness issues, and increased system cost. In this paper, a new power flow architecture is designed for LVDC system that directly connects the PV array to consumer electronics (rated at 24 V) and employs only one front-end bidirectional DC-DC converter between the 24 V load line and the 48 V bus. The bi-directional converter manages load line voltage regulation through a 48 V bus. Under normal conditions, the PV array powers the load while seeking minimal support from the 48 V bus via bi-directional converter, while extensive power is drawn only when the PV output is insufficient for the load requirement, ensuring differential power processing. By introducing a unique power flow layout with a simple design and eliminating intermediate converters, this architecture offers superior end-to-end efficiency, simplified control, and greater reliability compared to previous solutions. To assess theoretical efficiency, a mathematical model of the proposed architecture is also developed. Simulation tests have been conducted, which validate the fundamentals of proposed architecture and indicate its efficiency over 95% under normal weather conditions. Moreover, the comparative analysis confirms the superior capability of proposed architecture over existing ones. Finally, the functionality of the proposed architecture is verified by experimental prototype.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"2689-2701"},"PeriodicalIF":10.9,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868233","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":"Performance Degradation Analysis of Downlink NOMA Systems Under Carrier Frequency Offsets","authors":"Mokhtar Besseghier;Abdelhak Zouggaret;Samir Ghouali;Ahmed Bouzidi Djebbar","doi":"10.1109/TCE.2025.3571676","DOIUrl":"https://doi.org/10.1109/TCE.2025.3571676","url":null,"abstract":"In this paper, we analyze the impact of carrier frequency offset (CFO) on downlink non-orthogonal multiple access (NOMA) systems. Our research objectives are to quantify performance degradation due to CFO and develop mitigation strategies for practical deployments. Using analytical modeling and closed-form derivations, we establish explicit mathematical relationships between CFO magnitude, power allocation coefficients, and system performance metrics. Our results reveal that users with higher power allocations experience quadratically increasing SNR degradation with CFO magnitude, with up to a 45% sum rate reduction at high CFO values. The core innovation of this work is twofold: first, we provide comprehensive closed-form expressions for SNR, achievable rate, and outage probability under various fading models; second, we develop an adaptive power allocation algorithm that dynamically adjusts coefficients based on real-time CFO estimates and channel conditions. This algorithm demonstrates significant performance improvements, reducing sum rate degradation by up to 25% compared to fixed allocation schemes while maintaining quality-of-service requirements.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 2","pages":"2508-2516"},"PeriodicalIF":10.9,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868254","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}