IEEE Transactions on Consumer Electronics最新文献

{"title":"Uncertainty Estimation of Automatic Software Debugging in Open-Source Projects Hosting Platform","authors":"Hetong Liang;Shikai Guo;Hui Li;Chenchen Li","doi":"10.1109/TCE.2024.3524511","DOIUrl":"https://doi.org/10.1109/TCE.2024.3524511","url":null,"abstract":"Fault localization and automatic repair of programs are critical tasks in software debugging. A proficient fault localization and automatic repair system can help developers promptly identify and resolve potential issues in various programs, thereby enhancing development and maintenance efficiency. In automatic software debugging, using transfer learning methods to acquire deep semantic features has shown promising results. However, traditional transfer learning methods are susceptible to the noisy data in datasets, which can affect the quality of extracting deep semantic features. To address this limitation, we propose a self-denoising transfer learning model, D-Helper. This model estimates the joint distribution of noisy and true labels to identify and exclude samples whose labels may have been corrupted, thereby mitigating the impact of noisy data on the quality of deep semantic features. The D-Helper consists of three main components: a software debugging knowledge learning component, a fault automatic localization component, and a fault automatic repair component. The software debugging knowledge learning component employs a self-filtering transfer learning method, efficiently acquiring deep semantic knowledge and mitigating the impact of noisy data on the quality of deep semantic features. The fault automatic localization component utilizes acquired deep semantic information for effective fault localization. The fault automatic repair component adopts a template-based repair method, using obtained deep semantic information to generate a reasonable template selection sequence, achieving efficient automatic fault repair. Comprehensive experiments conducted on the widely-recognized Defects4J benchmark demonstrate significant improvements in fault localization scores: Top-1/3/5 and MFR scores of 98, 151, 177, and 76.44, respectively. These represent enhancements of 7.0%, 4.8%, 3.5%, and 4.4% compared to the baseline model. In the repair phase, our results on Defects4J show a 6.4% improvement over the baseline model. Therefore, D-Helper excels in both fault localization and repair tasks, addressing the challenge of noisy data in deep semantic acquisition to enhance model accuracy and robustness.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"905-917"},"PeriodicalIF":4.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314711","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":"Semi-Supervised Multi-Task Deep Learning for WiFi Fingerprint Database Construction in Building-Scale Localization","authors":"Chun Wang;Juan Luo;Luxiu Yin;Chuang Li;Wenbin Huang;Wei Liang;Kuan-Ching Li","doi":"10.1109/TCE.2024.3524613","DOIUrl":"https://doi.org/10.1109/TCE.2024.3524613","url":null,"abstract":"WiFi-based indoor positioning has emerged as a crucial technology for enabling smart consumer electronic applications, particularly in large-scale buildings. The construction of WiFi fingerprint databases using received signal strength (RSS) is foundational due to its widespread deployment. However, achieving high positioning accuracy typically requires labor-intensive and time-consuming site surveys. While recent crowdsourcing methods have facilitated the collection of numerous RSS samples, these samples frequently lack labels and reliability in multi-scale building environments. In this paper, we design a novel semi-supervised and multi-task mean-teacher model (MTMT-DNN) to annotate crowdsourcing unlabeled multi-scale fingerprint samples. This method enables the construction of a comprehensive fingerprint database without requiring intensive manual effort or compromising positioning accuracy. Our key idea is to first develop a multi-task Deep Neural Network (MT-DNN) for simultaneously annotating building, floor, and intra-floor coordinate labels by leveraging their complementary information. Then we employ the mean-teacher semi-supervised learning to leverage additional unlabeled fingerprint data for further improving the annotating performance and reducing intensive manual effort. Finally, we train the MTMT-DNN model by developing two multi-task loss functions and ensuring consistency between them, thereby enhancing the reliability of the annotated crowdsourced fingerprints. We conducted real-world experiments in a 20,<inline-formula> <tex-math>$000~m^{2}$ </tex-math></inline-formula> site encompassing three multi-story buildings. The results demonstrate that our proposed method significantly reduces the workload of manually collecting labeled fingerprint samples. With only 20% of labeled fingerprints collected, we achieve 99% average annotation accuracy for building and floor labels and an average coordinates annotation error within <inline-formula> <tex-math>$4~m$ </tex-math></inline-formula>.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"488-500"},"PeriodicalIF":4.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308570","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 Sputum Sound Collection and Sputum Deposition Degree Diagnosis System Based on Improved Support Vector Machine Method","authors":"Yixuan Wang;Shuwang Rui;Kehaoyu Yang;Wei Luo;Jiaxing Xie;Ying Liang;Yan Shi","doi":"10.1109/TCE.2024.3524476","DOIUrl":"https://doi.org/10.1109/TCE.2024.3524476","url":null,"abstract":"Sputum sounds are a consistent characteristic of every breath in pneumonia patients. Based on this, this research have designed a novel portable continuous monitoring system that collects 30 seconds of respiratory signals, performs adaptive wavelet thresholding to denoise the signals, and uses a dual threshold method to extract all 1-3 second respiratory sub segments. Optimized Mel-frequency cepstral coefficients are then extracted from these sub-segments for classification and recognition. This research proposes an adaptive wavelet threshold design method based on Bayesian Occam’s rule, providing dual threshold methods and related thresholds suitable for this study. This method improves the frequency domain distribution of Mel filter banks and optimizes the support vector machine classifier. This research proposes a feature transformation method based on sine mapping and an ensemble learning method to further improve the classification accuracy of the model. Compared to directly recognizing the 30-second signal, this approach reduces the data volume, avoids overlap of respiratory spectra, and integrates the recognition results of multiple respiratory segments, achieving a recognition accuracy of nearly 100% for the 30-second signal. These optimization methods can be extended to other machine learning models, providing valuable guidance for research in this field.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"1584-1598"},"PeriodicalIF":4.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144323224","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 Stable Intelligent Model-Based Framework Using Graph Convolutional Networks and MULTIMOORA for Clinical Decision Support Systems","authors":"Chao Zhang;Xiaochuan Li;Wenhui Bai;Arun Kumar Sangaiah;Deyu Li","doi":"10.1109/TCE.2024.3524248","DOIUrl":"https://doi.org/10.1109/TCE.2024.3524248","url":null,"abstract":"Artificial intelligence (AI) is rapidly advancing in consumer electronics, particularly in clinical decision support systems (CDSSs). AI-driven devices enhance the effectiveness of healthcare-related electronics via predictive health analytics, reshaping medical data collection, analysis, and decision-making. Nevertheless, due to the abundance of imprecise, hesitant, and fuzzy information in healthcare data stemming from consumer electronics, AI may misinterpret the data, resulting in erroneous and unstable medical decisions. Therefore, this paper endeavors to establish a stable intelligent medical decision model, employing two essential tools: graph convolutional networks (GCNs) and MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form). First, a granular computing (GrC) framework based on GCNs and MULTIMOORA is established. In this framework, GCNs are initially employed to process multi-modal data within the hesitant fuzzy linguistic (HFL) background. Second, a comprehensive HFL information system (IS) is constructed. Third, three types of multi-granularity (MG) HFL methods are developed via MULTIMOORA. To better address the bounded rationality of decision-makers (DMs), regret theory (RT) is utilized to consolidate the multi-modal data. Finally, the efficacy and practically of the proposed decision model are assessed via a case study on medication selections.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"773-784"},"PeriodicalIF":4.3,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314727","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":"Unbiased Anomalous Trajectory Detection With Hierarchical Sequence Modeling","authors":"Xiangjie Kong;Yuwei He;Guojiang Shen;Jiaxin Du;Zhi Liu;Ivan Lee","doi":"10.1109/TCE.2024.3523565","DOIUrl":"https://doi.org/10.1109/TCE.2024.3523565","url":null,"abstract":"Anomalous trajectory detection plays an important role in the field of trajectory big data mining, providing significant support for identifying drivers traveling at inappropriate speeds and detecting cab fraud. Current studies often use equal-sized grids to represent trajectory points, and they mainly focus on the general shape of trajectories while ignoring the spatial density distribution of trajectories. In addition, existing generative models are biased in learning the patterns of normal trajectories, and the same bias exists in processing labeling information. To address the above two problems, we propose an unbiased anomalous trajectory detection method (HS-UATD) based on hierarchical sequence modeling. Our method constructs a hierarchical structure of the entire spatial region using a quadtree, which captures the location density distribution of the entire spatial region. Our model captures the rich spatio-temporal pattern of trajectories containing spatial hierarchical information and learns the probability distribution of unbiased normal trajectories. We employ both clustering algorithms and anomaly injection techniques to obtain unbiased labeling information, and we define trajectories that deviate from the normal pattern as anomalies. Through extensive experiments on three unbiased, biased and real trajectory datasets, we validate the effectiveness of the method.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"388-401"},"PeriodicalIF":4.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308203","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":"Test-Time Adaptation With Self-Supervised Learning for Gaze Estimation","authors":"Pengwei Yin;Jingjing Wang;Xiaojun Wu","doi":"10.1109/TCE.2024.3523486","DOIUrl":"https://doi.org/10.1109/TCE.2024.3523486","url":null,"abstract":"Gaze estimation plays a significant role in consumer electronics, particularly in the realm of user interface and interactive technology. While existing methods rely on either few-shot adaptation requiring annotated samples or unsupervised domain adaptation necessitating source domain data, these approaches face limitations due to the high cost of annotation and data privacy concerns. This paper addresses this critical gap by introducing a novel test-time adaptation framework for gaze estimation that operates without the need for source domain data or annotated samples for adaptation. Here, we present a dual-objective training strategy that combines supervised and self-supervised learning on the source domain, with a particular focus on a face and eye reconstruction task designed to enhance the learning of head pose and eye direction features crucial for gaze estimation. At test time, our model undergoes adaptation solely through fine-tuning with the self-supervised objective, optimizing the model’s ability to estimate gaze in new, unseen scenarios. Our extensive experiments on benchmarks validate the effectiveness of our approach, demonstrating improved generalization capabilities without the dependency on expensive annotations or sensitive source domain data.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"75-89"},"PeriodicalIF":4.3,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144323037","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 Low-Resolution Video Action Recognition Approach Based on Multi-Scale Reconstruction and Multi-Modal Fusion","authors":"Hui Zheng;Yesheng Zhao;Bo Zhang;Guoqiang Shang;Mohammad H. Yahya Al-Shamri;Haya Aldossary","doi":"10.1109/TCE.2024.3521512","DOIUrl":"https://doi.org/10.1109/TCE.2024.3521512","url":null,"abstract":"The challenge of low-resolution video action recognition task lies in recovering and extracting feature representations that can effectively capture action characteristics with limited semantic information. In this paper, we propose an approach to address this challenge, which primarily comprises a multi-scale reconstruction module and a multi-modal fusion module. In multi-scale reconstruction module, we introduce a frequency-adaptive reconstruction model to reconstruct lost information from multiple scales. For crucial high-frequency sub-band images, we propose a wavelet-based super-resolution generative adversarial network to recover detailed information. In multi-modal fusion module, we propose a two-stream Transformer-based network to mine spatial-temporal joint feature representations from the reconstructed video. Additionally, we utilize another Transformer model to fuse features from different modalities, capturing both consistent and complementary representations. Finally, the fused features are fed into a classifier for recognition. Experimental results show that our proposed model outperforms other models for low-quality action recognition on HMDB51 (<inline-formula> <tex-math>$16times 12~58.70$ </tex-math></inline-formula>%, <inline-formula> <tex-math>$14times 14~62.25$ </tex-math></inline-formula>%, <inline-formula> <tex-math>$80times 60~68.94$ </tex-math></inline-formula>%), UCF101 (<inline-formula> <tex-math>$14times 14~76.74$ </tex-math></inline-formula>%, <inline-formula> <tex-math>$28times 28~84.15$ </tex-math></inline-formula>%, <inline-formula> <tex-math>$80times 60~92.78$ </tex-math></inline-formula>%), and Tiny-VIRAT (35.63%) datasets.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"970-983"},"PeriodicalIF":4.3,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314818","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":"An Explainable Recommendation Method for Artificial Intelligence of Things Based on Reinforcement Learning With Knowledge Graph Inference","authors":"Yunliang Chen;Yuqi Li;Xiaohui Huang;Yuewei Wang;Guishui Zhu;Geyong Min;Jianxin Li","doi":"10.1109/TCE.2024.3521435","DOIUrl":"https://doi.org/10.1109/TCE.2024.3521435","url":null,"abstract":"In the realm of consumer electronics, the integration of knowledge graphs with causal inference significantly advances recommendation systems within the Artificial Intelligence of Things (AIoT). This paper introduces a novel method that addresses the limitations of traditional AIoT-based systems, which tend to prioritize correlation over causality and demonstrate limitations in navigating inference paths across knowledge graphs. A reinforcement learning based knowledge graph model is designed to enhance interpretability and trustworthiness in recommendation processes. A soft reward strategy is employed within a Markov decision process, utilizing a multi-hop scoring function to ensure rational outcome assessments. Additionally, a graph search algorithm with user-conditional action pruning is incorporated to facilitate efficient and accurate sampling of inference paths. Experimental results indicate significant improvements in key performance metrics such as normalized discounted cumulative gain, recall, hit ratio, and precision ratio over existing methods. Furthermore, interpretable reasoning paths are provided, establishing a new benchmark in the AIoT-driven recommendation landscape for consumer electronics.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"1980-1991"},"PeriodicalIF":4.3,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308440","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":"Solar PV-Based Enhanced EV Battery Charging Solution With SOSMCC Disturbance Observer for Seamless Grid Integration via SABCAF Control","authors":"Kalash Srivastava;Shailendra Kumar;Rakesh Maurya;Sanjeevikumar Padmanaban","doi":"10.1109/TCE.2024.3520241","DOIUrl":"https://doi.org/10.1109/TCE.2024.3520241","url":null,"abstract":"The vision of achieving zero-carbon emissions in the automobile sector, powered by solar PV-based charging, fosters clean energy transportation and supports sustainable development. Therefore, this paper proposes a sustainable solution for integrating solar photovoltaic (SPV) systems into residential grids by incorporating an electric vehicle (EV) battery energy storage (BES) system and linear/nonlinear load. It utilizes a second-order sliding mode cascaded control (SOSMCC) to regulate the DC-link voltage and manage EV battery charge/discharge operations. This control system is enhanced with disturbance observers to handle the overshoot/undershoot in the DC-link voltage within a cycle under various dynamic situations, i.e., load perturbation, changing solar insolation, and transitions between grid and vehicle charging modes. After comparing the performance of multiple disturbance observers, the linear extended state disturbance observer (LESDO) demonstrates the lowest undershoot (less than 5%) and settling time among other observers. A robust Sparse-Aware Bias-Compensated Adaptive Filtering (SABCAF) algorithm is employed to calculate the fundamental component of load current, effectively reducing higher and suborder harmonic components from deformed load currents. The comparative analysis shows that SABCAF control improves system dynamics by minimizing mean square (MSE) error, enhancing convergence speed, and injecting lower harmonic currents into the grid, thus improving the power quality of the distribution network. The total harmonic distortion (THD) analysis complies with IEEE 519 standard which is less than 5%.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"516-526"},"PeriodicalIF":4.3,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308439","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":"Breast-Cancer Cell Lines Recognition: Modeling and Simulation With Repulsive Steric Hindrance Approach","authors":"Amit Bhattacharyya;Srinivasa Rao Karumuri;Manash Chanda","doi":"10.1109/TCE.2024.3521993","DOIUrl":"https://doi.org/10.1109/TCE.2024.3521993","url":null,"abstract":"Early detection of breast-cancer cell lines (HTB-126, HTB-26, MCF-7, and T-47D) reliant on double-metalIn0.53Ga0.47As/Si hetero-junctioned dopingless expanded gate Bio-TFET (DM-DL-EG-Bio-HTFET)with enormous sensitivity is specified in this manuscript. Analytical modeling for the configuration has been developedand assessed with Silvaco ATLAS TCAD device simulator. Possible fabrication framework of the projected model is portrayedhere. Optimization of device layout parameters concerning molar fraction of Ga and expanded gate length is performed toachieve superior efficacy. The repulsive nature of steric effect (RSE) is initiated to evade the deviations among the hypothetical evaluations and practical results. Device electrostatics along with the sensing presentations of the offered Bio-HTFET and the impact of RSE on electrical features is explored. A best possible ON-to-OFF current sensitivity (<inline-formula> <tex-math>${mathrm {S}}_{text {Ion/Ioff}}$ </tex-math></inline-formula>) of <inline-formula> <tex-math>$18.6times 10{^{{6}}}$ </tex-math></inline-formula> with average sub-threshold swing sensitivity (SSSA) of 93% are realized for T-47D category breast-cancer cell line with permittivity 32.2. Benchmarking isprepared to offer a quantifiable evaluation of the recommended Bio-HTFET with recently reported articles to spotlight itsefficiency. An utmost 41% inaccuracy in resultant capacitance is estimated devoid of considering RSE. Hence, RSE needs to be incorporated during biosensing investigations to create it generally realistic.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"1054-1062"},"PeriodicalIF":4.3,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314715","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}