IEEE Transactions on Consumer Electronics最新文献

{"title":"A2FA: Adversarial Angular Feature Alignment for Multimodal Indoor Object Recognition","authors":"Huicen Guo;Qiucen Li;Zhikui Chen;Shubin Ma;Wei Wang","doi":"10.1109/TCE.2026.3677625","DOIUrl":"https://doi.org/10.1109/TCE.2026.3677625","url":null,"abstract":"In recent years, object recognition has attracted significant attention as a fundamental task for scene understanding in commercial robotics, particularly within consumer electronic products such as smart home assistants and service robots. In indoor environments, RGB images captured by conventional cameras are prone to variations in lighting conditions and occlusions. In contrast, depth images capture 3-D structural information that helps reduce occlusion effects and handle low-light conditions, leading to more consistent recognition performance. While recent advancements in RGB-Depth (RGB-D) fusion have improved environmental adaptability, two key challenges persist: preserving fine-grained local features in complex environments and achieving robust cross-domain generalization from synthetic data to real-world scenarios. To address the aforementioned challenges, this paper proposes a cross-domain RGB-D indoor object recognition method based on a convolutional neural network (CNN) architecture. By incorporating depth image features, the proposed approach effectively reduces the influence of visual noise present in RGB images. A novel proxy task—angle prediction via circular cropping—is introduced to guide the model in attending to local feature discrepancies between the two modalities. In addition, a domain classifier proxy task, formulated using adversarial learning, is designed to improve the generalization ability of the feature extractor and mitigate the synthetic-to-real domain shift. Experimental results on multiple public datasets demonstrate that the proposed method achieves superior recognition accuracy compared to existing approaches.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6913-6923"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836636","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":"Deep Learning and Wi-Fi Channel State Information-Based Hand Hygiene Monitoring","authors":"Akshay Madan;Siva Sai;Vinay Chamola;David Tipper","doi":"10.1109/TCE.2025.3645283","DOIUrl":"https://doi.org/10.1109/TCE.2025.3645283","url":null,"abstract":"To improve hand hygiene compliance in healthcare settings, we introduce an innovative approach that uses WiFi Channel State Information (CSI) for monitoring handwashing and hand rubbing practices. Traditional methods for ensuring hand hygiene compliance among HCWs often require a lot of resources and may not be as accurate. We present a novel approach to hand hygiene compliance to address this gap, which uses WiFi CSI for hand hygiene compliance. We propose a Random Convolutional Kernels (RCK)-based method for feature extraction from the CSI data and a new time series classification model that enhances accuracy. The proposed method offers a less resource-intensive solution and maintains patient privacy and non-intrusiveness by utilizing existing WiFi infrastructure. The evaluation of our model against existing machine learning models shows higher performance in terms of accuracy and F1 scores. With this work, we aim to enhance the progress in environment-sensing technology for Internet of Things (IoT) environments for healthcare applications.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6049-6056"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836698","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":"Deep Reinforcement Learning for Secure and Energy-Efficient RIS-Assisted UAV Networks Under Imperfect CSI","authors":"Fang Xu;Zhen Wang;Min Deng;Manzoor Ahmed;Yan Zhang;Nada Alzaben;Wali Ullah Khan","doi":"10.1109/TCE.2026.3677344","DOIUrl":"https://doi.org/10.1109/TCE.2026.3677344","url":null,"abstract":"The increasing complexity of urban environments has amplified the demand for secure, reliable, and energy-efficient wireless communications. Traditional terrestrial base stations frequently face challenges in dense urban areas, mainly due to recurring non-line-of-sight (NLOS) scenarios, intense interference, and high susceptibility to eavesdropping. Uncrewed aerial vehicles (UAVs) have stood out as a valuable supplementary option, thanks to their ability to support flexible deployment and reliable line-of-sight (LOS) connections. Meanwhile, millimeter-wave (mmWave) bands provide abundant spectrum to satisfy the growing capacity demands of urban networks, but remain highly susceptible to path loss, blockages, and beam misalignment, limiting their effectiveness in such environments. As a cost-efficient and energy-conscious option, reconfigurable intelligent surfaces (RIS) work by smartly reconfiguring wireless reflections to recover blocked links, expand coverage range, and boost secrecy performance. This paper investigates a RIS-aided UAV mmWave communication framework engineered to jointly address energy efficiency and physical layer security under potential eavesdropping threats. A deep reinforcement learning (DRL) strategy is formulated, where the UAV agent interacts with the dynamic urban environment based on imperfect channel state information (CSI) and local position feedback. The agent jointly optimizes UAV active beamforming, RIS phase shifts, and UAV trajectory in real time. To mitigate estimation bias, a softmax operator is incorporated into the learning process. Simulation findings demonstrate that the method put forward in this study outperforms baseline solutions relying on DRL. Specifically, it alleviates both overestimation and underestimation issues while significantly improving secrecy capacity and secure energy efficiency in RIS-assisted UAV mmWave systems.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7093-7104"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836739","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":"Consumer-Oriented Stability Augmentation of 2-Stage 1-Phase Solar PV Systems Using Digital Twin","authors":"Arun Kumar;Nishant Kumar","doi":"10.1109/TCE.2026.3675900","DOIUrl":"https://doi.org/10.1109/TCE.2026.3675900","url":null,"abstract":"This paper presents the stability monitoring of a consumer-oriented two-stage single-phase grid-connected solar photovoltaic (SPV) system using Digital Twin (DT) subjected to various perturbations. The DT is meticulously developed utilizing discretized equations derived from the Backward-Euler method augmented by the Enhanced Momentum Search Optimization (EMSA) algorithm to optimize system tuning and facilitate effective data collaboration and proposed Limit Cycle Oscillator Tuned Generalized Integrator-Unit Vector Template (LCOGI-UVT) for the pre-eminent control of inverter. This integration ensures a more refined and efficient modeling process, enhancing the overall performance and reliability of the DT. Following the establishment of the DT’s operational integrity, the stability of this model is systematically assessed at every operational point through the application of the Lyapunov approach. Additionally, the stability of a proposed control strategy is monitored using the Jacobian methodology. The DT for the system is implemented in OPAL-RT, with experimental validation conducted on a physical testbed, confirming the model’s robustness, accuracy (>98%), and relevance for intelligent consumer electronic systems.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5594-5601"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836874","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":"Consumer-Centric Control of Grid-Interactive PV Systems Using AGI-CTS-MPC-SODA for Enhanced Power Quality and Reliability","authors":"Kingsuk Majumdar;Naresh Kumar Kumawat;Nishant Kumar;Subrata Banerjee","doi":"10.1109/TCE.2026.3675880","DOIUrl":"https://doi.org/10.1109/TCE.2026.3675880","url":null,"abstract":"The integration of renewable energy sources with weak distribution grid and local highly nonlinear loads, such as solar photovoltaics (PV), demands the development of advanced control strategies to address key challenges, including the optimization of controller parameters, ensuring DC-link voltage stability, supply optimal nonlinear power to local consumers, and achieving robust synchronization with the grid at Point of Common Coupling (PCC). This paper introduces a novel AGI (Advanced Generalised Integrator)-CTS (Chi-square Teager-Kaiser energy operator Selfish herd optimizer)-MPC (Model Predictive Control) with SODA (Second Order Derivative based Adaptive) control strategy for 3-phase single-stage grid-interactive PV systems. Here, AGI is used to filter the harmonics from the grid voltage, which is used for unit template generation for accurate grid synchronization. It is also used with consumer load to estimate the active and nonlinear power requirement. CTS is used for controller parameter tuning in dynamic condition, specially when variation is large and rapid. MPC is used for optimal switching pulse generation for inverter by minimizing error and improving grid current quality. SODA is used for accurate maximum power peak detection, specially when solar PV irradiation is changing very drastically. This AGI-CTS-MPC-SODA control strategy is dedicatedly designed and developed for 3-phase single-stage grid-interactive PV systems. The developed control strategy is tested on hardware prototype under different adverse grid, load and solar condition, demonstrates significant improvements in DC-link voltage stability, power quality, and system reliability, making this approach highly suitable for next-generation consumer power electronics.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5571-5578"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836832","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 Energy-Efficient FPGA-Based Transformer Accelerator for AIoT Consumer Electronics Using Dual-Side Diagonal Sparsity","authors":"Sichen Liu;Yuqin Zhao;Haotian Liu;Haihang Xia;Xinyi Wang;John Goodenough;Charith Abhayaratne;Tiantai Deng","doi":"10.1109/TCE.2026.3688916","DOIUrl":"https://doi.org/10.1109/TCE.2026.3688916","url":null,"abstract":"Consumer electronics, such as smartphones, wearables, and smart cameras, increasingly demand real-time and energy-efficient on-device intelligence enabled by Artificial Intelligence (AI) and the Internet of Things (IoT) to support perception and control under strict latency and power constraints. Transformer-based models have been increasingly adopted in sensing and perception tasks due to their ability to capture contextual relationships via self-attention. However, their high computational and memory costs limit their practicality on resource- and power-constrained Artificial Intelligence of Things (AIoT) devices. To address these challenges, we propose a dual-side diagonal sparsity mechanism that partitions the <inline-formula> <tex-math>$Q$ </tex-math></inline-formula> and <inline-formula> <tex-math>$K$ </tex-math></inline-formula> matrices into <inline-formula> <tex-math>$2times 2$ </tex-math></inline-formula> blocks and applies diagonal pruning within each block, reducing computation and memory overhead while preserving transposition invariance and hardware-friendly regularity. We design the Sparse Processor Architecture for Transformer Acceleration (SPATA), a Field-Programmable Gate Array (FPGA)-based framework for energy-efficient on-device Transformer inference on AIoT devices, supporting both sparse–sparse and dense–dense matrix multiplications in multi-head self-attention (MHSA). SPATA integrates a Dual-Mode Matrix Unit (DMMU) along with a diagonal prune–compress module and a vector unit supporting fused addition and rectified linear unit (ReLU) operations. Experimental results on a Xilinx Kintex-7 FPGA show that SPATA achieves 168.48 giga operations per second (GOP/s) throughput, 0.05 ms latency, and 82.18 GOP/J energy efficiency on MHSA workloads, delivering up to a <inline-formula> <tex-math>$40times $ </tex-math></inline-formula> speedup over Central Processing Units (CPUs) and Graphics Processing Units (GPUs) baselines and outperforming prior FPGA-based Transformer accelerators.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7649-7661"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836936","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":"Mish-BiFPN: Temperature-Controlled Mish Activation With Bidirectional Feature Pyramid Networks for Thermal Hotspot Detection and Energy Conservation in Photovoltaic Panels","authors":"Rhaditia Kurnia Asyuri;Arun Kumar Sangaiah;Wei Tong Chen","doi":"10.1109/TCE.2026.3667852","DOIUrl":"https://doi.org/10.1109/TCE.2026.3667852","url":null,"abstract":"The current level of adoption of solar photovoltaic systems requires better methods of thermal fault monitoring, which will support sustainable energy production systems. The application of traditional methods in detecting hotspots is highly significant in analysing the thermal anomaly pattern, but the procedure is ineffective since the process of inspection is manual, time-consuming, and labour-intensive. However, thermal imaging devices offer scalable solutions that are limited in terms of managing complex thermal patterns and combining temperature data at various scales. This paper proposes a Mish-BiFPN Framework to detect thermal hotspots in solar PV systems. Unlike conventional BiFPN or Mish-based models, the proposed framework integrates a temperature-controlled Mish activation with CBAM-guided fusion at every pyramid level, combined with a RegNet backbone and thermal-preserving preprocessing to enhance sensitivity to subtle heat gradients. The offered architecture uses multi-scale feature extraction and attention layers in a way that the model can focus on temperature-sensitive and spatial features at different pyramid layers. It ensures thermal characteristics are retained through preprocessing and data augmentation. The framework further provides a basis to combine the real-time thermal performance monitoring with long-term energy planning that allows dynamically calibrating estimates of solar PV energy generation. This model is trained and validated on thermal hotspot datasets, achieving 12 percentage-point improvement in precision, a 6% improvement in recall, 9% in F1-score, and 21% in Intersection over Union in comparison to the YOLOv10 model. The model shows its potential to address complicated thermal patterns. Energy loss modeling demonstrates that single hotspot detection can prevent approximately 9 kWh per year of power losses per 450 W module. Therefore, this model is very appropriate for large-scale solar PV systems, with both accurate detection and energy conservation optimization.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6629-6642"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837091","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":"HA-Pos: Hierarchical Prompt-Guided Adaptive Detection for Cross-View Visual Positioning System","authors":"Jiehao Zheng;Guoheng Huang;Xiaoyong Chen;Haoran Fang;Kaiqi Zhao;Xiaochen Yuan;Bingo Wing-Kuen Ling;Kim-Fung Tsang;Guanli Chen;Chi-Man Pun","doi":"10.1109/TCE.2026.3676565","DOIUrl":"https://doi.org/10.1109/TCE.2026.3676565","url":null,"abstract":"With the rapid proliferation of Location-Based Services (LBS), achieving high-precision self-positioning on consumer-grade mobile devices—such as smartphones and civil drones—remains a critical challenge, particularly in GPS-denied or multipath-prone urban environments. This paper proposes HA-Pos, a novel hierarchical adaptive prompting mechanism enhancing the Cross-view Visual Positioning System (CVPS) for consumer electronics. The proposed method enables target specification via a user-defined click on a query image captured by a consumer terminal, subsequently locating that object within corresponding satellite reference imagery. Unlike traditional methods struggling with cross-view geometric distortions, HA-Pos incorporates a Hierarchical Prompt Query Encoder (HPQE). This encoder provides precise spatial guidance across various depth stages, significantly bolstering the ability to distinguish target objects from distractors. Building upon this, a Geometric Adaptive Decoupled Head (GAD-Head) is designed to improve geometric adaptability and positioning accuracy. The GAD-Head integrates deformable convolutions as a Deformation-Aware Module (DAM) to effectively capture geometric variations while independently optimizing regression and classification tasks. Extensive experiments demonstrate that HA-Pos achieves state-of-the-art performance on the CVOGL benchmark dataset.(<uri>https://github.com/a-talking-stone/HA-Pos</uri>)","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6077-6088"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837095","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":"Privacy-Preserving Federated Learning Model for Clinical Decision Support in Bladder Cancer Monitoring With CCIoMT Wearables","authors":"Bin Wang;Kai Wu;Yu Cui;Xuebing Han;Hongyu Liu","doi":"10.1109/TCE.2026.3661487","DOIUrl":"https://doi.org/10.1109/TCE.2026.3661487","url":null,"abstract":"Consumer-Centric Internet of Medical Things (CCIoMT) devices, including wearable sensors, home health monitors, and mobile applications, are redefining healthcare by enabling continuous monitoring and predictive decision support outside traditional hospital environments. These devices capture physiological and behavioral data streams that are highly valuable but present two major challenges: preserving the privacy of sensitive health information and addressing the heterogeneity of resource-constrained devices. This paper proposes a privacy-preserving federated learning framework tailored to CCIoMT ecosystems. In this design, raw data remain securely on-device while local models are trained with lightweight optimizers, and only encrypted, differentially private updates are transmitted via secure aggregation. To ensure scalability and robustness, the framework integrates adaptive participation scheduling, communication compression, and fairness-aware optimization, maintaining stability under non-IID conditions and intermittent connectivity. Evaluation on bladder-cancer monitoring data demonstrates near-centralized accuracy (AUROC <inline-formula> <tex-math>$approx 0.98$ </tex-math></inline-formula>) while reducing communication overhead by 30-40% and achieving significant energy savings compared with standard federated methods. Robustness against adversarial updates, subgroup fairness analysis, and SHAP-based interpretability confirm transparency and reliability for clinical adoption. These results establish federated learning combined with edge-fog CCIoMT integration as a practical pathway to secure, efficient, and explainable decision support, advancing personalized healthcare and consumer trust in next-generation medical electronics.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5984-5994"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837041","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":"KArAt-KidneyNet: Proactive Threat Hunting and Anomaly Detection Framework for Consumer Wearable Healthcare Electronics in Kidney Disease Diagnosis","authors":"Jing Yang;Hongjin Wang;Yupeng Chen;Theyazn H. H. Aldhyani;Xu Yan;Lip Yee Por;Jiaxing Lin;Jiawen Wang","doi":"10.1109/TCE.2026.3680956","DOIUrl":"https://doi.org/10.1109/TCE.2026.3680956","url":null,"abstract":"Consumer wearable healthcare electronics, including kidney-monitoring wearables and point-of-care diagnostic devices, generate continuous multimodal physiological and imaging data. Their increasing integration within connected health systems also expands the attack surface, creating vulnerabilities that may affect diagnostic integrity, model reliability, and patient safety. This paper presents KArAt-KidneyNet, a unified framework for kidney disease diagnosis and system-state monitoring that combines Kolmogorov–Arnold Transformer (KArAt) attention, Soft Actor–Critic (SAC)–based adaptive defense, and privacy-preserving federated learning. The proposed KArAt attention module replaces softmax attention with a set of learnable basis functions inspired by the Kolmogorov–Arnold representation concept, enabling structured feature decomposition and interpretable attention maps for ultrasound imaging. The SAC component provides adaptive parameter adjustment for anomaly-aware defensive actions based on system state indicators derived from detection modules. Federated learning with differential privacy is used to train the diagnostic model over decentralized healthcare datasets without sharing raw patient data. Additional protective layers include post-quantum cryptographic signatures resistant to emerging quantum computing threats and blockchain-based logging to ensure authenticity and traceability of diagnostic outputs. Evaluation across multi-center kidney ultrasound datasets and simulated adversarial/anomalous operating conditions shows that the framework achieves 96.8% diagnostic accuracy, 94.0% robustness under attack, and 94.2% anomaly detection rate, with inference latency of 412.3 ms on edge-class hardware (Jetson Xavier), meeting real-time clinical screening requirements. These results indicate that KArAt-KidneyNet can support secure and interpretable kidney disease classification in distributed consumer healthcare environments.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7105-7120"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837045","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}