Chinese Journal of Electronics最新文献_第8页

Adaptive Decision Boundary Learning with Class-Balanced Pseudo-Labelling for Open-Set Semi-Supervised Hyperspectral Image Classification 类平衡伪标记自适应决策边界学习在开集半监督高光谱图像分类中的应用

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-07-01 Epub Date: 2026-09-09 DOI: 10.23919/cje.2025.00.316

Wuli Wang;Yun Liu;Qi Sun;Sichao Fu;Jianbu Wang;Baodi Liu;Peng Ren

{"title":"Adaptive Decision Boundary Learning with Class-Balanced Pseudo-Labelling for Open-Set Semi-Supervised Hyperspectral Image Classification","authors":"Wuli Wang;Yun Liu;Qi Sun;Sichao Fu;Jianbu Wang;Baodi Liu;Peng Ren","doi":"10.23919/cje.2025.00.316","DOIUrl":"https://doi.org/10.23919/cje.2025.00.316","url":null,"abstract":"In the past few years, semi-supervised hyperspectral image (HSI) classification has garnered significant attention, which aims to achieve high-precision land cover classification under the guidance of limited labeled samples. Nevertheless, existing methods follow the standard closed-set setting and often overlook the presence of unknown classes in real-world scenarios, which severely hurts model effectiveness. When directly applying existing methods to the above open-set semi-supervised HSI classification, they often suffer from biased decision boundaries, imbalance and inaccuracy of the pseudo-label generated from unlabeled HSI. Such boundary bias leads to misclassification not only among known classes but also between known and unknown classes. To address the above-mentioned issues, we propose a class-balanced pseudo-labelling enhanced adaptive decision boundary learning framework for open-set semi-supervised HSI classification. Specifically, a spatial-contextual superpixel module is first introduced to resolve class imbalance and inaccuracy of generated pseudo-labels via the construction of balanced unlabeled sample sets. Then, a distribution-regularized attention module is proposed to address class misclassification by adaptively fusing spectral-spatial features and sharpening inter-class decision boundaries. Finally, a class-center constrained dynamic thresholding strategy is designed to enhance the separation between known and unknown classes through compact known-class feature distributions. Extensive experiments on three HSI benchmark datasets demonstrate the effectiveness of the proposed method in comparison to the existing methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 4","pages":"1351-1363"},"PeriodicalIF":4.5,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11685234","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148909473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Detection and Defense Against Backdoor Attacks in Large Language Models Based on Repeated Words Analysis 基于重复词分析的大型语言模型后门攻击检测与防御

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2025.00.003

Chuan Zhang;Xiaolong Tao;Baokun Zheng;Zheng Gao;Liehuang Zhu

引用次数: 0

PoseTrack: Enhancing Multi-Object Tracking with 3D Pose-Visual Fusion and Adaptive Trajectory Management PoseTrack：利用三维姿态视觉融合和自适应轨迹管理增强多目标跟踪

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2025.00.250

Jinglin Xu;Xudong Zhang;Ziyi Liu;Hongmin Liu

{"title":"PoseTrack: Enhancing Multi-Object Tracking with 3D Pose-Visual Fusion and Adaptive Trajectory Management","authors":"Jinglin Xu;Xudong Zhang;Ziyi Liu;Hongmin Liu","doi":"10.23919/cje.2025.00.250","DOIUrl":"https://doi.org/10.23919/cje.2025.00.250","url":null,"abstract":"In this paper, we introduce PoseTrack, a new multi-object tracking (MOT) framework specifically designed for multi-person sports scenes. Existing methods often struggle due to challenges such as similar player appearances, frequent occlusions, and unpredictable entrances and exits. PoseTrack proposes a new MOT approach by introducing human pose estimation into the tracking algorithm and temporally fusing it with two-dimensional visual cues to address these challenges. Specifically, by leveraging the unique three-dimensional poses of individuals, PoseTrack enhances the association between trajectories and detections across consecutive frames, thereby improving the accuracy of tracking. In addition, our PoseTrack ensures robust tracking performance even when athletes enter or exit the frame by imposing constraints on disappeared trajectories and adaptively adjusting their disappearance time based on the trajectory's survival duration. Extensive evaluations on two large-scale sports benchmarks—SportsMOT and Soccer Net-Tracking—demonstrate that PoseTrack outperforms previous methods across key metrics (higher order tracking accuracy, identification F1 score, association accuracy, and detection accuracy). PoseTrack can support applications such as sports tactical analysis and athlete performance evaluation by enabling highly accurate and reliable motion analysis.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 2","pages":"804-816"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11554541","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148196135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Offloading Budget-Constrained Tasks to Edge via Reinforced Embedding 通过增强嵌入将预算受限的任务卸载到边缘

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2024.00.346

Jizhe Dou;Dantong Li;Lina Li;Chuanwen Luo;Guodong Sun

{"title":"Offloading Budget-Constrained Tasks to Edge via Reinforced Embedding","authors":"Jizhe Dou;Dantong Li;Lina Li;Chuanwen Luo;Guodong Sun","doi":"10.23919/cje.2024.00.346","DOIUrl":"https://doi.org/10.23919/cje.2024.00.346","url":null,"abstract":"In edge computing applications, partitioning user tasks into subtasks and offloading them to multiple edge servers for parallel execution is a promising strategy to reduce latency. Despite its potential, existing research often overlooks the challenges introduced by budget constraints and heterogeneous processing capabilities of edge servers. This paper proposes the partition-allocation-selection (PAS) problem, which makes decisions on task partition, subtask allocation, and selection of executors under budget constraints to minimize task makespan. This problem is not only NP-hard but also characterized by intricate interdependencies among these decisions. To address computational challenges, we propose ReEmNet, a novel framework based on reinforcement learning and representation learning, which reformulates PAS as a learning problem within an embedding space. ReEmNet introduces two innovations: 1) it unifies three key problems: task partitioning, subtask allocation, and executor selection into a single-step decision-making process using continuous-action reinforcement learning. This integration efficiently encodes interdependencies of those problems, ensures disjoint task partitions, and manages the high dimensionality of the decision space, and 2) it adopts a representation learning strategy to produce supervision-free, refined and interpretable action representations compared to traditional discrete-action methods. Extensive numerical experiments demonstrate that ReEmNet significantly outperforms state-of-the-art approaches, underscoring its potential to advance intelligent task offloading in edge computing.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 2","pages":"852-865"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11554566","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148196089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

A Physics-Based Compact Model for Kink Effects in GaN HEMTs GaN hemt中扭结效应的物理紧凑模型

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2025.00.229

Lei Huang;Shuman Mao;Qingzhi Wu;Min Tang;Yuehang Xu;Yan Wang

{"title":"A Physics-Based Compact Model for Kink Effects in GaN HEMTs","authors":"Lei Huang;Shuman Mao;Qingzhi Wu;Min Tang;Yuehang Xu;Yan Wang","doi":"10.23919/cje.2025.00.229","DOIUrl":"https://doi.org/10.23919/cje.2025.00.229","url":null,"abstract":"An accurate model of the kink effect is critical for understanding device operation mechanisms, ensuring reliability, and enabling robust circuit design. However, accurate modeling of the kink effect-arising from both trapping effects and impact ionization-remains a significant challenge. Conventional empirical models often lack physical insight, particularly regarding the interplay between impact ionization and the electric field. In this work, a physics-based compact model that incorporates both impact ionization and trapping effects is proposed. First, a well-calibrated technology computer-aided design model is developed to investigate the physical origins of the kink effect. By analyzing the variations in physical parameters-such as the electric field and trap ionization density-before and after the onset of the kink, it is shown that both impact ionization and buffer/substrate-related trapping effects jointly contribute to its occurrence. Subsequently, a compact model is derived based on a zone-division approach, capturing the underlying physical mechanisms. This model is then integrated into the drain-source current formulation for validation. Simulation results confirm that the proposed model accurately reproduces the electric field distribution and I-V characteristics. Thus, the model is well-suited for circuits simulations and device performance optimization.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 2","pages":"415-422"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11554567","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

The Impact Analysis of Device Variations, Data Quality and Collection Intervals on the Performance of Blood Pressure Prediction Model 器械变化、数据质量和采集间隔对血压预测模型性能的影响分析

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2025.00.426

Mei Zou;Xun Li;Shu Cong;Jinhong Li;Yunfen Wei;Long Pi

{"title":"The Impact Analysis of Device Variations, Data Quality and Collection Intervals on the Performance of Blood Pressure Prediction Model","authors":"Mei Zou;Xun Li;Shu Cong;Jinhong Li;Yunfen Wei;Long Pi","doi":"10.23919/cje.2025.00.426","DOIUrl":"https://doi.org/10.23919/cje.2025.00.426","url":null,"abstract":"This study investigates the impacts of device variability, data quality, and collection intervals on the performance of blood pressure (BP) prediction models. Four datasets were utilized: Guilin Hospital, MIMIC-II, a self-collected dataset, and a mixed dataset. Multiple feature engineering methods-including principal component analysis (PCA), Pearson correlation, maximal information coefficient (MIC), and Relief-were combined with modeling approaches such as multiple linear regression (MLR), decision trees (DT), long short-term memory (LSTM), and convolutional neural network (CNN) for BP estimation. Results showed that models trained on the MIMIC-II dataset, which employs invasive arterial BP as reference, achieved the best performance, with systolic BP (SBP) and diastolic BP (DBP) prediction errors as low as 2.09 ± 2.55 mmHg and 1.08 ± 1.25 mmHg, respectively, satisfying Association for the Advancement of Medical Instrumentation (AAMI) standards. In contrast, the hybrid dataset led to significantly increased errors (e.g., mean absolute error rise over 300% in some cases) and correlation degradation (r dropping to negative values). Temporal data drift also markedly reduced model accuracy-after 98 days, SBP mean absolute error (MAE) increased from 2.09 mmHg to 9.86 mmHg. However, recalibration effectively restored model performance, reducing MAE to 3.92 ± 4.92 mmHg for SBP and 2.54 ± 2.72 mmHg for DBP in later measurements. This study underscores the critical importance of high-quality, device-consistent data and periodic recalibration in maintaining reliable cuffless BP estimation. These findings offer practical insights for enhancing the robustness and real-world applicability of continuous BP monitoring systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 2","pages":"602-613"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11554550","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Investigation on the Interplay Between S Parameters and Near-Field Radiation Characteristics of Defected Ground Structures 缺陷地面结构S参数与近场辐射特性的相互作用研究

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-06-08 DOI: 10.23919/cje.2025.00.292

Tianmeng Zhang;Jinchun Gao;Ziren Wang;Yiming Chen;Rui Ji

{"title":"Investigation on the Interplay Between S Parameters and Near-Field Radiation Characteristics of Defected Ground Structures","authors":"Tianmeng Zhang;Jinchun Gao;Ziren Wang;Yiming Chen;Rui Ji","doi":"10.23919/cje.2025.00.292","DOIUrl":"https://doi.org/10.23919/cje.2025.00.292","url":null,"abstract":"Defected ground structures (DGSs) are widely used to improve the electric and electromagnetic characteristics of devices and components, which may affect the signal transmission performance and lead to radiation emissions at specific frequencies. In this work, the relationship between near-field radiation intensities and <tex>$S$</tex> parameters of the signal transmission channels with DGSs was revealed using theoretical modeling and experimental tests. Based on the <tex>$S$</tex> parameters results, the <tex>$S_{text{eq}}$</tex> parameter was derived and calculated. The results indicate that the peak near-field electric radiation intensities occur at frequencies of peak <tex>$S_{text{eq}}$</tex> values. A three-dimensional (3-D) electromagnetic field model and an equivalent circuit model were developed to analyze the <tex>$S$</tex> parameters and near-field electric radiation intensities. High-frequency and near-field measurements were conducted to verify the simulation. This study provides a theoretical support for predicting frequencies corresponding to peak radiation intensities of DGSs via <tex>$S$</tex> parameters, which are essential for mitigating electromagnetic compatibility (EMC) issues in electronic systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 2","pages":"444-452"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11554552","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Fundamental Limits of Bistatic Integrated Sensing and Communication Under Sensing Information Leakage Constraint 传感信息泄漏约束下双基地集成传感与通信的基本限制

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-07-03 DOI: 10.23919/cje.2025.00.285

Qi Gong;Yao Liu;Min Li

{"title":"Fundamental Limits of Bistatic Integrated Sensing and Communication Under Sensing Information Leakage Constraint","authors":"Qi Gong;Yao Liu;Min Li","doi":"10.23919/cje.2025.00.285","DOIUrl":"https://doi.org/10.23919/cje.2025.00.285","url":null,"abstract":"Integrated sensing and communication (ISAC) systems aim to unify sensing and communication within a shared waveform, offering benefits in spectrum and hardware efficiency. However, this integration raises critical security concerns, particularly regarding the leakage of sensing-related information due to the broadcast nature of wireless transmissions. While prior work has explored ISAC under data security constraints, securing sensing information remains a key open challenge. In this work, we address this gap by studying a two-receiver state-dependent bistatic ISAC model with a sensing eavesdropper. We characterize the fundamental trade-off among communication capacity, sensing distortion, and sensing information leakage. Specifically, we derive an inner bound using an input-constrained randomized encoding scheme and propose a new outer bound that incorporates leakage constraints. Under a reversely-degraded channel condition, we further establish the exact optimal trade-off. Numerical results validate our scheme and illustrate the complex interactions among capacity, distortion, and leakage in secure ISAC systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 3","pages":"1007-1016"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11595425","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

An Asset-Oriented Method for Evaluating the Security of Software Architecture Quantitatively 面向资产的软件体系结构安全性定量评估方法

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-07-03 DOI: 10.23919/cje.2024.00.274

Hao Chen;Bixin Li;Shengyang Zhou;Chen Chen;Zheng Dai;Bohui Wang

{"title":"An Asset-Oriented Method for Evaluating the Security of Software Architecture Quantitatively","authors":"Hao Chen;Bixin Li;Shengyang Zhou;Chen Chen;Zheng Dai;Bohui Wang","doi":"10.23919/cje.2024.00.274","DOIUrl":"https://doi.org/10.23919/cje.2024.00.274","url":null,"abstract":"Even though the security of software architecture plays an important role in the security of complex and large-size software systems, there are still very few feasible methods to evaluate the security of software architecture quantitatively. To fill this gap, we propose an asset-oriented method to quantitatively evaluate the security of software architecture in this paper. The core idea is that we first use a multi-hierarchy dependence graph (MHDG) to describe the system and capture the dependence information between hierarchies, then we mark the positions of assets and attack points on MHDG, afterwards we identify potential attack paths and feasible attack paths from attack points to assets, and finally we evaluate the security of software architecture using some indicators from the perspective of software developers and defenders. We validated the method on four architectural styles and five evolutionary versions. Results show that it accurately captures the security differences among four representative architectural styles, effectively reflects security variations across five evolutionary versions of the same system, and facilitates security-oriented architectural optimization. Moreover, compared with random reinforcement strategies, our method achieves greater improvement in system security under the same protection cost, demonstrating practical value for security-aware architectural design.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 3","pages":"1285-1300"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11595458","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148443333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Towards Secure and Robust Vision-Language Models in Autonomous Driving: A Survey for Perception-Oriented and Decision-Oriented Attacks 面向安全鲁棒的自动驾驶视觉语言模型：面向感知和面向决策的攻击研究综述

IF 4.5 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-03-01 Epub Date: 2026-07-03 DOI: 10.23919/cje.2025.00.095

Tianyuan Zhang;Jiangfan Liu;Yongkang Guo;Fangzhi Zhong;Wei Bao;Jian Dong;Aishan Liu;Xianglong Liu;Yue Cao

{"title":"Towards Secure and Robust Vision-Language Models in Autonomous Driving: A Survey for Perception-Oriented and Decision-Oriented Attacks","authors":"Tianyuan Zhang;Jiangfan Liu;Yongkang Guo;Fangzhi Zhong;Wei Bao;Jian Dong;Aishan Liu;Xianglong Liu;Yue Cao","doi":"10.23919/cje.2025.00.095","DOIUrl":"https://doi.org/10.23919/cje.2025.00.095","url":null,"abstract":"Vision-language models (VLMs) have been widely adopted in autonomous driving (AD) for their strong generalization capabilities and interpretability. However, they remain inherently vulnerable to robustness challenges, particularly adversarial examples, which pose significant safety risks. This paper presents a comprehensive survey of attacks on VLMs in AD, introducing a novel taxonomy that categorizes attacks into two types: perception-oriented attacks, which manipulate input data to mislead the perception process, and decision-oriented attacks, which exploit vulnerabilities in decision-making and interaction processes. Following this classification, the paper conducts a systematic review of existing attack methods, their limitations, and the key challenges they present. It also explores future directions and potential applications to enhance the robustness and performance of VLMs in AD. This work aims to lay a foundation for developing more secure and reliable VLMs for AD systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 3","pages":"1195-1210"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11595460","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148443338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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