Chinese Journal of Electronics最新文献

HTLIN-Stega: Hierarchical Text-Label Integration Network for Text Steganalysis 用于文本隐写分析的分层文本-标签集成网络

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.245

Juan Wen;Jianghao Jia;Jing Wang;Ziwei Zhang;Yiming Xue

{"title":"HTLIN-Stega: Hierarchical Text-Label Integration Network for Text Steganalysis","authors":"Juan Wen;Jianghao Jia;Jing Wang;Ziwei Zhang;Yiming Xue","doi":"10.23919/cje.2024.00.245","DOIUrl":"https://doi.org/10.23919/cje.2024.00.245","url":null,"abstract":"Neural text steganalysis has achieved impressive success. However, existing algorithms struggle to detect mixed texts generated by multiple steganography algorithms. To improve the detection capability for mixed texts, this paper proposes a novel hierarchical text-label integration network (HTLIN-Stega), introducing the steganography-related hierarchical structure into the training process. Specifically, we assign different granularities of hierarchical labels to text samples, ranging from coarsegrained to finegrained labels. Then a word-label fusion unit (WLFU) is proposed to map the text and multi-layer label features into a joint space. A loss function is designed to align labels and text features within the joint space and to learn the distance relationships between text representations and labels from different granularities, including coarse-grained labels, fine-grained labels, sibling labels, and inter-class labels. Experimental results on various hierarchical datasets demonstrate that the HTLIN-Stega can effectively learn multi-layer steganographic features and significantly improve the detection accuracy of mixed steganographic text.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"257-269"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480062","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665472","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

Fast Nonparallel Support Vector Machine with the Margin Hyper-planes and Its Iterative Solver 边缘超平面快速非并行支持向量机及其迭代求解

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2025.00.007

Liming Liu;Yonghui Yang;Ping Li;Maoxiang Chu

{"title":"Fast Nonparallel Support Vector Machine with the Margin Hyper-planes and Its Iterative Solver","authors":"Liming Liu;Yonghui Yang;Ping Li;Maoxiang Chu","doi":"10.23919/cje.2025.00.007","DOIUrl":"https://doi.org/10.23919/cje.2025.00.007","url":null,"abstract":"Nonparallel support vector machine (NPSVM) combines the advantages of support vector machine (SVM) and twin SVM, excelling in small-scale data classification. However, its inability to leverage the structural distribution of samples limits its generalization capability. NPSVM requires solving a pair of quadratic programming problems with inequality constraints, thereby reducing learning efficiency. To handle these draw-backs, we propose a fast NPSVM model with the margin hyper-planes (MH-fNPSVM), which introduces several key innovations. Firstly, by replacing inequality constraints with equality constraints, MH-fNPSVM transforms the optimization problem into solving a pair of linear equations, significantly improving computational efficiency. Secondly, MH-fNPSVM also incorporates margin distribution by optimizing the first and second-order statistics of the training samples, improving the generalization performance. Furthermore, MH-fNPSVM transforms the slack variables from 1-norm to 2-norm by employing a quadratic loss function, which overcomes the non-smoothness of the original loss function in NPSVM and enables the model to effectively fit the trends in data distribution, enhancing the robustness and generalization ability. Lastly, an iterative conjugate gradient method is designed for MH-fNPSVM to avoid kernel matrix inversion, thereby ensuring both accuracy and scalability. The model was validated on different datasets and demonstrated excellent performance in generalization and runtime compared to the baseline model.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"336-350"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480064","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665492","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

CycleGAN-TMDE: An Image Dehazing Model Using Cycle Generative Adversarial Network with Transmission Map and Depth Estimation 基于传输映射和深度估计的循环生成对抗网络的图像去雾模型CycleGAN-TMDE

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.141

Xinlai Guo;Yanyun Tao;Yuzhen Zhang;Xu Biao;Jianying Zheng;Guang Ji

{"title":"CycleGAN-TMDE: An Image Dehazing Model Using Cycle Generative Adversarial Network with Transmission Map and Depth Estimation","authors":"Xinlai Guo;Yanyun Tao;Yuzhen Zhang;Xu Biao;Jianying Zheng;Guang Ji","doi":"10.23919/cje.2024.00.141","DOIUrl":"https://doi.org/10.23919/cje.2024.00.141","url":null,"abstract":"Hazy conditions significantly reduce image contrast and obscure object boundaries, impairing the performance of vision-based tasks such as object detection, tracking, and scene understanding. Learning-based de-hazing methods have attained numerous achievements in dehazing images. For real-world haze images, the current methods result in the poor quality of haze-free images. In this study, we propose an image dehazing method based on cycle generative adversarial network (CycleGAN), which integrates the transmission map and depth estimation (CycleGAN-TMDE). In CycleGAN-TMDE, we designed a dehaze generator that includes a transmission map estimator and an atmospheric scattering model to produce haze-free images with real-world physical characteristics. To further improve the dehaze generator's dehazing capability, we adopt a depth estimator to generate haze images while simultaneously using the dehaze generator to remove haze from these generated images. The cycle loss function compensates for the absence of matched hazy sample pairs in unsupervised learning. The adaptive loss function enhances the model's robustness, ensuring that when a haze-free image is used as input, Cycle-GAN-TMDE can produce similarly clear outputs. On the real-world hazy images of the realistic single image de-hazing (RESIDE) dataset, CycleGAN-TMDE achieves clearer and more natural haze-free images, particularly producing better visual effects for distant scenery while also yielding favorable no-reference image quality assessment metrics. On the synthetic hazy datasets RESIDE and Haze4k, CycleGAN-TMDE can restore high-quality haze-free images while achieving comparable peak signal-to-noise ratio and structural similarity index values to supervised learning methods and outperforms other unsupervised learning methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"377-391"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665483","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

When RIS and Digital Twin Meet UAV-Assisted Mobile Edge Computing: A Survey 当RIS和数字孪生遇上无人机辅助移动边缘计算：一项调查

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.229

Shancheng Zhao;Wantong Zhao;Xin Fan;Yongyi Jinma;Yi Hong;Chuanwen Luo;Yi Li

{"title":"When RIS and Digital Twin Meet UAV-Assisted Mobile Edge Computing: A Survey","authors":"Shancheng Zhao;Wantong Zhao;Xin Fan;Yongyi Jinma;Yi Hong;Chuanwen Luo;Yi Li","doi":"10.23919/cje.2024.00.229","DOIUrl":"https://doi.org/10.23919/cje.2024.00.229","url":null,"abstract":"In the ultra 5th generation mobile communication technology/6th generation mobile communication technology era, unmanned aerial vehicle (UAV)-assisted mobile edge computing (AEC) emerges as a vital component in the Internet of things. By leveraging the flexible deployment capabilities of UAVs, AEC offers users lowlatency and high-bandwidth edge computing services. However, the progression of AEC networks still confronts serious challenges, including channel blockages, complex channel fading, and real-time decision requirements. To effectively address these challenges, the emerging reconfigurable intelligence surface (RIS) and digital twin (DT) technologies demonstrate immense optimization potential. Specifically, RIS enhances the efficiency and reliability of computational offloading by optimizing the intricate UAV communication environment. Simultaneously, DT technology digitizes wireless networks, facilitating low-cost, highly adaptive, and rapid optimization and design of AEC networks. These two technologies open up a new path for the advancement of AEC networks. To our knowledge, there is a lack of comprehensive reviews addressing this emerging cross-cutting area. Therefore, this paper aims to fill this gap by providing an in-depth analysis of the latest research progress of RIS and DT technologies-assisted AEC networks. Ultimately, this paper furnishes a clear and comprehensive perspective, exploring the immense potential of RIS and DT technologies in driving the development of AEC networks.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"400-414"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480058","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665451","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

Graph Regularized Sparse Nonnegative Tucker Decomposition with $l_{0}$ -Constraints for Unsupervised Learning 无监督学习约束下的图正则化稀疏非负Tucker分解

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.290

Weifeng Yang;Wenwen Min

{"title":"Graph Regularized Sparse Nonnegative Tucker Decomposition with $l_{0}$ -Constraints for Unsupervised Learning","authors":"Weifeng Yang;Wenwen Min","doi":"10.23919/cje.2024.00.290","DOIUrl":"https://doi.org/10.23919/cje.2024.00.290","url":null,"abstract":"Nonnegative Tucker decomposition (NTD) is a powerful feature extraction tool widely utilized in dimensionality reduction and clustering of multi-dimensional data. In this paper, we propose a novel graph regularized sparse nonnegative Tucker decomposition method with <tex>$ell_{0}$</tex>-norm constraints (<tex>$ell_{0}$</tex>-GSNTD). Unlike most existing sparse NTD methods, which overlook the manifold structure of data and uncontrollably promote the sparsity of the core tensor and factor matrices by using a relaxation scheme of <tex>$p_{0}$</tex>-norm regularization, our method incorporates the graph regularization into NTD to encode the manifold structure information of data and directly employs the <tex>$ell_{0}$</tex>-norm constraints to explicitly control the sparsity of the core tensor and factor matrices in NTD, thereby enhancing the feature extraction capability. However, due to the nonconvex nature of NTD and the non-convex and nonsmooth nature of the <tex>$ell_{0}$</tex>-norm constraints, optimizing <tex>$ell_{0}$</tex>-GSNTD is NP-hard. To tackle these challenges, we propose a proximal alternating linearized (PAL) algorithm to solve the original <tex>$ell_{0}$</tex>-GSNTD, and introduce the inertial version of PAL algorithm named inertial PAL algorithm to accelerate convergence. Our algorithms provide a practical convergent scheme to directly solve <tex>$ell_{0}$</tex>-GSNTD without relaxing its constraints. Furthermore, we prove that the sequence generated by our algorithms is globally convergent to a critical point and analyze the per-iteration complexity of our algorithms. The experimental results on the unsupervised clustering tasks, which are conducted using twelve real-world benchmark datasets, demonstrate that our method outperforms some state-of-the-art methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"362-376"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480440","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665482","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 Efficient Online/Offline Heterogeneous Signcryption Scheme with Keyword Search for IoVs 基于关键字搜索的iov在线/离线异构签名加密方案

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.345

Yingzhe Hou;Yue Cao;Hu Xiong;Chi-Hung Chi;Kwok-Yan Lam;Chakkaphong Suthaputchakun

{"title":"An Efficient Online/Offline Heterogeneous Signcryption Scheme with Keyword Search for IoVs","authors":"Yingzhe Hou;Yue Cao;Hu Xiong;Chi-Hung Chi;Kwok-Yan Lam;Chakkaphong Suthaputchakun","doi":"10.23919/cje.2024.00.345","DOIUrl":"https://doi.org/10.23919/cje.2024.00.345","url":null,"abstract":"The rapid development of Internet of vehicle (IoV) technologies has led to the current trend that vehicles on the road are increasingly Internet-connected, be they for assisting navigation, safety monitoring, traffic management or infotainment. With the explosive growth in the number of connected vehicles, massive amount of data is collected from vehicles, transmitted, stored and processed in the cloud to provide artificial intelligence-assisted/ autonomous functions. From the perspective of safety and security, the timely transmission and processing of data are critical problems that need to be addressed rigorously. Typically, advanced data management services via the cloud server are developed for supporting IoV. However, the potential risk of data leakage in the cloud has caused serious privacy concerns which could even result in breaches in privacy regulations. To address these issues, we propose an online/offline heterogeneous signcryption with keyword search scheme (OOHSC-KW). Firstly, the incorporation of heterogeneous signcryption keyword search guarantees the security of data. The presented protocol executes the keyword retrieval from heterogeneous devices, which increases the availability of ci-phertext and reduces the search overhead. Secondly, the proposed scheme divides signcryption phase into two stages, and the overall signcryption overhead is reduced. Finally, our scheme has the smallest computational over-head during the key generation step, when the number of messages is greater than 25, our construction also has a lower signcryption overhead compared to the listed works.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"322-335"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665503","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

Exploring Neural Radiance Fields for Thermal View Synthesis Solely with Thermal Inputs 仅用热输入探索热视图合成的神经辐射场

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.335

Haixuan Ding;Jialiang Tang;Sheng Wan;Chen Gong

{"title":"Exploring Neural Radiance Fields for Thermal View Synthesis Solely with Thermal Inputs","authors":"Haixuan Ding;Jialiang Tang;Sheng Wan;Chen Gong","doi":"10.23919/cje.2024.00.335","DOIUrl":"https://doi.org/10.23919/cje.2024.00.335","url":null,"abstract":"Novel view synthesis (NVS) for thermal scenes aims to generate thermal images from unseen view-points. It shows great potential in various applications, such as nighttime autonomous driving, industrial inspection, and agricultural monitoring. Recently, neural radiance fields (NeRF) has emerged as a powerful approach for NVS in thermal scenes. This approach typically necessitates paired RGB and thermal images to produce realistic thermal images from new views. However, practical limitations, such as insufficient lighting, the prohibitive cost of RGB image acquisition, or the lack of RGB cameras, make it challenging or even impossible to obtain high-quality RGB images, which prevents the existing NeRF methods from generating realistic thermal images. To address this problem, we devise a simple yet effective NeRF framework based on thermal radiation prediction (TRP), which is termed “NeRF-TRP”, for NVS in thermal scenes. Unlike the existing NeRF techniques that rely on paired RGB and thermal images, NeRF-TRP exclusively utilizes thermal images as input. By leveraging the principle of thermal imaging, NeRF-TRP predicts the thermal radiation emitted by objects to generate thermal images from novel perspectives. Meanwhile, motivated by the thermal equilibrium observed in thermal scenes, we design a patch-based regularization method to enhance the realism of the generated thermal images. Extensive experiments on thermal images demonstrate that NeRF-TRP not only produces more accurate thermal image synthesis, but also reveals superior efficiency in both training and rendering when compared with various representative baseline approaches.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"351-361"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11479946","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665493","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

Enhanced Shuffle Models for Optimized Differential Privacy in Federated Learning 联邦学习中优化差分隐私的增强Shuffle模型

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2025.00.120

Hongbin Zhu

引用次数: 0

MOEA-SISA: Multiobjective Optimization to Improve Model Performance During Forgetting Data MOEA-SISA：遗忘数据时提高模型性能的多目标优化

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2024.00.052

Bin Cao;Zhaokun Wang;Dingjun Chang;Xin Liu;Yun Li

{"title":"MOEA-SISA: Multiobjective Optimization to Improve Model Performance During Forgetting Data","authors":"Bin Cao;Zhaokun Wang;Dingjun Chang;Xin Liu;Yun Li","doi":"10.23919/cje.2024.00.052","DOIUrl":"https://doi.org/10.23919/cje.2024.00.052","url":null,"abstract":"With the proliferation of shared personal data online, users encounter difficulties in revoking data access permissions and requesting data deletions, thus increasing the risk of privacy breaches. Machine unlearning offers a solution and is useful for sensing-computing integrated chips and systems, but the state-of-the-art shard-ed, isolated, sliced, and aggregated (SISA) method produces models with high complexity and limited generalization ability. This study proposes a novel framework, named multiobjective evolutionary algorithm-SISA (MOEA-SISA), which integrates feature decomposition-based differential grouping (FDbDG) to improve optimization efficiency through dynamic grouping of decision variables. Three optimization objectives can hence be proposed: model accuracy, model complexity, and generalization ability. By optimizing these three objectives, the trained model becomes closer to the retrained results while preventing excessive forgetting. Experimental models including ViT, VGG-16, and ResNet-50 are used for sub-class forgetting tasks. Compared with various state-of-the-art methods, MOEA-SISA offers advantages across these models, especially in terms of model complexity and generalization ability. Tests against membership inference attacks demonstrate that MOEA-SISA effectively retains accuracy and enhances the generalization ability in sub-class forgetting scenarios. Additionally, the proposed approach offers significant advantages for improving the efficiency and performance of sensing-computing integrated chips and systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"35 1","pages":"392-399"},"PeriodicalIF":3.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11480068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665543","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

DyCAPS: Asynchronous Dynamic-Committee Proactive Secret Sharing DyCAPS：异步动态委员会主动秘密共享

IF 3 4区计算机科学

Chinese Journal of Electronics Pub Date : 2026-01-01 Epub Date: 2026-04-13 DOI: 10.23919/cje.2025.00.072

Zongyang Zhang;Bin Hu;Han Chen;You Zhou;Huazu Jiang;Jianwei Liu

引用次数: 0