Pub Date : 2025-01-01DOI: 10.23919/cje.2023.00.315
Shunmiao Zhang;Siyuan Zheng;Degen Huang;Dan Li
Dialogue-based relation extraction (DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model (HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.
{"title":"Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph","authors":"Shunmiao Zhang;Siyuan Zheng;Degen Huang;Dan Li","doi":"10.23919/cje.2023.00.315","DOIUrl":"https://doi.org/10.23919/cje.2023.00.315","url":null,"abstract":"Dialogue-based relation extraction (DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model (HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"295-308"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891971","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446191","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}
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the $ell_{0}$-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and convergence. This algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.
{"title":"Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning","authors":"Hengmin Zhang;Jian Yang;Wenli Du;Bob Zhang;Zhiyuan Zha;Bihan Wen","doi":"10.23919/cje.2023.00.340","DOIUrl":"https://doi.org/10.23919/cje.2023.00.340","url":null,"abstract":"Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the <tex>$ell_{0}$</tex>-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and convergence. This algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"98-113"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891967","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438329","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}
Perfect vortex (PV) beam, as a novel paradigm to carry orbital angular momentum (OAM), owns constant radius of energy intensity and infinite mode of helical patterns, which overcomes the divergence performances of conventional vortex beam. However, common approaches for PV beam generation require optical cascading systems that should constitute of various lenses and components with bulk volume and high alignment standards, also cannot realize PV customization. Thus, in this paper, we propose a general scheme based on compact platform of geometric metasurface to achieve PV beams generations and deformable wave-front modulations. The adopted unit cell is designed with “ABA”-shaped configuration, which can high-efficiently transform circular polarization incident wave into its cross-polarized state and impose required PV phase patterns. Here, we construct series of metasurface lenses to achieve PVs with eight different OAM modes at operating frequency 10 GHz, and additionally conduct quasi-elliptical energy-ring intensities and fractional modals of PVs by introducing asymmetric periodicity and extra singularities. By exploiting compact metasurface platform, this general scheme for PV beam generation and modulation would provide a theoretical foundation for the electromagnetic waves controlling in modern wireless communication systems.
{"title":"Deformable Perfect Vortex Wave-Front Modulation Based on Geometric Metasurface in Microwave Regime","authors":"Yueyi Yuan;Wenjie Zhou;Mengnuo Fan;Qun Wu;Kuang Zhang","doi":"10.23919/cje.2023.00.416","DOIUrl":"https://doi.org/10.23919/cje.2023.00.416","url":null,"abstract":"Perfect vortex (PV) beam, as a novel paradigm to carry orbital angular momentum (OAM), owns constant radius of energy intensity and infinite mode of helical patterns, which overcomes the divergence performances of conventional vortex beam. However, common approaches for PV beam generation require optical cascading systems that should constitute of various lenses and components with bulk volume and high alignment standards, also cannot realize PV customization. Thus, in this paper, we propose a general scheme based on compact platform of geometric metasurface to achieve PV beams generations and deformable wave-front modulations. The adopted unit cell is designed with “ABA”-shaped configuration, which can high-efficiently transform circular polarization incident wave into its cross-polarized state and impose required PV phase patterns. Here, we construct series of metasurface lenses to achieve PVs with eight different OAM modes at operating frequency 10 GHz, and additionally conduct quasi-elliptical energy-ring intensities and fractional modals of PVs by introducing asymmetric periodicity and extra singularities. By exploiting compact metasurface platform, this general scheme for PV beam generation and modulation would provide a theoretical foundation for the electromagnetic waves controlling in modern wireless communication systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"64-72"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891987","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438401","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}
Pub Date : 2025-01-01DOI: 10.23919/cje.2023.00.418
Jiachen Tian;Yu Han;Shi Jin;Jun Zhang;Jue Wang
Multiple antenna technologies, from traditional multiple-input multiple-output (MIMO) to massive MIMO and the emerging extra large-scale MIMO, have consistently played a pivotal role in enhancing transmission rates by increasing the number of antennas. To guide the design of transmission strategies, channel models, especially analytical ones, are always significant tools, which can also reveal the performance improvements brought about by multiple antenna technologies. Analytical channel models have enjoyed significant success in traditional MIMO and massive MIMO systems. Nevertheless, due to the extended size of the array in an extra large-scale MIMO system, the distance between the receiver and the transmitter decreases and new channel properties, which did not manifest in massive MIMO systems, begin to kick in. To model the channel tailored for extra large-scale MIMO systems analytically, it is crucial to conduct a comprehensive review of traditional analytical MIMO channel models, which serves as a foundational step in understanding the fundamental characteristics of multi-antenna channels. In this paper, we first provide a survey on the state-of-the-art analytical MIMO channel models from the perspective of spatial correlation and signal propagation. Subsequently, we summarize the new properties of extra large-scale MIMO systems, i.e., near-field properties and spatial non-stationarities, and their influences on analytical channel modeling. Our objective is to elucidate how these novel properties affect the analytical MIMO channel models, and ultimately facilitate the development of precise analytical channel models well-suited to the extra large-scale MIMO systems.
{"title":"Analytical Channel Modeling: From MIMO to Extra Large-Scale MIMO","authors":"Jiachen Tian;Yu Han;Shi Jin;Jun Zhang;Jue Wang","doi":"10.23919/cje.2023.00.418","DOIUrl":"https://doi.org/10.23919/cje.2023.00.418","url":null,"abstract":"Multiple antenna technologies, from traditional multiple-input multiple-output (MIMO) to massive MIMO and the emerging extra large-scale MIMO, have consistently played a pivotal role in enhancing transmission rates by increasing the number of antennas. To guide the design of transmission strategies, channel models, especially analytical ones, are always significant tools, which can also reveal the performance improvements brought about by multiple antenna technologies. Analytical channel models have enjoyed significant success in traditional MIMO and massive MIMO systems. Nevertheless, due to the extended size of the array in an extra large-scale MIMO system, the distance between the receiver and the transmitter decreases and new channel properties, which did not manifest in massive MIMO systems, begin to kick in. To model the channel tailored for extra large-scale MIMO systems analytically, it is crucial to conduct a comprehensive review of traditional analytical MIMO channel models, which serves as a foundational step in understanding the fundamental characteristics of multi-antenna channels. In this paper, we first provide a survey on the state-of-the-art analytical MIMO channel models from the perspective of spatial correlation and signal propagation. Subsequently, we summarize the new properties of extra large-scale MIMO systems, i.e., near-field properties and spatial non-stationarities, and their influences on analytical channel modeling. Our objective is to elucidate how these novel properties affect the analytical MIMO channel models, and ultimately facilitate the development of precise analytical channel models well-suited to the extra large-scale MIMO systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"1-15"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891999","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438403","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}
Recently, redactable blockchain has been proposed and leveraged in a wide range of real systems for its unique properties of decentralization, traceability, and transparency while ensuring controllable on-chain data redaction. However, the development of redactable blockchain is now obstructed by three limitations, which are data privacy breaches, high communication overhead, and low searching efficiency, respectively. In this paper, we propose PriChain, the first efficient privacy-preserving fine-grained redactable blockchain in decentralized settings. PriChain provides data owners with rights to control who can read and redact on-chain data while maintaining downward compatibility, ensuring the one who can redact will be able to read. Specifically, inspired by the concept of multi-authority attribute-based encryption, we utilize the isomorphism of the access control tree, realizing fine-grained redaction mechanism, downward compatibility, and collusion resistance. With the newly designed structure, PriChain can realize $mathcal{O}(n)$ communication and storage overhead compared to prior $mathcal{O}(n^{2})$ schemes. Furthermore, we integrate multiple access trees into a tree-based dictionary, optimizing searching efficiency. Theoretical analysis proves that PriChain is secure against the chosen-plaintext attack and has competitive complexity. The experimental evaluations show that PriChain realizes $10times$ efficiency improvement of searching and $100times$ lower communication and storage overhead on average compared with existing schemes.
{"title":"PriChain: Efficient Privacy-Preserving Fine-Grained Redactable Blockchains in Decentralized Settings","authors":"Hongchen Guo;Weilin Gan;Mingyang Zhao;Chuan Zhang;Tong Wu;Liehuang Zhu;Jingfeng Xue","doi":"10.23919/cje.2023.00.305","DOIUrl":"https://doi.org/10.23919/cje.2023.00.305","url":null,"abstract":"Recently, redactable blockchain has been proposed and leveraged in a wide range of real systems for its unique properties of decentralization, traceability, and transparency while ensuring controllable on-chain data redaction. However, the development of redactable blockchain is now obstructed by three limitations, which are data privacy breaches, high communication overhead, and low searching efficiency, respectively. In this paper, we propose PriChain, the first efficient privacy-preserving fine-grained redactable blockchain in decentralized settings. PriChain provides data owners with rights to control who can read and redact on-chain data while maintaining downward compatibility, ensuring the one who can redact will be able to read. Specifically, inspired by the concept of multi-authority attribute-based encryption, we utilize the isomorphism of the access control tree, realizing fine-grained redaction mechanism, downward compatibility, and collusion resistance. With the newly designed structure, PriChain can realize <tex>$mathcal{O}(n)$</tex> communication and storage overhead compared to prior <tex>$mathcal{O}(n^{2})$</tex> schemes. Furthermore, we integrate multiple access trees into a tree-based dictionary, optimizing searching efficiency. Theoretical analysis proves that PriChain is secure against the chosen-plaintext attack and has competitive complexity. The experimental evaluations show that PriChain realizes <tex>$10times$</tex> efficiency improvement of searching and <tex>$100times$</tex> lower communication and storage overhead on average compared with existing schemes.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"82-97"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438493","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}
Pub Date : 2025-01-01DOI: 10.23919/cje.2023.00.016
Yunqiang Li;Ting Cui
The authenticated encryption stream cipher ACORN is one of the finalists of the Competition for Authenticated Encryption: Security, Applicability, and Robustness (CAESAR) and is intended for lightweight applications. Because of structural weaknesses in the state update function of ACORN, we can introduce a linear function to analyze conditions and differential trails of the state collision and present a linear method to construct forgery messages under the condition that the key and initialization vector are known or the register state at a certain time is known. The attack method is suitable for three versions of ACORN and may be also extended to any ACORN-like, of which the linear feedback shift register (LFSR) can be replaced by other LFSRs and the feedback function can be replaced by other nonlinear functions. For continuous $l(l > 293)$ bits of new input data, we can construct $2^{l-294}$ forgery messages for any given message of ACORN. Using a standard personal computer, a concrete forgery message can be constructed almost instantly and the required central processing unit time and memory are equivalent to the required resources for solving a system of 293 linear equations over the binary field. These attacks in this paper make that the sender and receiver may easily cheat each other, which is not a desirable property for an ideal cipher and casts some doubt on the necessary authentication security requirements of ACORN.
{"title":"Linear Forgery Attacks on the Authenticated Encryption Cipher ACORN-Like","authors":"Yunqiang Li;Ting Cui","doi":"10.23919/cje.2023.00.016","DOIUrl":"https://doi.org/10.23919/cje.2023.00.016","url":null,"abstract":"The authenticated encryption stream cipher ACORN is one of the finalists of the Competition for Authenticated Encryption: Security, Applicability, and Robustness (CAESAR) and is intended for lightweight applications. Because of structural weaknesses in the state update function of ACORN, we can introduce a linear function to analyze conditions and differential trails of the state collision and present a linear method to construct forgery messages under the condition that the key and initialization vector are known or the register state at a certain time is known. The attack method is suitable for three versions of ACORN and may be also extended to any ACORN-like, of which the linear feedback shift register (LFSR) can be replaced by other LFSRs and the feedback function can be replaced by other nonlinear functions. For continuous <tex>$l(l > 293)$</tex> bits of new input data, we can construct <tex>$2^{l-294}$</tex> forgery messages for any given message of ACORN. Using a standard personal computer, a concrete forgery message can be constructed almost instantly and the required central processing unit time and memory are equivalent to the required resources for solving a system of 293 linear equations over the binary field. These attacks in this paper make that the sender and receiver may easily cheat each other, which is not a desirable property for an ideal cipher and casts some doubt on the necessary authentication security requirements of ACORN.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"257-265"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891972","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438530","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}
Pub Date : 2025-01-01DOI: 10.23919/cje.2024.00.003
Zhengyu Zhang;Ruisi He;Mi Yang;Xuejian Zhang;Ziyi Qi;Hang Mi;Guiqi Sun;Jingya Yang;Bo Ai
Integrated sensing and communications (ISAC) is a potential technology of 6G, aiming to enable end-to-end information processing ability and native perception capability for future communication systems. As an important part of the ISAC application scenarios, ISAC aided vehicle-to-everything (V2X) can improve the traffic efficiency and safety through intercommunication and synchronous perception. It is necessary to carry out measurement, characterization, and modeling for vehicular ISAC channels as the basic theoretical support for system design. In this paper, dynamic vehicular ISAC channel measurements at 28 GHz are carried out and provide data for the characterization of non-stationarity characteristics. Based on the actual measurements, this paper analyzes the time-varying PDPs, RMSDS and non-stationarity characteristics of front, lower front, left and right perception directions in a complicated V2X scenarios. The research in this paper can enrich the investigation of vehicular ISAC channels and enable the analysis and design of vehicular ISAC systems.
{"title":"Non-Stationarity Characteristics in Dynamic Vehicular ISAC Channels at 28 GHz","authors":"Zhengyu Zhang;Ruisi He;Mi Yang;Xuejian Zhang;Ziyi Qi;Hang Mi;Guiqi Sun;Jingya Yang;Bo Ai","doi":"10.23919/cje.2024.00.003","DOIUrl":"https://doi.org/10.23919/cje.2024.00.003","url":null,"abstract":"Integrated sensing and communications (ISAC) is a potential technology of 6G, aiming to enable end-to-end information processing ability and native perception capability for future communication systems. As an important part of the ISAC application scenarios, ISAC aided vehicle-to-everything (V2X) can improve the traffic efficiency and safety through intercommunication and synchronous perception. It is necessary to carry out measurement, characterization, and modeling for vehicular ISAC channels as the basic theoretical support for system design. In this paper, dynamic vehicular ISAC channel measurements at 28 GHz are carried out and provide data for the characterization of non-stationarity characteristics. Based on the actual measurements, this paper analyzes the time-varying PDPs, RMSDS and non-stationarity characteristics of front, lower front, left and right perception directions in a complicated V2X scenarios. The research in this paper can enrich the investigation of vehicular ISAC channels and enable the analysis and design of vehicular ISAC systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"73-81"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891984","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438371","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}
Pub Date : 2025-01-01DOI: 10.23919/cje.2023.00.268
Qingsheng Feng;Shuai Xiao;Wangyang Liu;Hong Li
Turnouts and switch machines play a crucial role in facilitating train line operations and establishing routes, making them vital for ensuring the safety and efficiency of railway transportation. Through the gap detection system of switch machines, the real-time working status of turnouts and switch machines on railway sites can be quickly known. However, due to the challenging working environment and demanding conversion tasks of switch machines, the current gap detection system has often experienced the issues of fault detection. To address this, this study proposes an automatic gap detection method for railway switch machines based on object detection and combination clustering. Firstly, a lightweight object detection network, specifically the MobileNet V3-YOLOv5s model, is used to accurately locate and extract the focal area. Subsequently, the extracted image undergoes preprocessing and is then fed into a combination clustering algorithm to achieve precise segmentation of the gap area and background, the algorithm consists of simple linear iterative clustering, Canopy and kernel fuzzy c-means clustering. Finally, the Fisher optimal segmentation criterion is utilized to divide the data sequence of pixel values, determine the classification nodes and calculate the gap size. The experimental results obtained from switch machine gap images captured in various scenes demonstrate that the proposed method is capable of accurately locating focal areas, efficiently completing gap image segmentation with a segmentation accuracy of 93.55%, and swiftly calculating the gap size with a correct rate of 98.57%. Notably, the method achieves precise detection of gap sizes even after slight deflection of the acquisition camera, aligning it more closely with the actual conditions encountered on railway sites.
{"title":"Research on Object Detection and Combination Clustering for Railway Switch Machine Gap Detection","authors":"Qingsheng Feng;Shuai Xiao;Wangyang Liu;Hong Li","doi":"10.23919/cje.2023.00.268","DOIUrl":"https://doi.org/10.23919/cje.2023.00.268","url":null,"abstract":"Turnouts and switch machines play a crucial role in facilitating train line operations and establishing routes, making them vital for ensuring the safety and efficiency of railway transportation. Through the gap detection system of switch machines, the real-time working status of turnouts and switch machines on railway sites can be quickly known. However, due to the challenging working environment and demanding conversion tasks of switch machines, the current gap detection system has often experienced the issues of fault detection. To address this, this study proposes an automatic gap detection method for railway switch machines based on object detection and combination clustering. Firstly, a lightweight object detection network, specifically the MobileNet V3-YOLOv5s model, is used to accurately locate and extract the focal area. Subsequently, the extracted image undergoes preprocessing and is then fed into a combination clustering algorithm to achieve precise segmentation of the gap area and background, the algorithm consists of simple linear iterative clustering, Canopy and kernel fuzzy c-means clustering. Finally, the Fisher optimal segmentation criterion is utilized to divide the data sequence of pixel values, determine the classification nodes and calculate the gap size. The experimental results obtained from switch machine gap images captured in various scenes demonstrate that the proposed method is capable of accurately locating focal areas, efficiently completing gap image segmentation with a segmentation accuracy of 93.55%, and swiftly calculating the gap size with a correct rate of 98.57%. Notably, the method achieves precise detection of gap sizes even after slight deflection of the acquisition camera, aligning it more closely with the actual conditions encountered on railway sites.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"186-203"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891988","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438417","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}
Pub Date : 2025-01-01DOI: 10.23919/cje.2023.00.276
Yuanyuan Wang;Xing Zhang;Zhiguang Chu;Wei Shi;Xiang Li
As people become increasingly reliant on the Internet, securely storing and publishing private data has become an important issue. In real life, the release of graph data can lead to privacy breaches, which is a highly challenging problem. Although current research has addressed the issue of identity disclosure, there are still two challenges: First, the privacy protection for large-scale datasets is not yet comprehensive; Second, it is difficult to simultaneously protect the privacy of nodes, edges, and attributes in social networks. To address these issues, this paper proposes a $(k, t)$-graph anonymity algorithm based on enhanced clustering. The algorithm uses $k$-means++ clustering for $k$-anonymity and $t$-closeness to improve $k$-anonymity. We evaluate the privacy and efficiency of this method on two datasets and achieved good results. This research is of great significance for addressing the problem of privacy breaches that may arise from the publication of graph data.
{"title":"An Enhanced Clustering-Based (k, t)-Anonymity Algorithm for Graphs","authors":"Yuanyuan Wang;Xing Zhang;Zhiguang Chu;Wei Shi;Xiang Li","doi":"10.23919/cje.2023.00.276","DOIUrl":"https://doi.org/10.23919/cje.2023.00.276","url":null,"abstract":"As people become increasingly reliant on the Internet, securely storing and publishing private data has become an important issue. In real life, the release of graph data can lead to privacy breaches, which is a highly challenging problem. Although current research has addressed the issue of identity disclosure, there are still two challenges: First, the privacy protection for large-scale datasets is not yet comprehensive; Second, it is difficult to simultaneously protect the privacy of nodes, edges, and attributes in social networks. To address these issues, this paper proposes a <tex>$(k, t)$</tex>-graph anonymity algorithm based on enhanced clustering. The algorithm uses <tex>$k$</tex>-means++ clustering for <tex>$k$</tex>-anonymity and <tex>$t$</tex>-closeness to improve <tex>$k$</tex>-anonymity. We evaluate the privacy and efficiency of this method on two datasets and achieved good results. This research is of great significance for addressing the problem of privacy breaches that may arise from the publication of graph data.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"365-372"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891996","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446298","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}
Distributed dual-function radar system is an emerging trend in next-generation wireless systems, offering the possibility of improved parameter estimation for target localization as well as improved communication performance. With sufficient resource allocation, the achievable minimum estimated mean square error (MSE) and maximum total communication rate of localization may exceed the intended performance metrics of the system, which may consume an excessive number of antennas as well as antenna costs. In order to avoid resource wastage, this paper proposes a distributed dual-function radar communication multiple-input multiple-output (MIMO) system capable of performing radar and communication tasks simultaneously. The distributed system achieves the desired MSE performance metrics and communication performance metrics by efficiently selecting a subset of antennas, and minimizing the number of transmitting antennas and receiving antennas used in the system as well as the cost. In this paper, the problem is modeled as a knapsack problem where the objective is to obtain the maximal MSE performance and the maximal total communication rate performance at the lowest cost, for which we design a heuristic antenna selection algorithm. The designed algorithm is effective in reducing the time complexity as well as reducing the cost of antenna, and minimizing the number of antennas required.
{"title":"Antenna Selection Method for Distributed Dual-Function Radar Communication in MIMO System","authors":"Haitao Zhao;Zhongzheng Ding;Qin Wang;Wenchao Xia;Bo xu;Hongbo Zhu","doi":"10.23919/cje.2023.00.270","DOIUrl":"https://doi.org/10.23919/cje.2023.00.270","url":null,"abstract":"Distributed dual-function radar system is an emerging trend in next-generation wireless systems, offering the possibility of improved parameter estimation for target localization as well as improved communication performance. With sufficient resource allocation, the achievable minimum estimated mean square error (MSE) and maximum total communication rate of localization may exceed the intended performance metrics of the system, which may consume an excessive number of antennas as well as antenna costs. In order to avoid resource wastage, this paper proposes a distributed dual-function radar communication multiple-input multiple-output (MIMO) system capable of performing radar and communication tasks simultaneously. The distributed system achieves the desired MSE performance metrics and communication performance metrics by efficiently selecting a subset of antennas, and minimizing the number of transmitting antennas and receiving antennas used in the system as well as the cost. In this paper, the problem is modeled as a knapsack problem where the objective is to obtain the maximal MSE performance and the maximal total communication rate performance at the lowest cost, for which we design a heuristic antenna selection algorithm. The designed algorithm is effective in reducing the time complexity as well as reducing the cost of antenna, and minimizing the number of antennas required.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"165-175"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891981","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438488","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：