Pub Date : 2025-07-01DOI: 10.23919/cje.2024.00.261
Li Chen;Wenjie Feng;Wenquan Che;Quan Xue
In this paper, a novel filtering switch with three operating states is proposed. The proposed structure consists of two coupling paths, a multi-mode bandpass filter, and an E-shaped notched band structure. A new transmission zero can be introduced through the source load coupling structure. Positive-intrinsic-negative (PIN) diodes are loaded at both ends of the branches of the multi-mode resonator and the branches of the notched band structure to switch different operating modes. The measured results show that the dual-band bandpass filter mode is centered at 2.35/3.23 GHz with 3-dB fractional bandwidth (FBW) of 10.20%/19.8%, and the minimal insertion isolation within the passband of 1.8/1.28 dB. The single-band bandpass filter mode is centered at 2.9 GHz, and the insertion loss is lower than 2.3 dB with FBW of 46.9%. The all-stop filter mode has an attenuation better than 27 dB from 1 GHz to 7 GHz. Simulated results and measured results show good agreement.
{"title":"A Novel Bandpass Filtering Switch with Reconfigurable Notched Band","authors":"Li Chen;Wenjie Feng;Wenquan Che;Quan Xue","doi":"10.23919/cje.2024.00.261","DOIUrl":"https://doi.org/10.23919/cje.2024.00.261","url":null,"abstract":"In this paper, a novel filtering switch with three operating states is proposed. The proposed structure consists of two coupling paths, a multi-mode bandpass filter, and an E-shaped notched band structure. A new transmission zero can be introduced through the source load coupling structure. Positive-intrinsic-negative (PIN) diodes are loaded at both ends of the branches of the multi-mode resonator and the branches of the notched band structure to switch different operating modes. The measured results show that the dual-band bandpass filter mode is centered at 2.35/3.23 GHz with 3-dB fractional bandwidth (FBW) of 10.20%/19.8%, and the minimal insertion isolation within the passband of 1.8/1.28 dB. The single-band bandpass filter mode is centered at 2.9 GHz, and the insertion loss is lower than 2.3 dB with FBW of 46.9%. The all-stop filter mode has an attenuation better than 27 dB from 1 GHz to 7 GHz. Simulated results and measured results show good agreement.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 4","pages":"1091-1099"},"PeriodicalIF":3.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151247","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144989946","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 : 2025-07-01DOI: 10.23919/cje.2025.00.016
Min Liu;Xiaoping Fan;Guiyun Liu;Dewei Liao;Junjie Yu;Jiale Huang
This paper focuses on enhancing the security of wireless sensor networks and analyzing the propagation of malware among nodes. It investigates an impulse susceptible-infectious-recovered (SILR-P, susceptible, infected, low-energy, recovered with impulses) model considering different communication connectivities. By using the next generation matrix, a threshold parameter similar to the basic reproduction number is derived. Combining this threshold parameter, the global stability of disease-free periodic solutions is examined. Additionally, the persistence of malware propagation is verified. To curb the spread of malware, an optimal control strategy based on the Pontryagin maximum principle is proposed. In numerical simulations, the impact of cross infection on malware propagation is specifically considered. Finally, partial rank correlation coefficients are utilized for sensitivity analysis of the proposed threshold parameter.
{"title":"An Epidemic Model with Two Impulses for the Propagation of Malware in Heterogeneous Wireless Sensor Networks","authors":"Min Liu;Xiaoping Fan;Guiyun Liu;Dewei Liao;Junjie Yu;Jiale Huang","doi":"10.23919/cje.2025.00.016","DOIUrl":"https://doi.org/10.23919/cje.2025.00.016","url":null,"abstract":"This paper focuses on enhancing the security of wireless sensor networks and analyzing the propagation of malware among nodes. It investigates an impulse susceptible-infectious-recovered (SILR-P, susceptible, infected, low-energy, recovered with impulses) model considering different communication connectivities. By using the next generation matrix, a threshold parameter similar to the basic reproduction number is derived. Combining this threshold parameter, the global stability of disease-free periodic solutions is examined. Additionally, the persistence of malware propagation is verified. To curb the spread of malware, an optimal control strategy based on the Pontryagin maximum principle is proposed. In numerical simulations, the impact of cross infection on malware propagation is specifically considered. Finally, partial rank correlation coefficients are utilized for sensitivity analysis of the proposed threshold parameter.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 4","pages":"1357-1374"},"PeriodicalIF":3.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151236","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990199","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 : 2025-07-01DOI: 10.23919/cje.2024.00.303
Chunlei Xie;Yu Sun;Liupiao Zhang;Hui Ge
This paper introduces a novel kind of cross Z-complementary sequence sets, characterized by zero correlation zones at both the front-end and tail-end shifts in their aperiodic correlation sums. Initially, we propose a direct approach to constructing mutually orthogonal complementary sequence sets through the Boolean functions. Subsequently, we present a direct construction of cross Z-complementary sequence sets featuring large set sizes and flexible lengths based on Boolean functions. These sequence sets hold potential applications in the design of training sequences for broadband generalized spatial modulation (GSM) systems operating over frequency-selective channels.
{"title":"New Constructions of Binary Cross Z-Complementary Sequence Sets Based on Boolean Functions for Training in Generalized Spatial Modulation","authors":"Chunlei Xie;Yu Sun;Liupiao Zhang;Hui Ge","doi":"10.23919/cje.2024.00.303","DOIUrl":"https://doi.org/10.23919/cje.2024.00.303","url":null,"abstract":"This paper introduces a novel kind of cross Z-complementary sequence sets, characterized by zero correlation zones at both the front-end and tail-end shifts in their aperiodic correlation sums. Initially, we propose a direct approach to constructing mutually orthogonal complementary sequence sets through the Boolean functions. Subsequently, we present a direct construction of cross Z-complementary sequence sets featuring large set sizes and flexible lengths based on Boolean functions. These sequence sets hold potential applications in the design of training sequences for broadband generalized spatial modulation (GSM) systems operating over frequency-selective channels.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 4","pages":"1146-1155"},"PeriodicalIF":3.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151176","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990281","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}
As an extension of human action recognition, dance action recognition has been a significant research area with potential applications in dance education, entertainment, artistic protection, and cultural heritage preservation. However, the current human action recognition methods face challenges in capturing rich geometric and physical characteristics of dance actions due to their diversity, high complexity, and individual variation in execution. In this paper, a dynamic topology inferenced graph convolution network (DTI-GNet) is proposed for dance action recognition. First, a bone-joint features embedding encoding module is devised to infer the geometric and physical characteristics hidden in spatial structures and temporal dynamics during action performance, aiming to capture action-specific bone-joint dependencies. Second, a spatial-temporal dynamic topological encoding module is specifically designed to exploit joint-bone geometric and physical properties, relaxing the restrictions of the fixed topology and overcoming oversmoothing problems encountered by stracked graph convolution layer with rigid topology. Finally, a dynamic topology inferenced spatial-temporal graph convolution layer is developed as a fundamental unit to construct DTI-GNet, exploring the co-occurrence features and inter-dependencies between joints. Experimental results on two dance action datasets, MSDanceAction and InDanceAction, demonstrate the superiority of the proposed method for dance action recognition.
{"title":"DTI-GNet: Dynamic Topology Inferenced Graph Convolution Network for Dance Action Recognition","authors":"Honghong Yang;Sai Wang;Lu Jiang;Yumei Zhang;Xiaojun Wu","doi":"10.23919/cje.2024.00.184","DOIUrl":"https://doi.org/10.23919/cje.2024.00.184","url":null,"abstract":"As an extension of human action recognition, dance action recognition has been a significant research area with potential applications in dance education, entertainment, artistic protection, and cultural heritage preservation. However, the current human action recognition methods face challenges in capturing rich geometric and physical characteristics of dance actions due to their diversity, high complexity, and individual variation in execution. In this paper, a dynamic topology inferenced graph convolution network (DTI-GNet) is proposed for dance action recognition. First, a bone-joint features embedding encoding module is devised to infer the geometric and physical characteristics hidden in spatial structures and temporal dynamics during action performance, aiming to capture action-specific bone-joint dependencies. Second, a spatial-temporal dynamic topological encoding module is specifically designed to exploit joint-bone geometric and physical properties, relaxing the restrictions of the fixed topology and overcoming oversmoothing problems encountered by stracked graph convolution layer with rigid topology. Finally, a dynamic topology inferenced spatial-temporal graph convolution layer is developed as a fundamental unit to construct DTI-GNet, exploring the co-occurrence features and inter-dependencies between joints. Experimental results on two dance action datasets, MSDanceAction and InDanceAction, demonstrate the superiority of the proposed method for dance action recognition.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 4","pages":"1284-1299"},"PeriodicalIF":3.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151181","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990313","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 : 2025-03-01DOI: 10.23919/cje.2023.00.381
Shihui Zheng;Shoujin Zang;Ruihao Xing;Jiayu Zhang;Changhai Ou
A persistent fault analysis (PFA) can break implementations of the advanced encryption standard (AES) secured by fault attack countermeasures that prevent differential analyses based on transient faults (DFA). When the AES implementation is protected by some higher-order masking countermeasure, the number of required ciphertexts may increase exponentially with the growth of the number of shares. We present a persistent-fault-based differential analysis (PFDA) against AES implementations. Two error patterns are detected by ciphertext pairs. Namely, only one error occurs at a SubBytes operation in round 10, and only one error occurs at a SubBytes operation in round 9. The latter is used to derive a differential characteristic (DC) for the key recovery, and the former is explored to deduce the input difference of the DC. Thus, the computational complexity is reduced compared to DFA. Encrypting a fixed plaintext many times to tolerate errors is utilized in PFDA against RP countermeasures. The number of required encryptions increases linearly with the growth of the number of shares. The simulation results show that PFDA can break unprotected AES implementations and implementations secured by fault attack counter-measures or the above higher-order masking countermeasures. Compared to other analyses based on persistent fault, the required number of ciphertexts of PFDA is the lowest.
{"title":"Persistent-Fault Based Differential Analysis and Applications to Masking and Fault Countermeasures","authors":"Shihui Zheng;Shoujin Zang;Ruihao Xing;Jiayu Zhang;Changhai Ou","doi":"10.23919/cje.2023.00.381","DOIUrl":"https://doi.org/10.23919/cje.2023.00.381","url":null,"abstract":"A persistent fault analysis (PFA) can break implementations of the advanced encryption standard (AES) secured by fault attack countermeasures that prevent differential analyses based on transient faults (DFA). When the AES implementation is protected by some higher-order masking countermeasure, the number of required ciphertexts may increase exponentially with the growth of the number of shares. We present a persistent-fault-based differential analysis (PFDA) against AES implementations. Two error patterns are detected by ciphertext pairs. Namely, only one error occurs at a SubBytes operation in round 10, and only one error occurs at a SubBytes operation in round 9. The latter is used to derive a differential characteristic (DC) for the key recovery, and the former is explored to deduce the input difference of the DC. Thus, the computational complexity is reduced compared to DFA. Encrypting a fixed plaintext many times to tolerate errors is utilized in PFDA against RP countermeasures. The number of required encryptions increases linearly with the growth of the number of shares. The simulation results show that PFDA can break unprotected AES implementations and implementations secured by fault attack counter-measures or the above higher-order masking countermeasures. Compared to other analyses based on persistent fault, the required number of ciphertexts of PFDA is the lowest.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 2","pages":"548-562"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10982070","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900610","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 : 2025-03-01DOI: 10.23919/cje.2024.00.041
Kun Li;Shuailong Chen;Shuaiyong Zheng;Xuanwen Wang;Jixi Liu;Peng Yang;Mengzhi Gao;Xiaoqin Jin
The BeiDou Navigation Satellite System (BDS-3) has provided positioning, navigation and timing (PNT) services to global users across land, maritime, and aviation. However, how to classify these three types of users with complex movement patterns poses great challenges to the work of monitoring and evaluating the PNT system. To accurately classify multi-type global navigation satellite system (GNSS) users, this paper proposes a method that combines random sample consensus (RANSAC) and K-means clustering to track the movements of massive users and classify them based on their dynamic characteristics in different areas, which is noted as RANSAC-K-means. The simulated massive user data show that the recognition rate of the proposed algorithm exceeds 83.22%, and compared with the conventional method, the proposed RANSAC-K-means method improved the recognition rate by 11.16%. The RANSAC-K-means method can provide more accurate clustering results under the situations where multi-type users present dynamic characteristics with significant differences, showing significant stability and robustness. The proposed method is more suitable for monitoring and evaluating the service performance of satellite navigation systems.
{"title":"Multi-Type GNSS User Classification Using RANSAC-K-Means Clustering","authors":"Kun Li;Shuailong Chen;Shuaiyong Zheng;Xuanwen Wang;Jixi Liu;Peng Yang;Mengzhi Gao;Xiaoqin Jin","doi":"10.23919/cje.2024.00.041","DOIUrl":"https://doi.org/10.23919/cje.2024.00.041","url":null,"abstract":"The BeiDou Navigation Satellite System (BDS-3) has provided positioning, navigation and timing (PNT) services to global users across land, maritime, and aviation. However, how to classify these three types of users with complex movement patterns poses great challenges to the work of monitoring and evaluating the PNT system. To accurately classify multi-type global navigation satellite system (GNSS) users, this paper proposes a method that combines random sample consensus (RANSAC) and K-means clustering to track the movements of massive users and classify them based on their dynamic characteristics in different areas, which is noted as RANSAC-K-means. The simulated massive user data show that the recognition rate of the proposed algorithm exceeds 83.22%, and compared with the conventional method, the proposed RANSAC-K-means method improved the recognition rate by 11.16%. The RANSAC-K-means method can provide more accurate clustering results under the situations where multi-type users present dynamic characteristics with significant differences, showing significant stability and robustness. The proposed method is more suitable for monitoring and evaluating the service performance of satellite navigation systems.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 2","pages":"730-738"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10982099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900629","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 : 2025-03-01DOI: 10.23919/cje.2024.00.200
Yuan Cao;Long Ma;Yongkui Sun;Feng Wang;Shuai Su
The complex infrastructure and harsh conditions of heavy-haul railways result in frequently and rapidly deteriorating rail surface defects. Accurate detection of these defects is essential. To solve the problem of low detection precision caused by complex background interference, significant variation in defect scales, and similar features between different types of defects, a high-precision rail surface defect detection method for heavy-haul railways based on an improved YOLOv8 is proposed. First, the original grayscale images are preprocessed to reduce background noise interference. Then, the designed scale variation adaptation module is introduced to mitigate the impact of significant scale variations in the target defects. Additionally, a bidirectional feature pyramid network is incorporated to enhance feature fusion effectiveness. Furthermore, a small target detection head is introduced to improve the detection performance of small-scale defects. Lastly, network performance is optimized by replacing the original loss function with wise-intersection over union. Experimental results demonstrate that the improved model achieves a mean average precision at 50% intersection over union (mAP50) value of 0.975, representing a 4.13% improvement in precision and a 7.75% increase in recall compared to the baseline model. The improved model effectively detects typical defects such as spalling, shelling, and corrugation, providing valuable technical support for field maintenance personnel.
{"title":"Improved YOLOv8 for High-Precision Detection of Rail Surface Defects on Heavy-Haul Railways","authors":"Yuan Cao;Long Ma;Yongkui Sun;Feng Wang;Shuai Su","doi":"10.23919/cje.2024.00.200","DOIUrl":"https://doi.org/10.23919/cje.2024.00.200","url":null,"abstract":"The complex infrastructure and harsh conditions of heavy-haul railways result in frequently and rapidly deteriorating rail surface defects. Accurate detection of these defects is essential. To solve the problem of low detection precision caused by complex background interference, significant variation in defect scales, and similar features between different types of defects, a high-precision rail surface defect detection method for heavy-haul railways based on an improved YOLOv8 is proposed. First, the original grayscale images are preprocessed to reduce background noise interference. Then, the designed scale variation adaptation module is introduced to mitigate the impact of significant scale variations in the target defects. Additionally, a bidirectional feature pyramid network is incorporated to enhance feature fusion effectiveness. Furthermore, a small target detection head is introduced to improve the detection performance of small-scale defects. Lastly, network performance is optimized by replacing the original loss function with wise-intersection over union. Experimental results demonstrate that the improved model achieves a mean average precision at 50% intersection over union (mAP50) value of 0.975, representing a 4.13% improvement in precision and a 7.75% increase in recall compared to the baseline model. The improved model effectively detects typical defects such as spalling, shelling, and corrugation, providing valuable technical support for field maintenance personnel.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 3","pages":"802-815"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11060014","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519223","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 : 2025-03-01DOI: 10.23919/cje.2024.00.115
Xuan Deng;Yikai Chen;Shiwen Yang
A novel multiport multi-input multi-output (MIMO) antenna for 4G/5G base station application is developed based on the theory of characteristic modes (TCM). The solved characteristic modes illustrate that it is possible to excite five modes simultaneously with a properly designed patch in the 1.7-2.7 GHz frequency band. The characteristic modes also provide clear guidelines for selecting feeding places and designing excitation for the characteristic modes. The natural orthogonality property of characteristic modes guarantees high isolations among the many ports in a MIMO antenna system. The developed MIMO antenna is comprised of two layers. The top layer is the radiating aperture, while the bottom layer is the feeding circuit. The working frequency band of the developed MIMO antenna is 1.64-2.74 GHz, which can be used in 4G Long-Term Evolution and sub-6 GHz 5G networks. By using TCM and orthogonality of characteristic modes, a compact four-port MIMO antenna is designed with at least 20 dB isolations. The four ports excite different shapes of radiation patterns with diverse polarizations and radiation patterns. The envelope correlation coefficient is extremely low between the four ports, which makes it attractive for MIMO diversity systems. Both simulated and measured results are presented to demonstrate the proposed design. In addition, the ergodic channel capacity is also evaluated to demonstrate the enhanced capability in communication system applications.
{"title":"A Characteristic Mode Based Multiport Antennas for MIMO Base Station Applications","authors":"Xuan Deng;Yikai Chen;Shiwen Yang","doi":"10.23919/cje.2024.00.115","DOIUrl":"https://doi.org/10.23919/cje.2024.00.115","url":null,"abstract":"A novel multiport multi-input multi-output (MIMO) antenna for 4G/5G base station application is developed based on the theory of characteristic modes (TCM). The solved characteristic modes illustrate that it is possible to excite five modes simultaneously with a properly designed patch in the 1.7-2.7 GHz frequency band. The characteristic modes also provide clear guidelines for selecting feeding places and designing excitation for the characteristic modes. The natural orthogonality property of characteristic modes guarantees high isolations among the many ports in a MIMO antenna system. The developed MIMO antenna is comprised of two layers. The top layer is the radiating aperture, while the bottom layer is the feeding circuit. The working frequency band of the developed MIMO antenna is 1.64-2.74 GHz, which can be used in 4G Long-Term Evolution and sub-6 GHz 5G networks. By using TCM and orthogonality of characteristic modes, a compact four-port MIMO antenna is designed with at least 20 dB isolations. The four ports excite different shapes of radiation patterns with diverse polarizations and radiation patterns. The envelope correlation coefficient is extremely low between the four ports, which makes it attractive for MIMO diversity systems. Both simulated and measured results are presented to demonstrate the proposed design. In addition, the ergodic channel capacity is also evaluated to demonstrate the enhanced capability in communication system applications.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 3","pages":"755-765"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11060053","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519446","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 : 2025-03-01DOI: 10.23919/cje.2023.00.130
Jiajie Shi;Zhi Yang;Jiafeng Liu;Hongli Shi
Many sparse representation problems boil down to address the underdetermined systems of linear equations subject to solution sparsity restriction. Many approaches have been proposed such as sparse Bayesian learning. In order to improve solution sparsity and effectiveness in a more intuitive way, a new approach is proposed, which starts from the general solution of the linear equation system. The general solution is decomposed into the particular and homogeneous solutions, where the homogeneous solution is designed to counteract as many elements of particular solution as possible to make the general solution sparse. First, construct a special system of linear equations to link the homogeneous solution with particular solution, which typically is an inconsistent system. Second, the largest consistent sub-system are extracted from the system so that as many corresponding elements of two solutions as possible cancel each other out. By improving implementation efficiency, the procedure can be accomplished with moderate computational time. The results of extensive experiments for sparse signal recovery and image reconstruction demonstrate the superiority of the proposed approach in terms of sparseness or recovery accuracy with acceptable computational burden.
{"title":"Sparse Homogeneous Learning: A New Approach for Sparse Learning","authors":"Jiajie Shi;Zhi Yang;Jiafeng Liu;Hongli Shi","doi":"10.23919/cje.2023.00.130","DOIUrl":"https://doi.org/10.23919/cje.2023.00.130","url":null,"abstract":"Many sparse representation problems boil down to address the underdetermined systems of linear equations subject to solution sparsity restriction. Many approaches have been proposed such as sparse Bayesian learning. In order to improve solution sparsity and effectiveness in a more intuitive way, a new approach is proposed, which starts from the general solution of the linear equation system. The general solution is decomposed into the particular and homogeneous solutions, where the homogeneous solution is designed to counteract as many elements of particular solution as possible to make the general solution sparse. First, construct a special system of linear equations to link the homogeneous solution with particular solution, which typically is an inconsistent system. Second, the largest consistent sub-system are extracted from the system so that as many corresponding elements of two solutions as possible cancel each other out. By improving implementation efficiency, the procedure can be accomplished with moderate computational time. The results of extensive experiments for sparse signal recovery and image reconstruction demonstrate the superiority of the proposed approach in terms of sparseness or recovery accuracy with acceptable computational burden.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 2","pages":"712-721"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10982098","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900513","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 : 2025-03-01DOI: 10.23919/cje.2024.00.182
Yue Chen;Yongzhong Huang
Temporal knowledge graph (TKG) reasoning aims to predict missing facts or future events at given timestamps and has attracted more and more attention in recent years. Existing TKG reasoning methods mainly focus on the interactions between entities and ignore the associations between events where the entities involve. In addition, the characteristics of different types of events have not been studied and exploited, which reduces the performance of event prediction. To address these problems, this paper proposes a combination model of periodic and non-periodic events (CM-PNP). Specifically, there are two basic components designed to process different types of events. The periodic component of CM-PNP learns the recurrent pattern of periodic events and encodes the temporal information in the manner of timespan to prevent the unseen timestamp issue. The non-periodic component of CM-PNP introduces extra information (e.g., entity attributes) to represent non-periodic events, and predicts this type of events according to the related historical events. A combination model of multiple sub-models that focus on encoding different parts of the event is used to improve the performance of single model. The periodic and non-periodic components are combined by a gate block. The experimental results on three real-world datasets demonstrate that CM-PNP outperforms the existing baselines.
{"title":"A Combination Model of Periodic and Non-periodic Events for Temporal Knowledge Graph Event Prediction","authors":"Yue Chen;Yongzhong Huang","doi":"10.23919/cje.2024.00.182","DOIUrl":"https://doi.org/10.23919/cje.2024.00.182","url":null,"abstract":"Temporal knowledge graph (TKG) reasoning aims to predict missing facts or future events at given timestamps and has attracted more and more attention in recent years. Existing TKG reasoning methods mainly focus on the interactions between entities and ignore the associations between events where the entities involve. In addition, the characteristics of different types of events have not been studied and exploited, which reduces the performance of event prediction. To address these problems, this paper proposes a combination model of periodic and non-periodic events (CM-PNP). Specifically, there are two basic components designed to process different types of events. The periodic component of CM-PNP learns the recurrent pattern of periodic events and encodes the temporal information in the manner of timespan to prevent the unseen timestamp issue. The non-periodic component of CM-PNP introduces extra information (e.g., entity attributes) to represent non-periodic events, and predicts this type of events according to the related historical events. A combination model of multiple sub-models that focus on encoding different parts of the event is used to improve the performance of single model. The periodic and non-periodic components are combined by a gate block. The experimental results on three real-world datasets demonstrate that CM-PNP outperforms the existing baselines.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 3","pages":"952-961"},"PeriodicalIF":1.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11060050","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519232","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：