Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906321
Yu Guo, Shufeng Li, Mingyu Cai
The Successive-Cancellation List (SCL) algorithm is a popular decoding algorithm for polar codes. Although SCL algorithm overcomes the error propagation problem in polar codes decoding, the improvement of error correction performance needs to pay the price of high latency. To solve this problem, a simplified SCL (SSCL) algorithm is proposed. For some special nodes, the SSCL algorithm can calculate path metric (PM) without traversing the decoding tree to achieve direct decoding, reducing the latency and complexity of decoding. In this paper, a new special node has been discovered, it is also possible to calculate PM without traversing decoding tree. Based on this, we propose an improved SSCL algorithm. Simulation results show that improved SSCL algorithm can further reduce the decoding latency and the loss of error-correction performance is negligible.
{"title":"An Improved Simplified Successive-Cancellation List Decoding of Polar Codes","authors":"Yu Guo, Shufeng Li, Mingyu Cai","doi":"10.1109/CCET55412.2022.9906321","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906321","url":null,"abstract":"The Successive-Cancellation List (SCL) algorithm is a popular decoding algorithm for polar codes. Although SCL algorithm overcomes the error propagation problem in polar codes decoding, the improvement of error correction performance needs to pay the price of high latency. To solve this problem, a simplified SCL (SSCL) algorithm is proposed. For some special nodes, the SSCL algorithm can calculate path metric (PM) without traversing the decoding tree to achieve direct decoding, reducing the latency and complexity of decoding. In this paper, a new special node has been discovered, it is also possible to calculate PM without traversing decoding tree. Based on this, we propose an improved SSCL algorithm. Simulation results show that improved SSCL algorithm can further reduce the decoding latency and the loss of error-correction performance is negligible.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132128199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906363
Lin Yang, Zhi-Long Zhang, Shoumo Wang, Wen-Ting Zhang, Rui Dai, Yin-Bo Liu
Current transformer is a key power equipment for high-speed railway power, with high risk for the operator. Based on the architecture of edge-cloud collaborative computing, an automatic high voltage transformer verification technology is proposed considering the applicability in various fields. a vehicle mounted verification device is designed, on which the verification computing at edge side can be realized. The working state model of current transformer is built based on the closed-loop ARMAX model. Combing the ARMAX Model identification with MOEA/D tendency guidance, the characteristic of fault mode for high voltage transformer is proposed. The comparative validation experiment is conducted for 30 consecutive days at a 15VA current transformer and a3.75VA current transformer. The results show that the estimated value of ratio error can reflect actual state changes, which can be used to identify the fault status of the high voltage current transformer. The automatic high voltage transformer verification is achieved with more security for the operator, and it has the value of promotion and application.
{"title":"Automatic Current Transformer Verification Technology for High-Speed Railway Power Based on Edge-Cloud Collaborative Computing","authors":"Lin Yang, Zhi-Long Zhang, Shoumo Wang, Wen-Ting Zhang, Rui Dai, Yin-Bo Liu","doi":"10.1109/CCET55412.2022.9906363","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906363","url":null,"abstract":"Current transformer is a key power equipment for high-speed railway power, with high risk for the operator. Based on the architecture of edge-cloud collaborative computing, an automatic high voltage transformer verification technology is proposed considering the applicability in various fields. a vehicle mounted verification device is designed, on which the verification computing at edge side can be realized. The working state model of current transformer is built based on the closed-loop ARMAX model. Combing the ARMAX Model identification with MOEA/D tendency guidance, the characteristic of fault mode for high voltage transformer is proposed. The comparative validation experiment is conducted for 30 consecutive days at a 15VA current transformer and a3.75VA current transformer. The results show that the estimated value of ratio error can reflect actual state changes, which can be used to identify the fault status of the high voltage current transformer. The automatic high voltage transformer verification is achieved with more security for the operator, and it has the value of promotion and application.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125366662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906356
Yu Zhang, Jinhong Li
The disadvantage of the grasshopper optimization algorithm (GOA) is its insufficient ability in global exploration, relatively slow convergence speed, and easy to obtain the local optimal solution. Aiming at the poor convergence accuracy of GOA algorithm, a new grasshopper optimization algorithm(OLCZGOA) based on adaptive fusion curve and reverse learning was proposed. Firstly, an improved curve adaptive formula is introduced to replace the linear adaptive formula of parameter C in the grasshopper optimization algorithm to improve the convergence speed of the algorithm. Secondly, considering that grasshopper optimization algorithm is easy to obtain local optimal solutions, three selection strategies are introduced to reverse learning, which makes grasshopper optimization algorithm have stronger global optimization ability. In this paper, nine test functions are selected to test the proposed improved algorithm. The results show the effectiveness of the proposed improved strategy, and the OLCZGOA algorithm has better solution accuracy compared with other comparison algorithms.
{"title":"Grasshopper Optimization Algorithm Based on Adaptive Curve and Reverse Learning","authors":"Yu Zhang, Jinhong Li","doi":"10.1109/CCET55412.2022.9906356","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906356","url":null,"abstract":"The disadvantage of the grasshopper optimization algorithm (GOA) is its insufficient ability in global exploration, relatively slow convergence speed, and easy to obtain the local optimal solution. Aiming at the poor convergence accuracy of GOA algorithm, a new grasshopper optimization algorithm(OLCZGOA) based on adaptive fusion curve and reverse learning was proposed. Firstly, an improved curve adaptive formula is introduced to replace the linear adaptive formula of parameter C in the grasshopper optimization algorithm to improve the convergence speed of the algorithm. Secondly, considering that grasshopper optimization algorithm is easy to obtain local optimal solutions, three selection strategies are introduced to reverse learning, which makes grasshopper optimization algorithm have stronger global optimization ability. In this paper, nine test functions are selected to test the proposed improved algorithm. The results show the effectiveness of the proposed improved strategy, and the OLCZGOA algorithm has better solution accuracy compared with other comparison algorithms.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126752509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906354
Yuwen Zhu, Lei Yu
As the cyberspace structure becomes more and more complex, the problems of dynamic network space topology, complex composition structure, large spanning space scale, and a high degree of self-organization are becoming more and more important. In this paper, we model the cyberspace elements and their dependencies by combining the knowledge of graph theory. Layer adopts a network space modeling method combining virtual and real, and level adopts a spatial iteration method. Combining the layer-level models into one, this paper proposes a fast modeling method for cyberspace security structure model with network connection relationship, hierarchical relationship, and vulnerability information as input. This method can not only clearly express the individual vulnerability constraints in the network space, but also clearly express the hierarchical relationship of the complex dependencies of network individuals. For independent network elements or independent network element groups, it has flexibility and can greatly reduce the computational complexity in later applications.
{"title":"A Modeling Method of Cyberspace Security Structure Based on Layer-Level Division","authors":"Yuwen Zhu, Lei Yu","doi":"10.1109/CCET55412.2022.9906354","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906354","url":null,"abstract":"As the cyberspace structure becomes more and more complex, the problems of dynamic network space topology, complex composition structure, large spanning space scale, and a high degree of self-organization are becoming more and more important. In this paper, we model the cyberspace elements and their dependencies by combining the knowledge of graph theory. Layer adopts a network space modeling method combining virtual and real, and level adopts a spatial iteration method. Combining the layer-level models into one, this paper proposes a fast modeling method for cyberspace security structure model with network connection relationship, hierarchical relationship, and vulnerability information as input. This method can not only clearly express the individual vulnerability constraints in the network space, but also clearly express the hierarchical relationship of the complex dependencies of network individuals. For independent network elements or independent network element groups, it has flexibility and can greatly reduce the computational complexity in later applications.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126985456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906353
Xu Yefeng, Jiao Ruili, Huang Minsong
This paper studies design of data processing software for raindrop spectrometer. It includes reading, decompression, data processing, storage and display. The difficulties are data decompression and the software architecture design. This software applies digital image processing technology to process the raindrop data measured by dual-line raindrop spectrometer data processing software (DRDPS) based on LabVIEW, realizes the display from data file to particle image, stores the obtained information and geometric parameters of precipitation particles, and the obtained meteorological information of precipitation intensity, precipitation particle shape, precipitation type and precipitation particle spectrum is displayed in the front panel of the software. The test results show that the software meets the system requirements completely and can be applied to the research of cloud precipitation and other atmospheric science relevant fields.
{"title":"Design of Data Processing Software for Raindrop Spectrometer Based on LabVIEW","authors":"Xu Yefeng, Jiao Ruili, Huang Minsong","doi":"10.1109/CCET55412.2022.9906353","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906353","url":null,"abstract":"This paper studies design of data processing software for raindrop spectrometer. It includes reading, decompression, data processing, storage and display. The difficulties are data decompression and the software architecture design. This software applies digital image processing technology to process the raindrop data measured by dual-line raindrop spectrometer data processing software (DRDPS) based on LabVIEW, realizes the display from data file to particle image, stores the obtained information and geometric parameters of precipitation particles, and the obtained meteorological information of precipitation intensity, precipitation particle shape, precipitation type and precipitation particle spectrum is displayed in the front panel of the software. The test results show that the software meets the system requirements completely and can be applied to the research of cloud precipitation and other atmospheric science relevant fields.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122740636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906365
Wang Lan, Zhang Ruimin
China’s environmental regulations are increasingly stringent to achieve carbon peaking and carbon neutrality. In this context, more enterprises carry out green innovation practice. As the decision-maker and the person who allocate resources in an enterprise, the characteristics of top management team (TMT) have an impact on the strategic practice and performance of green innovation. Based on data of A-shares listed manufacturing companies from 2019 to 2020, we explore the relationship between TMT’s overconfidence and green innovation behavior from three dimensions, green supply process innovation, green production process innovation and green distribution process innovation. The results show that the overconfident TMT facilitates green production process innovation and green distribution process innovation.
{"title":"Study on the Relationship between TMT’s Overconfidence and Green Innovation","authors":"Wang Lan, Zhang Ruimin","doi":"10.1109/CCET55412.2022.9906365","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906365","url":null,"abstract":"China’s environmental regulations are increasingly stringent to achieve carbon peaking and carbon neutrality. In this context, more enterprises carry out green innovation practice. As the decision-maker and the person who allocate resources in an enterprise, the characteristics of top management team (TMT) have an impact on the strategic practice and performance of green innovation. Based on data of A-shares listed manufacturing companies from 2019 to 2020, we explore the relationship between TMT’s overconfidence and green innovation behavior from three dimensions, green supply process innovation, green production process innovation and green distribution process innovation. The results show that the overconfident TMT facilitates green production process innovation and green distribution process innovation.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133052450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906322
Yuting Wang, Ting Hao, Hai Wang
With the communication network scale, the increasing bandwidth and complexity of the constant improvement of the quality of network service, and user requirements, an urgent need to intelligent communication system of the current high speed communication network for effective and reliable management, and fault management is becoming more difficult and important than ever, when the network produces a fault or failure, Many thousands of alarms are generated in a short period of time, so analyzing the signals of these alarms becomes more complicated. Some existing alarm analysis systems have some shortcomings, such as poor scalability, difficulty in dealing with complex situations, and lack of learning ability. This paper proposes a method of fault identification and alarm correlation analysis based on deep learning algorithm. Combined with deep reinforcement learning technology, a sleep scheduling strategy based on multi-level is designed to reduce energy consumption, and its effectiveness is verified by simulation. Experimental results show THAT this method can overcome the limitations of common alarm correlation analysis methods, and create favorable conditions for improving the efficient utilization of spectrum resources in private networks.
{"title":"Research on Fault Identification Method of Power System Communication Network Based on Deep Learning","authors":"Yuting Wang, Ting Hao, Hai Wang","doi":"10.1109/CCET55412.2022.9906322","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906322","url":null,"abstract":"With the communication network scale, the increasing bandwidth and complexity of the constant improvement of the quality of network service, and user requirements, an urgent need to intelligent communication system of the current high speed communication network for effective and reliable management, and fault management is becoming more difficult and important than ever, when the network produces a fault or failure, Many thousands of alarms are generated in a short period of time, so analyzing the signals of these alarms becomes more complicated. Some existing alarm analysis systems have some shortcomings, such as poor scalability, difficulty in dealing with complex situations, and lack of learning ability. This paper proposes a method of fault identification and alarm correlation analysis based on deep learning algorithm. Combined with deep reinforcement learning technology, a sleep scheduling strategy based on multi-level is designed to reduce energy consumption, and its effectiveness is verified by simulation. Experimental results show THAT this method can overcome the limitations of common alarm correlation analysis methods, and create favorable conditions for improving the efficient utilization of spectrum resources in private networks.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133242604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906358
Shen Hong, Heng Qian, Yongchao Gao, Hongli Lyu
In knowledge graphs (KGs), there exist some unsolved problems such as incomplete data, hidden information with incomplete mining and so on. In the most completion models, the information of the triples in the KG is generally utilized, but the neighborhood information and rich entity description information are not included in the triples. In this paper, the knowledge graph completion (KGC) method is improved based on graph attention networks (GATs) with text information by using the neighborhood information of aggregated triples and entity description information. And the embedding capability of semantic information is enhanced in KGs. First, the feature vector of entity description information is extracted by the Bi-LSTM model and concatenated with the entity embedding in the triples. Then the joint vectors are trained by GATs to aggregate the neighborhood information. Next, the KGC task is realized by a decoder. Finally, the effectiveness of the proposed method is verified by the link prediction experiments in the public datasets FB15K-237 and WNISRR and comparison is investigated with several other existing methods. The test results show that most of the indicators in the two datasets are improved. Furthermore, it is proved that the model combined with multi-source information has better representation ability for entities, which can further improve the accuracy and comprehensive performance of KGC tasks.
{"title":"Knowledge Graph Completion Based on Graph Attention Networks and Text Information","authors":"Shen Hong, Heng Qian, Yongchao Gao, Hongli Lyu","doi":"10.1109/CCET55412.2022.9906358","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906358","url":null,"abstract":"In knowledge graphs (KGs), there exist some unsolved problems such as incomplete data, hidden information with incomplete mining and so on. In the most completion models, the information of the triples in the KG is generally utilized, but the neighborhood information and rich entity description information are not included in the triples. In this paper, the knowledge graph completion (KGC) method is improved based on graph attention networks (GATs) with text information by using the neighborhood information of aggregated triples and entity description information. And the embedding capability of semantic information is enhanced in KGs. First, the feature vector of entity description information is extracted by the Bi-LSTM model and concatenated with the entity embedding in the triples. Then the joint vectors are trained by GATs to aggregate the neighborhood information. Next, the KGC task is realized by a decoder. Finally, the effectiveness of the proposed method is verified by the link prediction experiments in the public datasets FB15K-237 and WNISRR and comparison is investigated with several other existing methods. The test results show that most of the indicators in the two datasets are improved. Furthermore, it is proved that the model combined with multi-source information has better representation ability for entities, which can further improve the accuracy and comprehensive performance of KGC tasks.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116249461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906386
Xin Jin, Xinnian Wang, Ran Ding, Yunchao Wu
Wargame, as a tool to generate sample data for analysis and model training, has vast application in fields of training, command & control, and tactical research. Traditional wargame technologies greatly rely on human wisdom in the loop, impossible to generate large scale sample data. Reinforcement learning technology can generate large scale sample data, but it is not competent for the decision complexity above campaign level. This paper proposes a hybrid intelligence wargame method, which can generate large scale sample data using AI algorithms under the guidance of human wisdom. It has wide applications, which provides data analysis functions that existing wargame methods cannot provide. Prototype software has been developed based on the method, with feasibility and effectiveness verified through experiments, which has certain reference value.
{"title":"Research on Hybrid Intelligence Wargame Method","authors":"Xin Jin, Xinnian Wang, Ran Ding, Yunchao Wu","doi":"10.1109/CCET55412.2022.9906386","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906386","url":null,"abstract":"Wargame, as a tool to generate sample data for analysis and model training, has vast application in fields of training, command & control, and tactical research. Traditional wargame technologies greatly rely on human wisdom in the loop, impossible to generate large scale sample data. Reinforcement learning technology can generate large scale sample data, but it is not competent for the decision complexity above campaign level. This paper proposes a hybrid intelligence wargame method, which can generate large scale sample data using AI algorithms under the guidance of human wisdom. It has wide applications, which provides data analysis functions that existing wargame methods cannot provide. Prototype software has been developed based on the method, with feasibility and effectiveness verified through experiments, which has certain reference value.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122051065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-19DOI: 10.1109/CCET55412.2022.9906401
Wenjie Shen, Yunzhen Jia, Yanping Wang, Yun Lin, Y. Li
Spaceborne SAR has the advantage of stable revisit period to obtain high-resolution images. For the long-time time-series images, the change information in the fixed area can be extracted by using the change detection technology. It is of great significance for environmental monitoring, disaster loss assessment and production capacity assessment. Most of the existing methods are aimed at large areas, and there are few target-level change detection methods. Therefore, this paper proposes a Log-Ratio (LR) operator based change detection method using spaceborne SAR time-series images to obtain the target-level change information. In this method, one of the time-series images in the sequence is taken as the reference image, and the change image is obtained by taking logarithm of the ratio of the input and reference image. Then, the CFAR algorithm is used to complete the detection on the change image. The proposed method is verified by the Sentinel1 dataset.
{"title":"Spaceborne SAR Time-Series Images Change Detection Based on Log-Ratio Operator","authors":"Wenjie Shen, Yunzhen Jia, Yanping Wang, Yun Lin, Y. Li","doi":"10.1109/CCET55412.2022.9906401","DOIUrl":"https://doi.org/10.1109/CCET55412.2022.9906401","url":null,"abstract":"Spaceborne SAR has the advantage of stable revisit period to obtain high-resolution images. For the long-time time-series images, the change information in the fixed area can be extracted by using the change detection technology. It is of great significance for environmental monitoring, disaster loss assessment and production capacity assessment. Most of the existing methods are aimed at large areas, and there are few target-level change detection methods. Therefore, this paper proposes a Log-Ratio (LR) operator based change detection method using spaceborne SAR time-series images to obtain the target-level change information. In this method, one of the time-series images in the sequence is taken as the reference image, and the change image is obtained by taking logarithm of the ratio of the input and reference image. Then, the CFAR algorithm is used to complete the detection on the change image. The proposed method is verified by the Sentinel1 dataset.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128907796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：