Pub Date : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00091
Yihan Wang
The drum water level is a very important operating parameter of a drum boiler, and it is also a sign of whether the boiler steam system is balanced. Maintaining the water level of the steam drum within a certain allowable range is a necessary condition to ensure the safe operation of boilers and steam turbines. Excessive water levels will affect the normal operation of the steam separator, and the steam quality will deteriorate. When the superheater tube wall and the steam turbine blade become fouled seriously, it will cause the steam to carry water and cause the steam turbine water impact to damage the equipment. If the water level is too low, the water circulation will be destroyed, and in severe cases, the water wall pipe will be deformed and burst. Therefore, the water level control of the steam drum has always received great attention. For the control of the water level of the steam drum, the motivation is to adapt the boiler water supply to the boiler's evaporation capacity, maintain the steam drum water level within the specified range, and at the same time maintain a stable water supply flow.
{"title":"Design and Realization of Drum Level Control System for 300MW Unit","authors":"Yihan Wang","doi":"10.1109/ISCEIC53685.2021.00091","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00091","url":null,"abstract":"The drum water level is a very important operating parameter of a drum boiler, and it is also a sign of whether the boiler steam system is balanced. Maintaining the water level of the steam drum within a certain allowable range is a necessary condition to ensure the safe operation of boilers and steam turbines. Excessive water levels will affect the normal operation of the steam separator, and the steam quality will deteriorate. When the superheater tube wall and the steam turbine blade become fouled seriously, it will cause the steam to carry water and cause the steam turbine water impact to damage the equipment. If the water level is too low, the water circulation will be destroyed, and in severe cases, the water wall pipe will be deformed and burst. Therefore, the water level control of the steam drum has always received great attention. For the control of the water level of the steam drum, the motivation is to adapt the boiler water supply to the boiler's evaporation capacity, maintain the steam drum water level within the specified range, and at the same time maintain a stable water supply flow.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114546055","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00062
Hangyu Li, Han Wu, Zhilong Zhang, Chuwei Li
Obtaining the accurate position and attitude of the object is the key to realize rendezvous and docking, on-orbit maintenance and other related tasks of space spacecraft. However, for non-cooperative objects, they lack prearranged cooperation sign, which would make it much more difficult to estimate their pose. Therefore, this paper attempts to use the powerful feature learning ability of neural network to establish the mapping relationship between the object in image and its current pose, then regresses the pose parameters of the object from a monocular image. Finally, we tested and verified the network on the public satellite dataset called Speed. The results showed that the translation error was 0.1237 and the rotation error was 0.1335.
{"title":"Pose estimation for monocular image object using convolution neural network","authors":"Hangyu Li, Han Wu, Zhilong Zhang, Chuwei Li","doi":"10.1109/ISCEIC53685.2021.00062","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00062","url":null,"abstract":"Obtaining the accurate position and attitude of the object is the key to realize rendezvous and docking, on-orbit maintenance and other related tasks of space spacecraft. However, for non-cooperative objects, they lack prearranged cooperation sign, which would make it much more difficult to estimate their pose. Therefore, this paper attempts to use the powerful feature learning ability of neural network to establish the mapping relationship between the object in image and its current pose, then regresses the pose parameters of the object from a monocular image. Finally, we tested and verified the network on the public satellite dataset called Speed. The results showed that the translation error was 0.1237 and the rotation error was 0.1335.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"SPEC Suppl 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129840951","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00063
Hang Zou, Yan Zhang, Yin Zhang, Xian Jiang, Ligang Dong
The existing video-oriented person tracking and re- recognition research are all based on face recognition, which cannot meet the requirements of high continuity and high accuracy. In order to solve this problem, this paper propose a tracking and re-identification scheme based on KM (Kuhn- Munkras) algorithm. When tracking a person, this scheme establishes the connection between the face image observed in real time, the face database, and the human body image observed in real time to determine their identity. During tracking person, the appearance characteristics can be captured all the time, and the recognition of person has high real-time performance and high continuity. In the tracking process, a real-time updated person information cache list is established to realize the re- identification function after the person tracking is interrupted for a long time.
{"title":"Real-time Person Tracking and Re-identification Based on Feature Matching","authors":"Hang Zou, Yan Zhang, Yin Zhang, Xian Jiang, Ligang Dong","doi":"10.1109/ISCEIC53685.2021.00063","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00063","url":null,"abstract":"The existing video-oriented person tracking and re- recognition research are all based on face recognition, which cannot meet the requirements of high continuity and high accuracy. In order to solve this problem, this paper propose a tracking and re-identification scheme based on KM (Kuhn- Munkras) algorithm. When tracking a person, this scheme establishes the connection between the face image observed in real time, the face database, and the human body image observed in real time to determine their identity. During tracking person, the appearance characteristics can be captured all the time, and the recognition of person has high real-time performance and high continuity. In the tracking process, a real-time updated person information cache list is established to realize the re- identification function after the person tracking is interrupted for a long time.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127032774","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00021
Zhenwei Zhang, Wenyan Wu, Dongjie Wu
With the rapid development of new technologies such as artificial intelligence, big data, and the Internet of Things, many researchers have probed into the study of learning analysis, trying to solve the problems of teaching by analyzing the learning behavior data from learning process. And in many learning behavior research, the sensor network usually consists of a host of mutually independent data sources, which can be used to monitor measured objects from multiple dimensions thereby obtaining the multi-source multi-modal sensory data. However, there still exist false negative readings, false positive readings and environmental interference, etc. Therefore, we propose a multi-source multimode sensory data acquisition method based on Date Quality(DQ). We first define the data quality in terms of four aspects-accuracy, integrity, consistency and instantaneity. Then, by the modeling there aspects respectively, we propose metrics to estimate the comprehensive data quality method of multi-source multi-mode sensory data. Finally, a data acquisition method is presented based on data quality, which selects a part of data sources for data transmission according to the given precision. This method aims at reducing the consumption of the sensory network on the premise of the data quality guarantee. An extensive experimental evaluation demonstrates the efficiency and effectiveness of the algorithm.
{"title":"A Multi-Mode Learning Behavior Real-time Data Acquisition Method Based on Data Quality","authors":"Zhenwei Zhang, Wenyan Wu, Dongjie Wu","doi":"10.1109/ISCEIC53685.2021.00021","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00021","url":null,"abstract":"With the rapid development of new technologies such as artificial intelligence, big data, and the Internet of Things, many researchers have probed into the study of learning analysis, trying to solve the problems of teaching by analyzing the learning behavior data from learning process. And in many learning behavior research, the sensor network usually consists of a host of mutually independent data sources, which can be used to monitor measured objects from multiple dimensions thereby obtaining the multi-source multi-modal sensory data. However, there still exist false negative readings, false positive readings and environmental interference, etc. Therefore, we propose a multi-source multimode sensory data acquisition method based on Date Quality(DQ). We first define the data quality in terms of four aspects-accuracy, integrity, consistency and instantaneity. Then, by the modeling there aspects respectively, we propose metrics to estimate the comprehensive data quality method of multi-source multi-mode sensory data. Finally, a data acquisition method is presented based on data quality, which selects a part of data sources for data transmission according to the given precision. This method aims at reducing the consumption of the sensory network on the premise of the data quality guarantee. An extensive experimental evaluation demonstrates the efficiency and effectiveness of the algorithm.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125408058","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00025
Zhou Yang, Haibin Liu, R. Xie
Path planning is a key technology in the research of Automatic Guided Vehicle (AGV). To solve the problem that the traditional Ant Colony Optimization (ACO) algorithm has poor convergence, low search efficiency, and easy to fall into the local optimality problems in AGV path planning, some improved methods are proposed in this paper. Through initial pheromones non-uniform and directed distribution to determine the search direction in the early stage, the search efficiency and convergence speed of the algorithm is improved. By adding the adaptive adjustment strategy of the iterations number, the computation amount and time complexity of the algorithm are greatly reduced. The parameters of ACO have an important influence on the convergence and the optimization effect, but there are no scientific bases to decide the values. To solve the above problem the improved ACO parameters are optimized by using the genetic algorithm (GA) which has good global search ability and easy fusion with other algorithms to find the parameters combination for the best performance of ACO. Simulation experiments in different environments show that the improved ACO has a better optimization effect and higher search efficiency compared with the traditional ACO.
{"title":"Improved Ant Colony Algorithm Based on Parameters Optimization for AGV Path Planning","authors":"Zhou Yang, Haibin Liu, R. Xie","doi":"10.1109/ISCEIC53685.2021.00025","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00025","url":null,"abstract":"Path planning is a key technology in the research of Automatic Guided Vehicle (AGV). To solve the problem that the traditional Ant Colony Optimization (ACO) algorithm has poor convergence, low search efficiency, and easy to fall into the local optimality problems in AGV path planning, some improved methods are proposed in this paper. Through initial pheromones non-uniform and directed distribution to determine the search direction in the early stage, the search efficiency and convergence speed of the algorithm is improved. By adding the adaptive adjustment strategy of the iterations number, the computation amount and time complexity of the algorithm are greatly reduced. The parameters of ACO have an important influence on the convergence and the optimization effect, but there are no scientific bases to decide the values. To solve the above problem the improved ACO parameters are optimized by using the genetic algorithm (GA) which has good global search ability and easy fusion with other algorithms to find the parameters combination for the best performance of ACO. Simulation experiments in different environments show that the improved ACO has a better optimization effect and higher search efficiency compared with the traditional ACO.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126744793","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00090
Kaili Feng, Tonghe Ding, Tianping Li, Jiayu Ou
In the era of rapid development of artificial intelligence technology, image denoising methods based on deep learning have achieved better and better results, and some deeper networks have also been proposed. However, with the increasing number of network layers, gradient explosion and over fitting problems also appear in the training process. In this paper, a new Gaussian image denoising method based on dual channel deep neural network with skip connection is proposed. The network is composed by the first layer network and the second layer network in parallel, so as to widen the width of the network. It not only improves the denoising effect, but also reduces the problems in the training process. The first layer uses dilated convolution to expand the receptive field of the network, and the second layer is composed of skip connection modules. The method is tested on the data set68 and achieves good results.
{"title":"Gaussian Image Denoising Method Based on the Dual Channel Deep Neural Network with the Skip Connection","authors":"Kaili Feng, Tonghe Ding, Tianping Li, Jiayu Ou","doi":"10.1109/ISCEIC53685.2021.00090","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00090","url":null,"abstract":"In the era of rapid development of artificial intelligence technology, image denoising methods based on deep learning have achieved better and better results, and some deeper networks have also been proposed. However, with the increasing number of network layers, gradient explosion and over fitting problems also appear in the training process. In this paper, a new Gaussian image denoising method based on dual channel deep neural network with skip connection is proposed. The network is composed by the first layer network and the second layer network in parallel, so as to widen the width of the network. It not only improves the denoising effect, but also reduces the problems in the training process. The first layer uses dilated convolution to expand the receptive field of the network, and the second layer is composed of skip connection modules. The method is tested on the data set68 and achieves good results.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114208958","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}
Aiming at the fault repair problem of a non-source-code software with QNX operating system,a repair method of discrete global control logic into collaborative sub-logic is proposed. The location of the fault repair was precisely locatedby using software reverse analysis, and the minimal repair scope was isolated. The result of test shown that the software fault repair is accurate and the repaired software runs stably and reliably.
{"title":"Research on a Fault Repair Method for Control Logic of Non-Source-Code Software","authors":"Ping Hu, Xue-Xia Liu, Xue-Feng Gu, Hao Chen, Kai Liu, Chao Zhang","doi":"10.1109/ISCEIC53685.2021.00066","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00066","url":null,"abstract":"Aiming at the fault repair problem of a non-source-code software with QNX operating system,a repair method of discrete global control logic into collaborative sub-logic is proposed. The location of the fault repair was precisely locatedby using software reverse analysis, and the minimal repair scope was isolated. The result of test shown that the software fault repair is accurate and the repaired software runs stably and reliably.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124885382","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00042
Fei Liu, Niansong Zhang, Aiming Wang, Yue Ding, Y. Cao, Liling Liu
In aviation, aerospace and military products, thin-walled parts are widely used for their excellent characteristics. Some key complex parts include thin-walled and special-shaped features, which require high precision. However, due to the low stiffness of thin-walled parts, it is easy to produce machining deformation due to cutting force during processing. Aimed at the difficulty of measuring parts milling deformation, this paper proposes a thin-walled parts processing deformation prediction method based on neural network, designed by the method of orthogonal test, the test program for different milling parameters under the condition of the milling test, test data as the training sample is established based on BP neural network and milling parameters of milling deformation forecast model. Finally, genetic algorithm is used to optimize the initial weight and threshold value of BP neural network to overcome the disadvantages of slow convergence rate and easy to fall into local minimum value .The performance of the neural network model is improved.
{"title":"Deformation prediction of thin-walled parts based on BP neural network","authors":"Fei Liu, Niansong Zhang, Aiming Wang, Yue Ding, Y. Cao, Liling Liu","doi":"10.1109/ISCEIC53685.2021.00042","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00042","url":null,"abstract":"In aviation, aerospace and military products, thin-walled parts are widely used for their excellent characteristics. Some key complex parts include thin-walled and special-shaped features, which require high precision. However, due to the low stiffness of thin-walled parts, it is easy to produce machining deformation due to cutting force during processing. Aimed at the difficulty of measuring parts milling deformation, this paper proposes a thin-walled parts processing deformation prediction method based on neural network, designed by the method of orthogonal test, the test program for different milling parameters under the condition of the milling test, test data as the training sample is established based on BP neural network and milling parameters of milling deformation forecast model. Finally, genetic algorithm is used to optimize the initial weight and threshold value of BP neural network to overcome the disadvantages of slow convergence rate and easy to fall into local minimum value .The performance of the neural network model is improved.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122654693","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00038
Yuelin Chen, ZhuCheng Gao, XiaoDong Cai
A method with data to text generation based on selecting encoding and fusing semantic loss is proposed in this paper. By highlighting key content and reducing the redundancy of text description information, the quality of the generated text is significantly improved. First, a new selection network is designed, which uses the amount of information related to data records as the coding basis for content importance, and multiple rounds of dynamic iterations of the results to achieve accurate and comprehensive selection of important information. Secondly, in the decoding process using Long Short-Term Memory (LSTM), a hierarchical attention mechanism is designed to assign dynamic selection weights to different entities and their attributes in the hidden layer output to obtain the best generated text Recall rate. Finally, a method of calculating the semantic similarity loss between the generated text and the reference text is introduced. By calculating the cosine distance of the semantic vectors of the two and iteratively feedback to the training process to obtain the optimization of key features, while reducing the redundancy of description information and improving the model BLEU performance. The experimental results show that the test Precision rate, Recall rate and BLEU is up to 94.58%, 53.72% and 17.24, which are better than existing models.
{"title":"Method with Data to Text Generation Based on Selecting Encoding and Fusing Semantic Loss","authors":"Yuelin Chen, ZhuCheng Gao, XiaoDong Cai","doi":"10.1109/ISCEIC53685.2021.00038","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00038","url":null,"abstract":"A method with data to text generation based on selecting encoding and fusing semantic loss is proposed in this paper. By highlighting key content and reducing the redundancy of text description information, the quality of the generated text is significantly improved. First, a new selection network is designed, which uses the amount of information related to data records as the coding basis for content importance, and multiple rounds of dynamic iterations of the results to achieve accurate and comprehensive selection of important information. Secondly, in the decoding process using Long Short-Term Memory (LSTM), a hierarchical attention mechanism is designed to assign dynamic selection weights to different entities and their attributes in the hidden layer output to obtain the best generated text Recall rate. Finally, a method of calculating the semantic similarity loss between the generated text and the reference text is introduced. By calculating the cosine distance of the semantic vectors of the two and iteratively feedback to the training process to obtain the optimization of key features, while reducing the redundancy of description information and improving the model BLEU performance. The experimental results show that the test Precision rate, Recall rate and BLEU is up to 94.58%, 53.72% and 17.24, which are better than existing models.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131171655","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 : 2021-08-01DOI: 10.1109/ISCEIC53685.2021.00049
Qiuyue Yin, Jinwang Yi, Jun Tang, Qin Zhu
In traditional airborne multiple-input multiple-output (MIMO) radar, high correlation of dictionary atoms usually degrades the performance of orthogonal matching pursuit (OMP) algorithm in sparse recovery space-time adaptive processing (SR-STAP). An OMP algorithm based on reduced-dimension dictionary is developed to solve this problem. It divides the dictionary along the clutter ridge and vertical direction of ridge, and eliminates atoms with high correlation by the prior knowledge. The experimental results indicate that the proposed method fully covers the clutter ridge, thus, the performance of clutter spectrum and signal-to-interference-plus-noise-ratio (SINR) are improved under these limitations of high correlation.
{"title":"A novel orthogonal matching pursuit algorithm based on reduced-dimension dictionary for airborne MIMO radar","authors":"Qiuyue Yin, Jinwang Yi, Jun Tang, Qin Zhu","doi":"10.1109/ISCEIC53685.2021.00049","DOIUrl":"https://doi.org/10.1109/ISCEIC53685.2021.00049","url":null,"abstract":"In traditional airborne multiple-input multiple-output (MIMO) radar, high correlation of dictionary atoms usually degrades the performance of orthogonal matching pursuit (OMP) algorithm in sparse recovery space-time adaptive processing (SR-STAP). An OMP algorithm based on reduced-dimension dictionary is developed to solve this problem. It divides the dictionary along the clutter ridge and vertical direction of ridge, and eliminates atoms with high correlation by the prior knowledge. The experimental results indicate that the proposed method fully covers the clutter ridge, thus, the performance of clutter spectrum and signal-to-interference-plus-noise-ratio (SINR) are improved under these limitations of high correlation.","PeriodicalId":342968,"journal":{"name":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications (ISCEIC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133695583","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：