Pub Date : 2021-11-01DOI: 10.1109/ITME53901.2021.00044
Yunyang
This paper introduces the principle of BP Neural Network to achieve Training algorithm, which work with Hopfield neural network associative memory to achieve prediction fire in the semi-closed space of the community. The BP Neural Network is regarded as a nonlinear mapping from input to output. Based on the BP neural network algorithm by the software monitoring technology obtain the prediction model which predict the output value is closed to the real value The high effectiveness of Artificial Neural Network is verified by the comparison of specific field simulation. Once the fire happened, People can get fire of extinguishing materials in time by the color of the smoke and fire emitted to prevent the expansion of the fire. Consequently, the fire disasters can be predicted and prevented through the pattern of the fire model.
{"title":"Situation Prediction of Fire Management System Based on BP Neural Network","authors":"Yunyang","doi":"10.1109/ITME53901.2021.00044","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00044","url":null,"abstract":"This paper introduces the principle of BP Neural Network to achieve Training algorithm, which work with Hopfield neural network associative memory to achieve prediction fire in the semi-closed space of the community. The BP Neural Network is regarded as a nonlinear mapping from input to output. Based on the BP neural network algorithm by the software monitoring technology obtain the prediction model which predict the output value is closed to the real value The high effectiveness of Artificial Neural Network is verified by the comparison of specific field simulation. Once the fire happened, People can get fire of extinguishing materials in time by the color of the smoke and fire emitted to prevent the expansion of the fire. Consequently, the fire disasters can be predicted and prevented through the pattern of the fire model.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"21 4","pages":"174-179"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91551108","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00041
Yanhua Liu, Jiaqi Li, Baoxu Liu, Xiaoling Gao, Ximeng Liu
In this paper, we propose a malware identification method employed by image analysis and generative adversarial networks, designed to solve the problems of increasingly sophisticated attack forms, insufficient sample data in malware. Specifically, we first generate fixed-size gray images of malware, which neither disassembly nor code execution is required for identification. Moreover, we introduce generative adversarial networks into malware identification for few samples scenarios and malware variants. Through the game training of generator and discriminator, the malware detection model is obtained from the discriminator and the samples are generated by the generator for data augment. Finally, we demonstrate that the proposed method is efficient and feasible using extensive experiments.
{"title":"Malware Identification Method Based on Image Analysis","authors":"Yanhua Liu, Jiaqi Li, Baoxu Liu, Xiaoling Gao, Ximeng Liu","doi":"10.1109/ITME53901.2021.00041","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00041","url":null,"abstract":"In this paper, we propose a malware identification method employed by image analysis and generative adversarial networks, designed to solve the problems of increasingly sophisticated attack forms, insufficient sample data in malware. Specifically, we first generate fixed-size gray images of malware, which neither disassembly nor code execution is required for identification. Moreover, we introduce generative adversarial networks into malware identification for few samples scenarios and malware variants. Through the game training of generator and discriminator, the malware detection model is obtained from the discriminator and the samples are generated by the generator for data augment. Finally, we demonstrate that the proposed method is efficient and feasible using extensive experiments.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"73 1","pages":"157-161"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76551256","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00049
Jinming Cao, Oren Katzir, Peng Jiang, D. Lischinski, D. Cohen-Or, Changhe Tu, Yangyan Li
Unsupervised domain adaptation aims at learning a shared model for two related domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches rely on the ability to extract domain-invariant latent factors which are common to both domains. Extracting latent commonality is also useful for disentanglement analysis. It enables separation between the common and the domain-specific features of both domains, which can be recombined for synthesis. In this paper, we propose a strategy to boost the performance of domain adaptation and disentangled synthesis iteratively. The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance. Better common feature extraction, in turn, helps further improve the feature disentanglement and the following disentangled synthesis. We show that iterating between domain adaptation and disentangled synthesis can consistently improve each other on several unsupervised domain adaptation benchmark datasets and tasks, under various domain adaptation backbone models.
{"title":"DiDA: Iterative Boosting of Disentangled Synthesis and Domain Adaptation","authors":"Jinming Cao, Oren Katzir, Peng Jiang, D. Lischinski, D. Cohen-Or, Changhe Tu, Yangyan Li","doi":"10.1109/ITME53901.2021.00049","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00049","url":null,"abstract":"Unsupervised domain adaptation aims at learning a shared model for two related domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches rely on the ability to extract domain-invariant latent factors which are common to both domains. Extracting latent commonality is also useful for disentanglement analysis. It enables separation between the common and the domain-specific features of both domains, which can be recombined for synthesis. In this paper, we propose a strategy to boost the performance of domain adaptation and disentangled synthesis iteratively. The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance. Better common feature extraction, in turn, helps further improve the feature disentanglement and the following disentangled synthesis. We show that iterating between domain adaptation and disentangled synthesis can consistently improve each other on several unsupervised domain adaptation benchmark datasets and tasks, under various domain adaptation backbone models.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"29 1","pages":"201-208"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77000892","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00069
Wan Yuqian, Ma Jianwei, Zang Shaofei
In order to solve the existing problems of low segmentation precision and obvious interference by background noise in the segmentation task of rectal cancer lesions, we propose an improved U-Net method based on feature fusion by U-Net network and weighted feature pyramid structure (W - FPN). First, the proportion of each pixel value in the final pixel is used to assign weights to strengthen the feature fusion ability and improve the segmentation effect by using the scale information in the fusion. Secondly, after the third network output layer, three serial depthwise separable dilated convolution layers with dilation rates of 1, 2 and 4 are added to enlarge the receptive field of feature image and make full use of image feature information. Finally, the improved model is compared with U-Net, SegNet and DeepLab segmentation models. The experimental results show that Our approach reaches good and stable results with a precision of 83.38% and the Dice similarity coefficient value of 92.56%.
{"title":"U -Net based on Feature Fusion for Rectal Cancer Image Segmentation","authors":"Wan Yuqian, Ma Jianwei, Zang Shaofei","doi":"10.1109/ITME53901.2021.00069","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00069","url":null,"abstract":"In order to solve the existing problems of low segmentation precision and obvious interference by background noise in the segmentation task of rectal cancer lesions, we propose an improved U-Net method based on feature fusion by U-Net network and weighted feature pyramid structure (W - FPN). First, the proportion of each pixel value in the final pixel is used to assign weights to strengthen the feature fusion ability and improve the segmentation effect by using the scale information in the fusion. Secondly, after the third network output layer, three serial depthwise separable dilated convolution layers with dilation rates of 1, 2 and 4 are added to enlarge the receptive field of feature image and make full use of image feature information. Finally, the improved model is compared with U-Net, SegNet and DeepLab segmentation models. The experimental results show that Our approach reaches good and stable results with a precision of 83.38% and the Dice similarity coefficient value of 92.56%.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"26 1","pages":"302-306"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76907018","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00019
L. Zhen, Lin Guanjun, Li Shusheng, Wang Weibin, L. Xiaoming
At present, the big data industry is developing rapidly in many fields around the world, and it brings opportunities for the transformation and upgradation of the traditional oil industry. The whole oil business chain is of large scale, and there are urgent needs to apply big data technologies in the fields of petroleum exploration and development, transportation, refining and other fields. However, the oil big data industry is still in its infancy and has encountered many challenges, including oil data storage and management being not standardized, technical standards being not unified, and security concerns. These issues further lead to the poor data sharing, repeated business deployment within the enterprise and the compromised of the systems. To solve the problems above, this paper proposes the overall architecture for the development of the oil big data industry. The architecture scheme integrates all the data and business of the oil industry chain, which allows the secure data sharing, effective business management and scientific allocation of resources. Therefore, the oil big data solution can provide an important research idea for the dynamic management of production process and industrial business, which improves the overall productivity of oil industry.
{"title":"Research on the future development scheme of the oil big data industry","authors":"L. Zhen, Lin Guanjun, Li Shusheng, Wang Weibin, L. Xiaoming","doi":"10.1109/ITME53901.2021.00019","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00019","url":null,"abstract":"At present, the big data industry is developing rapidly in many fields around the world, and it brings opportunities for the transformation and upgradation of the traditional oil industry. The whole oil business chain is of large scale, and there are urgent needs to apply big data technologies in the fields of petroleum exploration and development, transportation, refining and other fields. However, the oil big data industry is still in its infancy and has encountered many challenges, including oil data storage and management being not standardized, technical standards being not unified, and security concerns. These issues further lead to the poor data sharing, repeated business deployment within the enterprise and the compromised of the systems. To solve the problems above, this paper proposes the overall architecture for the development of the oil big data industry. The architecture scheme integrates all the data and business of the oil industry chain, which allows the secure data sharing, effective business management and scientific allocation of resources. Therefore, the oil big data solution can provide an important research idea for the dynamic management of production process and industrial business, which improves the overall productivity of oil industry.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"13 1","pages":"42-46"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75587094","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00061
T. Zhou, Yun Cheng
Most of the localization algorithms can achieve extremely high positioning accuracy in line of sight (LOS) environment. However, they are unable to obtain ideal accuracy due to the obstacles in non-line of sight (NLOS) environment. In order to reduce the influence of NLOS on positioning accuracy in indoor environment, Fang algorithm, Chan algorithm and Taylor algorithm based on TDOA in UWB indoor positioning technology are analyzed and tested. Through comparative simulation analysis, it can be concluded that in the case of Gaussian noise, regardless of the number of base stations, Chan algorithm has the best performance, Taylor algorithm is the second, and Fang algorithm has the worst performance. When the number of base stations reaches a certain number, Chan algorithm and Taylor algorithm are not sensitive to the number of base stations, but they can use all TDOA information to obtain more accurate parameter solutions, and can also be adapted to different measurement environments.
{"title":"Positioning Algorithm of UWB based on TDOA Technology in Indoor Environment","authors":"T. Zhou, Yun Cheng","doi":"10.1109/ITME53901.2021.00061","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00061","url":null,"abstract":"Most of the localization algorithms can achieve extremely high positioning accuracy in line of sight (LOS) environment. However, they are unable to obtain ideal accuracy due to the obstacles in non-line of sight (NLOS) environment. In order to reduce the influence of NLOS on positioning accuracy in indoor environment, Fang algorithm, Chan algorithm and Taylor algorithm based on TDOA in UWB indoor positioning technology are analyzed and tested. Through comparative simulation analysis, it can be concluded that in the case of Gaussian noise, regardless of the number of base stations, Chan algorithm has the best performance, Taylor algorithm is the second, and Fang algorithm has the worst performance. When the number of base stations reaches a certain number, Chan algorithm and Taylor algorithm are not sensitive to the number of base stations, but they can use all TDOA information to obtain more accurate parameter solutions, and can also be adapted to different measurement environments.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"22 1","pages":"261-266"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83056357","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00067
Lei Xu, X. Hui, Peicheng Du, L. Du
Objective: To study the safety and effectiveness of panax notoginseng saponins (trade name: Xuesaitong) for patients with diabetic peripheral neuropathy. Methods: first, search the literature of randomized controlled trials clinical studies of all patients with diabetic peripheral neuropathy using panax notoginseng saponins or Xuesaitong through CNKI and Wanfang, and set the search time in order to establish the database until January 16, 2021, the documents include English and Chinese documents, and further screening will be carried out according to the inclusion criteria of the documents and the exclusion criteria of the documents, and then the basic information in the included documents and the total effective rate, obvious efficiency and the data on the incidence of adverse reactions was extracted into an Excel table. Finally, RevMan 5.3 software was used to meta-analyze the data to study the safety and effectiveness of panax notoginseng saponins in patients with diabetic peripheral neuropathy. Results: a total of 26 Chinese literatures of randomized controlled trials were included, but there were no English literatures. A total of 1804 patients with diabetic peripheral neuropathy were included. The results of meta-analysis showed that patients with diabetic peripheral neuropathy treated with Panax notoginseng saponins had a significant rate [OR=3.27, 95%CI (2.64, 4.05), Z=10.89, P<0.00001] and a total effective rate [OR=4.60, 95%] CI (3.63, 5.82), P<0.00001] was significantly higher than the control group. Conclusion: patients with diabetic peripheral neuropathy have a better therapeutic effect with total saponins of notoginseng.
{"title":"Meta-analysis of the curative effect of panax notoginseng saponins in the treatment of diabetic peripheral neuropathy","authors":"Lei Xu, X. Hui, Peicheng Du, L. Du","doi":"10.1109/ITME53901.2021.00067","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00067","url":null,"abstract":"Objective: To study the safety and effectiveness of panax notoginseng saponins (trade name: Xuesaitong) for patients with diabetic peripheral neuropathy. Methods: first, search the literature of randomized controlled trials clinical studies of all patients with diabetic peripheral neuropathy using panax notoginseng saponins or Xuesaitong through CNKI and Wanfang, and set the search time in order to establish the database until January 16, 2021, the documents include English and Chinese documents, and further screening will be carried out according to the inclusion criteria of the documents and the exclusion criteria of the documents, and then the basic information in the included documents and the total effective rate, obvious efficiency and the data on the incidence of adverse reactions was extracted into an Excel table. Finally, RevMan 5.3 software was used to meta-analyze the data to study the safety and effectiveness of panax notoginseng saponins in patients with diabetic peripheral neuropathy. Results: a total of 26 Chinese literatures of randomized controlled trials were included, but there were no English literatures. A total of 1804 patients with diabetic peripheral neuropathy were included. The results of meta-analysis showed that patients with diabetic peripheral neuropathy treated with Panax notoginseng saponins had a significant rate [OR=3.27, 95%CI (2.64, 4.05), Z=10.89, P<0.00001] and a total effective rate [OR=4.60, 95%] CI (3.63, 5.82), P<0.00001] was significantly higher than the control group. Conclusion: patients with diabetic peripheral neuropathy have a better therapeutic effect with total saponins of notoginseng.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"1 1","pages":"292-297"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87482711","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00025
Yuzhu Wang, Jianwei Ma, Jinfeng Lv, Zhaoyang Zhao
SiamRPN++ has achieved excellent performance on thermal infrared object tracking. However, it directly fuses multi-layer features using weighted summation, which has the problem of insufficient feature fusion. In this paper, we propose an adaptive feature fusion module. It can fuse the features of different layers by adaptively allocating channel weights. Meanwhile, CIoU loss is used to make the regression of the bounding box more accurate. Experimental results show that the proposed method improves the baseline algorithm effectively and achieves excellent tracking accuracy and efficiency. The proposed method has strong robustness, effectively dealing with some challenges such as interference and occlusion. Therefore, the proposed method is valuable in practical application.
{"title":"Thermal Infrared Object Tracking Based on Adaptive Feature Fusion","authors":"Yuzhu Wang, Jianwei Ma, Jinfeng Lv, Zhaoyang Zhao","doi":"10.1109/ITME53901.2021.00025","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00025","url":null,"abstract":"SiamRPN++ has achieved excellent performance on thermal infrared object tracking. However, it directly fuses multi-layer features using weighted summation, which has the problem of insufficient feature fusion. In this paper, we propose an adaptive feature fusion module. It can fuse the features of different layers by adaptively allocating channel weights. Meanwhile, CIoU loss is used to make the regression of the bounding box more accurate. Experimental results show that the proposed method improves the baseline algorithm effectively and achieves excellent tracking accuracy and efficiency. The proposed method has strong robustness, effectively dealing with some challenges such as interference and occlusion. Therefore, the proposed method is valuable in practical application.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"6 1","pages":"71-75"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87501055","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00105
Yiming Jia, Fu Xie, Sen Wang
NAO,as a new type of robot, has gradually attracted the attention of the industry. The use of NAO robots in education, especially the introduction of NAO robots into the classroom, has attracted the attention of an increasing number of researchers. First of all, this research briefly introduces the research status and development trend of robot-assisted teaching. Secondly, this research elaborates the design of teaching activities based on the teaching content of “C Programming Fundamentals” in secondary vocational schools, with the help of robot-assisted teaching. Finally, we hope that this study can provide a practical and experimental approach for assisted instruction, and also can promote the application of artificial intelligence technology in classroom teaching.
{"title":"The application of NAO robots in the course of “C language programming foundation” in secondary vocational schools","authors":"Yiming Jia, Fu Xie, Sen Wang","doi":"10.1109/ITME53901.2021.00105","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00105","url":null,"abstract":"NAO,as a new type of robot, has gradually attracted the attention of the industry. The use of NAO robots in education, especially the introduction of NAO robots into the classroom, has attracted the attention of an increasing number of researchers. First of all, this research briefly introduces the research status and development trend of robot-assisted teaching. Secondly, this research elaborates the design of teaching activities based on the teaching content of “C Programming Fundamentals” in secondary vocational schools, with the help of robot-assisted teaching. Finally, we hope that this study can provide a practical and experimental approach for assisted instruction, and also can promote the application of artificial intelligence technology in classroom teaching.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"37 1","pages":"495-499"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85458564","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 : 2021-11-01DOI: 10.1109/ITME53901.2021.00013
Ling Jiang, Yi Jiang, Guimin Shi, Zhongjie Xiao
In order to overcome the premarure risk of differential evolution algorithm, harmony search mechanism is introduced to optimize the pattern synthesis of multiple input and multiple output radar. Firstly, the memory of harmony search receives the optimizing results of differential evolution algorithm. And then it disturbs the local best to achieve better global optimization results. The advantage of novel method than standard differential evolution is tested with benchmark function while it can also maintain the diversity of population. What's more, several experiments are conducted to show that the optimal peak side lobe level and convergence performance have been achieved better through the proposed algorithm for multiple input and multiple output radar.
{"title":"Array optimization for MIMO radar based on harmony search mechanism","authors":"Ling Jiang, Yi Jiang, Guimin Shi, Zhongjie Xiao","doi":"10.1109/ITME53901.2021.00013","DOIUrl":"https://doi.org/10.1109/ITME53901.2021.00013","url":null,"abstract":"In order to overcome the premarure risk of differential evolution algorithm, harmony search mechanism is introduced to optimize the pattern synthesis of multiple input and multiple output radar. Firstly, the memory of harmony search receives the optimizing results of differential evolution algorithm. And then it disturbs the local best to achieve better global optimization results. The advantage of novel method than standard differential evolution is tested with benchmark function while it can also maintain the diversity of population. What's more, several experiments are conducted to show that the optimal peak side lobe level and convergence performance have been achieved better through the proposed algorithm for multiple input and multiple output radar.","PeriodicalId":6774,"journal":{"name":"2021 11th International Conference on Information Technology in Medicine and Education (ITME)","volume":"12 1","pages":"13-16"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85872252","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：