{"title":"相同频率电磁辐射源的分离方法","authors":"Yingchun Xiao, Yang Yang, Feng Zhu","doi":"10.26866/jees.2023.6.r.197","DOIUrl":null,"url":null,"abstract":"To separate electromagnetic interference sources with an unknown source number, a new separation method is proposed, which includes five key steps: spatial spectrum estimation, source number and direction-of-arrival estimation, mixed matrix estimation, separation matrix estimation, and source signal recovery. A pseudospatial spectrum estimation network based on a convolutional neural network is proposed to estimate the number of electromagnetic radiation sources, their direction of arrival, and the mixing matrix. A new loss function is designed as an optimization criterion for estimating the separation matrix. To ensure generalization, both simulated and measured datasets are used to train the proposed network. Experimental results demonstrate that the proposed separation method outperforms existing source separation techniques in terms of correlation coefficient, root mean square error, and running time. Importantly, it exhibits strong performance in underdetermined cases, as well as in overdetermined or determined cases.","PeriodicalId":15662,"journal":{"name":"Journal of electromagnetic engineering and science","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Separation Method for Electromagnetic Radiation Sources of the Same Frequency\",\"authors\":\"Yingchun Xiao, Yang Yang, Feng Zhu\",\"doi\":\"10.26866/jees.2023.6.r.197\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To separate electromagnetic interference sources with an unknown source number, a new separation method is proposed, which includes five key steps: spatial spectrum estimation, source number and direction-of-arrival estimation, mixed matrix estimation, separation matrix estimation, and source signal recovery. A pseudospatial spectrum estimation network based on a convolutional neural network is proposed to estimate the number of electromagnetic radiation sources, their direction of arrival, and the mixing matrix. A new loss function is designed as an optimization criterion for estimating the separation matrix. To ensure generalization, both simulated and measured datasets are used to train the proposed network. Experimental results demonstrate that the proposed separation method outperforms existing source separation techniques in terms of correlation coefficient, root mean square error, and running time. Importantly, it exhibits strong performance in underdetermined cases, as well as in overdetermined or determined cases.\",\"PeriodicalId\":15662,\"journal\":{\"name\":\"Journal of electromagnetic engineering and science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2023-11-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of electromagnetic engineering and science\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.26866/jees.2023.6.r.197\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of electromagnetic engineering and science","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.26866/jees.2023.6.r.197","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
A Separation Method for Electromagnetic Radiation Sources of the Same Frequency
To separate electromagnetic interference sources with an unknown source number, a new separation method is proposed, which includes five key steps: spatial spectrum estimation, source number and direction-of-arrival estimation, mixed matrix estimation, separation matrix estimation, and source signal recovery. A pseudospatial spectrum estimation network based on a convolutional neural network is proposed to estimate the number of electromagnetic radiation sources, their direction of arrival, and the mixing matrix. A new loss function is designed as an optimization criterion for estimating the separation matrix. To ensure generalization, both simulated and measured datasets are used to train the proposed network. Experimental results demonstrate that the proposed separation method outperforms existing source separation techniques in terms of correlation coefficient, root mean square error, and running time. Importantly, it exhibits strong performance in underdetermined cases, as well as in overdetermined or determined cases.
期刊介绍:
The Journal of Electromagnetic Engineering and Science (JEES) is an official English-language journal of the Korean Institute of Electromagnetic and Science (KIEES). This journal was launched in 2001 and has been published quarterly since 2003. It is currently registered with the National Research Foundation of Korea and also indexed in Scopus, CrossRef and EBSCO, DOI/Crossref, Google Scholar and Web of Science Core Collection as Emerging Sources Citation Index(ESCI) Journal. The objective of JEES is to publish academic as well as industrial research results and discoveries in electromagnetic engineering and science. The particular scope of the journal includes electromagnetic field theory and its applications: High frequency components, circuits, and systems, Antennas, smart phones, and radars, Electromagnetic wave environments, Relevant industrial developments.