{"title":"基于小波变换结合奇异值和NCA-CNN的通信信号调制自动识别","authors":"Yixin Ding","doi":"10.1109/WOCC58016.2023.10139354","DOIUrl":null,"url":null,"abstract":"In communication signal recognition, there are problems such as a tedious feature extraction process and low applicability of extracted features. This paper simulates wireless communication channels and suggests an algorithm that uses nearest neighbor component analysis (NCA) along with convolutional neural networks (CNN) for classification. The algorithm chooses wavelet entropy (WE), wavelet approximate energy ratio (WAER), and the first 2–4 singular values as the core features. Eight different forms of modulations, including GFSK, CPFSK, B-FM, DSB-AM, SSB-AM, BPSK, QPSK and PAM4 would be automatically classified using the technique. According to the experiment results, the average recognition accuracy for the eight signals is 93.6% when the signal-to-noise ratio is 30dB. In addition, this paper also discusses the results and accuracy of the model to identify 6 and 10 types of signal modulation and studies the accuracy of the recognition under different signal-to-noise ratios, verifying the robustness of the model.","PeriodicalId":226792,"journal":{"name":"2023 32nd Wireless and Optical Communications Conference (WOCC)","volume":"34 5","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic modulation recognition of communication signal based on wavelet transform combined with singular value and NCA-CNN\",\"authors\":\"Yixin Ding\",\"doi\":\"10.1109/WOCC58016.2023.10139354\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In communication signal recognition, there are problems such as a tedious feature extraction process and low applicability of extracted features. This paper simulates wireless communication channels and suggests an algorithm that uses nearest neighbor component analysis (NCA) along with convolutional neural networks (CNN) for classification. The algorithm chooses wavelet entropy (WE), wavelet approximate energy ratio (WAER), and the first 2–4 singular values as the core features. Eight different forms of modulations, including GFSK, CPFSK, B-FM, DSB-AM, SSB-AM, BPSK, QPSK and PAM4 would be automatically classified using the technique. According to the experiment results, the average recognition accuracy for the eight signals is 93.6% when the signal-to-noise ratio is 30dB. In addition, this paper also discusses the results and accuracy of the model to identify 6 and 10 types of signal modulation and studies the accuracy of the recognition under different signal-to-noise ratios, verifying the robustness of the model.\",\"PeriodicalId\":226792,\"journal\":{\"name\":\"2023 32nd Wireless and Optical Communications Conference (WOCC)\",\"volume\":\"34 5\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 32nd Wireless and Optical Communications Conference (WOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WOCC58016.2023.10139354\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 32nd Wireless and Optical Communications Conference (WOCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WOCC58016.2023.10139354","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Automatic modulation recognition of communication signal based on wavelet transform combined with singular value and NCA-CNN
In communication signal recognition, there are problems such as a tedious feature extraction process and low applicability of extracted features. This paper simulates wireless communication channels and suggests an algorithm that uses nearest neighbor component analysis (NCA) along with convolutional neural networks (CNN) for classification. The algorithm chooses wavelet entropy (WE), wavelet approximate energy ratio (WAER), and the first 2–4 singular values as the core features. Eight different forms of modulations, including GFSK, CPFSK, B-FM, DSB-AM, SSB-AM, BPSK, QPSK and PAM4 would be automatically classified using the technique. According to the experiment results, the average recognition accuracy for the eight signals is 93.6% when the signal-to-noise ratio is 30dB. In addition, this paper also discusses the results and accuracy of the model to identify 6 and 10 types of signal modulation and studies the accuracy of the recognition under different signal-to-noise ratios, verifying the robustness of the model.