现代电子技术2018，Vol.41Issue(3)：1-5,5.DOI:10.16652/j.issn.1004-373x.2018.03.001
基于softmax回归的通信信号循环谱的多分类识别方法
Softmax regression based multi-classification recognition method of communication signal cyclic spectrum
摘要
Abstract
The automatic identification of communication signal modulation mode has important application in the field of communication countermeasures,and is an important component of the future cognitive radio system,so how to quickly and ac-curately recognize the multiple mixed communication signals in the increasingly-intensive signal environment is the key to realize the automatic identification of communication signal modulation mode. By taking the cyclic spectrum of the digital communica-tion signals as the feature,and building the softmax regression multi-classification recognizer,a ssoftmax regression based multi-classification recognition method of communication signal cyclic spectrum is put forward. The algorithm performance was verified with computer under different conditions,which proves that the method needn′t know the symbol rate,carrier frequency,syn-chronization timing and priori information of the typical digital modulation signals(such as ASK,BPSK,QPSK,16 QAM and 64 QAM). The mixed signals can identify the modulation mode including each modulation signal correctly,and has fast identifi-cation speed.关键词
softmax/多分类识别/循环谱/调制方式识别/神经网络/电子对抗Key words
softmax/multi-classification recognition/cyclic spectrum/modulation mode recognition/neural network/elec-tronic countermeasure分类
信息技术与安全科学引用本文复制引用
刘亚冲,唐智灵..基于softmax回归的通信信号循环谱的多分类识别方法[J].现代电子技术,2018,41(3):1-5,5.基金项目
国家自然科学基金(61461013) （61461013）
广西自动检测技术与仪器重点实验室主任基金(YQ15115) （YQ15115）
桂林电子科技大学创新团队"广西无线宽带通信与信号处理重点实验室"2016年主任基金项目(GXKL06160103) Project Supported by National Natural Science Foundation of China (61461013),Guangxi Automatic Detection Technology and Instrument Key Laboratory Director Foundation (YQ15115),Guilin University of Electronic Technology Innovation Team "Guangxi Wireless Broadband Commu-nications and Signal Processing Laboratory" 2016 Fund Project (GXKL06160103) （GXKL06160103）
