摘要
在无线通信系统中,信号调制方式的自动识别是软件无线电的重要应用场景。与传统神经网络算法相比,基于软件无线电平台提出利用支持向量机进行识别的方法,能显著提高信号模拟和数字调制方式的识别效率,平均识别正确率均在90%以上。在接收信号信噪比为30 dB时,该方法的识别正确率达到100%,是调制信号自识别系统中的一种优秀方法。
In wireless communication system,automatic identification of signal modulation mode is an important application scenario of software radio.Compared with the traditional neural network algorithm,this paper proposes a recognition method based on software radio platform using support vector machine,which can significantly improve the recognition efficiency of signal analog and digital modulation,and the average recognition accuracy is above 90%.When the signal-to-noise ratio of the received signal is 30 dB,the recognition accuracy of this method reaches 100%,which is an excellent method in the modulation signal self-recognition system.
作者
黎鹏
陈心嘉
马诗扬
袁能
丁洪伟
LI Peng;CHEN Xinjia;MA Shiyang;YUAN Neng;DING Hongwei(School of Information Science,Yunnan University,Kunming 650091,China;School of Internet+,Dianchi College of Yunnan University,Kunming 650228,China;PetroChina Yunnan Company,Kunming 650328,China)
出处
《电声技术》
2024年第3期129-134,共6页
Audio Engineering
基金
云南省本科教育教学改革项目(JG2023178)
云南大学校级教育教学改革项目(2022026)。
