| 基于BP神经网络的数字调制识别方法 |
| |
| 引用本文： | 余嘉,陈印.基于BP神经网络的数字调制识别方法[J].传感器与微系统,2012,31(5):16-19. |
| |
| 作者姓名： | 余嘉 陈印 |
| |
| 作者单位： | 1. 重庆大学自动化学院,重庆40030
2. 重庆大学通信与测控中心,重庆,400030 |
| |
| 基金项目： | 中央高校基本科研业务费资助项目(CDJZR10160011);重庆市自然科学基金资助项目(2010BB2049) |
| |
| 摘 要： | 针对低信噪比条件下通信信号调制类型识别困难的问题,提出一种新的基于瞬时信息的数字调制识别方法。该方法采用改进的小波阈值消噪算法对信号的瞬时信息进行消噪处理,从而增大不同调制信号间特征值的差异,再采用弹性反向传播(RPROP)算法训练的BP神经网络对MASK,MFSK,MPSK,MQAM等7种调制信号进行分类识别。仿真结果表明:该算法在信噪比低至2dB时,能使所有调制信号均达到96%以上的正确识别率,极大地改善了低信噪比下的识别性能。
|
| 关 键 词： | 数字调制识别 瞬时信息 小波阈值消噪 神经网络 |
Digital modulation recognition method based on BP neural network |
| |
| YU Jia
,
CHEN Yin.Digital modulation recognition method based on BP neural network[J].Transducer and Microsystem Technology,2012,31(5):16-19. |
| |
| Authors: | YU Jia CHEN Yin |
| |
| Affiliation: | 1.School of Automation,Chongqing University,Chongqing 400030,China; 2.Center of Communication and Tracking Telemetering & Command,Chongqing University, Chongqing 400030,China) |
| |
| Abstract: | A new digital modulation recognition method based on instantaneous information is proposed for the application under low signal-to-noise ratio(SNR).An improved wavelet threshold de-noising algorithm is used for instantaneous information de-noising,which can improve recognition ability under low SNR.The method can identify and classify seven digital signals which are MASK,MFSK,MPSK and MQAM and so on,by using BP neural network with resilient backpropagation(RPROP) training algorithm as the classifier.The computer simulations show that the proposed algorithm effectively improves the practicability because of an overall success rate of 96 % at the SNR of 2 dB. |
| |
| Keywords: | digital modulation recognition instantaneous information wavelet threshold de-noising neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
