一种小波特征与深度神经网络结合的信号制式识别算法

计算机工程与科学

一种小波特征与深度神经网络结合的信号制式识别算法

唐作栋，龚晓峰，雒瑞森

（四川大学电气工程学院，四川成都 610065)

收稿日期:2019-10-21 修回日期:2019-11-27 出版日期:2020-05-25 发布日期:2020-05-25
基金资助:
校企合作项目（17H1199，19H0355）

A signal modulation recognition method based

on wavelet feature and depth neural network

TANG Zuo-dong,GONG Xiao-feng,LUO Rui-sen

(College of Electrical Engineering,Sichuan University,Chengdu 610065,China)

Received:2019-10-21 Revised:2019-11-27 Online:2020-05-25 Published:2020-05-25

摘要/Abstract

摘要：

针对当前通信信号的制式识别算法在低信噪比情况下识别不准确的问题，提出一种新的小波特征与改进的深度神经网络结合（WL-DNN）的识别算法。该算法将生成的10种｛2ASK、4ASK、2PSK、4PSK、2FSK、4FSK、OFDM、16QAM、AM、FM｝含有高斯白噪声的通信信号，用小波分解重构算法提取出一类新的小波特征参数。本文测试了含有多层隐含层的改进BP神经网络作为分类器，利用弹性反向传播算法训练神经网络的参数，确定神经网络的最优超参数。仿真结果表明：在信噪比低至0 dB的情况下，单个调制信号最低识别率超过95%，平均识别率超过98%，大幅提高了制式识别在低信噪比下的识别率，由此表明了该算法的有效性和正确性。

关键词: 小波特征, 深度神经网络, 弹性反向传播, 制式识别

Abstract:

Aiming at the problem of inaccurate recognition of current communication signals in low signal-to-noise ratio (SNR), a recognition algorithm combining wavelet feature and depth neural network is proposed. This method generates 10 kinds of common communication signals with Gauss white noise{MASK, MPSK, MFSK, OFDM, 16QAM, AM, FM}. A new kind of wavelet characteristic parameters are extracted from the signals by using the wavelet decomposition and reconstruction algorithm. The improved BP neural network with plenty hidden layers is studied and tested as classifier. The parameters of the neural network are trained by the elastic back propagation algorithm. The optimal layers of the neural network are determined by the identification results. The simulation results show that the minimum recognition rate of single modulated signals is more than 95% and the average recognition rate is more than 98%, when the signal-to-noise ratio is as low as 0 dB, which greatly improves the recognition rate of standard recognition under low signal-to-noise ratio, thus proving the effectiveness and practicability of this method.

Key words: wavelet feature, deep neural network, elastic back propagation, modulation recognition

唐作栋，龚晓峰，雒瑞森. 一种小波特征与深度神经网络结合的信号制式识别算法[J]. 计算机工程与科学.

TANG Zuo-dong,GONG Xiao-feng,LUO Rui-sen.

A signal modulation recognition method based

on wavelet feature and depth neural network

[J]. Computer Engineering & Science.

[1]	姜晶菲, 何源宏, 许金伟, 许诗瑶, 钱希福. NM-SpMM：面向国产异构向量处理器的半结构化稀疏矩阵乘算法[J]. 计算机工程与科学, 2024, 46(07): 1141-1150.
[2]	吴瑕, 郑洪英, 肖迪. 一种基于认证文件的双方验证模型水印方案[J]. 计算机工程与科学, 2024, 46(04): 647-656.
[3]	曹健, 陈怡梅, 李海生, 蔡强, . 基于图神经网络的行人轨迹预测研究综述[J]. 计算机工程与科学, 2023, 45(06): 1040-1053.
[4]	马铭苑, 李虎, 王梓斌, 况晓辉. 深度神经网络模型后门植入与检测技术研究综述[J]. 计算机工程与科学, 2022, 44(11): 1959-1968.
[5]	张开生, 赵小芬. 复杂环境下基于自适应深度神经网络的鲁棒语音识别[J]. 计算机工程与科学, 2022, 44(06): 1105-1113.
[6]	翦杰, 罗章, 赖明澈, 肖立权, 徐炜遐. 基于深度神经网络的高速信道自适应均衡器[J]. 计算机工程与科学, 2022, 44(04): 605-610.
[7]	杜鹏, 李超, 石剑平, 姜麟. 基于阿当姆斯捷径连接的深度神经网络模型压缩方法[J]. 计算机工程与科学, 2021, 43(11): 2043-2048.
[8]	张立志, 冉浙江, 赖志权, 刘锋. 分布式深度学习通信架构的性能分析[J]. 计算机工程与科学, 2021, 43(03): 416-425.