基于CWD和残差收缩网络的调制方式识别方法

doi:10.12305/j.issn.1001-506X.2021.11.38

Abstract

Abstract:

Aiming at the problems of difficulty in guaranteeing the accuracy of feature extraction and poor recognition performance at low signal to noise ratio under the Rice channel, a modulation recognition method for communication radiator signal based on Choi-Williams distribution (CWD) and deep residual shrinkage network (DRSN) is proposed. In this work, CWD is used to convert the time-domain complex signals into two-dimensional time-frequency matrices firstly. Meanwhile, the soft thresholding is added to the deep residual networks (ResNets) to obtain the DRSN. Subsequently, the time-frequency matrices are used to train the DRSN. Modulation recognition network under different signal to noise ratios are finally constructed. Simulation experiments based on the RadioML2016.10a data show that the recognition network constructed has high accuracy and strong robustness to noise by utilizing partial prior information. At 0 dB, the overall recognition accuracy of the 11 types of signals reaches 89.95%. Above 2 dB, the overall recognition accuracy of the 11 types of signals exceeds 91%, which is better than other modulation recognition methods based on deep learning.

Key words: modulation recognition, soft thresholding, Choi-Williams distribution (CWD), deep residual shrinkage network (DRSN)

CLC Number:

TN911.7

Zihao SONG, Wei CHENG, Cenxin PENG, Xiaobai LI. Modulation recognition method based on CWD and residual shrinkage network[J]. Systems Engineering and Electronics, 2021, 43(11): 3371-3379.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

Fig.10

References 20

1	何继爱, 张文启. 通信信号调制识别技术及其发展[J]. 高技术通讯, 2016, 26 (2): 157- 165. doi: 10.3772/j.issn.1002-0470.2016.02.006
	HE J A , ZHANG W Q . The technology for modulation of communication signals and its development[J]. Chinese High Technology Letters, 2016, 26 (2): 157- 165. doi: 10.3772/j.issn.1002-0470.2016.02.006
2	LI X F , DONG F W , ZHANG S , et al. A survey on deep learning techniques in wireless signal recognition[J]. Wireless Communications and Mobile Computing, 2019, 2019 (1): 1- 12.
3	O'SHEA T J, CORGAN J, CLANCY T C. Convolutional radio modulation recognition networks[C]//Proc. of the International Conference on Engineering Applications of Neural Networks, 2016: 213-226.
4	LIU X, YANG D, GAMAL A E. Deep neural network architectures for modulation classification[D]. West Lafayette: Purdue University, 2017: 23-28.
5	PENG S L , JIANG H Y , WANG H X , et al. Modulation classification based on signal constellation diagrams and deep learning[J]. IEEE Trans.on Neural Networks and Learning Systems, 2019, 30 (3): 718- 727. doi: 10.1109/TNNLS.2018.2850703
6	ZHANG Z F , WANG C , GAN C Q , et al. Automatic modulation classification using convolutional neural network with features fusion of SPWVD and BJD[J]. IEEE Trans.on Signal & Information Processing Over Networks, 2019, 5 (2): 469- 478.
7	ZENG Y , ZHANG M , HAN F , et al. Spectrum analysis and convolutional neural network for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8 (3): 929- 932. doi: 10.1109/LWC.2019.2900247
8	张斌, 刘凯, 赵梦伟. 基于时频分析的深度学习调制识别算法[J]. 工业控制计算机, 2020, 33 (5): 66- 68, 71. doi: 10.3969/j.issn.1001-182X.2020.05.027
	ZHANG B , LIU K , ZHAO M W . Deep learning modulation recognition algorithm based on time-frequency analysis[J]. Industrial Control Computer, 2020, 33 (5): 66- 68, 71. doi: 10.3969/j.issn.1001-182X.2020.05.027
9	李楠. 双谱特征和深度学习在信号调制识别中的应用[J]. 弹箭与制导学报, 2019, 39 (5): 81- 84, 88.
	LI N . Application of bi-spectral feature and depth learning in signal modulation recognition[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2019, 39 (5): 81- 84, 88.
10	毕然. 无线信道的小尺度衰落特性参数提取及评估分析方法[D]. 合肥: 合肥工业大学, 2019.
	BI R. Small-scale fading characteristic parameter extraction and evaluation analysis method for wireless channel[D]. Hefei: Hefei University of Technology, 2019.
11	COHEN L . Time-frequency distributions-a review[J]. Proceedings of the IEEE, 1989, 77 (7): 941- 981.
12	LIU Y , XIAO P , WU H C , et al. LPI radar signal detection based on radial integration of Choi-Williams time-frequency image[J]. Journal of Systems Engineering and Electronics, 2015, 26 (5): 973- 981. doi: 10.1109/JSEE.2015.00106
13	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision & Pattern Recognition, 2016: 770-778.
14	ZHAO M H , ZHONG S S , FU X Y , et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Trans.on Industrial Informatics, 2020, 16 (17): 4681- 4690.
15	付伟. 基于自适应阈值的高压电缆局部放电信号降噪研究[J]. 电子测量技术, 2020, 43 (11): 138- 141.
	FU W . Research on noise reduction of partial discharge signal of high voltage cable based on improved threshold function[J]. Electronic Measurement Technology, 2020, 43 (11): 138- 141.
16	阳晟. 基于PCA和L2正则化的自适应学习率自编码器降维算法研究[D]. 南宁: 广西大学, 2019.
	YANG C. The research on dimension reduction algorithm of adaptive learning rate auto-encoder based on PCA and L2 regularization[D]. Nanning: Guangxi University, 2019.
17	KINGMA D P, BA J L. Adam: a method for stochastic optimization[C]//Proc. of the 3rd International Conference on Learning Representations, 2015.
18	王爽. 基于时频分析和模糊函数的LPI雷达波形识别算法研究[D]. 哈尔滨: 哈尔滨工程大学, 2019.
	WANG S. Research on LPI radar waveform recognition algorithm based on joint time-frequency analysis and ambiguity function[D]. Harbin: Harbin Engineering University, 2019.
19	刘歌, 张旭洲, 汪洪艳. 基于AR功率谱和ZAM变换的FSK-BPSK复合信号参数估计[J]. 电讯技术, 2017, 57 (4): 430- 435.
	LIU G , ZHANG X Z , WANG H Y . Parameter estimation of FSK-BPSK hybrid modulation signal based on AR power spectrum and ZAM transform[J]. Telecommunication Engineering, 2017, 57 (4): 430- 435.
20	任思睿, 黄铭. 基于改进的长短期记忆网络的调制识别算法[J]. 云南大学学报(自然科学版), 2021, 43 (1): 39- 45.
	REN S R , HUANG M . A modulation classification algorithm based on modified LSTM network[J]. Journal of Yunnan University: Natural Sciences Edition, 2021, 43 (1): 39- 45.

网络结构	单批次训练时间/s	训练参数个数
CNN	0.136 6	208 761
ResNets	0.181 8	208 761
DRSN	0.212 1	234 161

[1]	Bowei QIN, Lei JIANG, Hua XU, Zisen QI. Modulation recognition algorithm based on residual generation adversarial network [J]. Systems Engineering and Electronics, 2022, 44(6): 2019-2026.
[2]	Kai SHAO, Miaomiao ZHU, Guangyu WANG. Modulation recognition method based on generative adversarial andconvolutional neural network [J]. Systems Engineering and Electronics, 2022, 44(3): 1036-1043.
[3]	Yunhao SHI, Hua XU, Wanze ZHENG, Yinghui LIU. Few-shot modulation recognition method based on ensemble learning and feature dimension reduction [J]. Systems Engineering and Electronics, 2021, 43(4): 1099-1109.
[4]	Kai LIU, Bin ZHANG, Qinghua HUANG. Modulation recognition algorithm based on TCNN-BiLSTM [J]. Systems Engineering and Electronics, 2020, 42(8): 1841-1849.
[5]	Kai LIU, Mengwei ZHAO, Qinghua HUANG. Multi-h CPM modulation recognition algorithm based on approximate entropy [J]. Systems Engineering and Electronics, 2020, 42(3): 698-703.
[6]	Chen LI, Jun'an YANG, Hui LIU. Modulation recognition algorithm based on information entropy and GA-ELM [J]. Systems Engineering and Electronics, 2020, 42(1): 223-229.
[7]	HAO Yunfei, LIU Zhangmeng, GUO Fucheng, ZHANG Min. Open-set recognition of signal modulation based on generative adversarial networks [J]. Systems Engineering and Electronics, 2019, 41(11): 2619-2624.
[8]	TAN Xiaoheng, CHU Guoxing, ZHANG Xuejing, YANG Yang. Modulation recognition algorithm based on high-order cumulants and wavelet transform [J]. Systems Engineering and Electronics, 2018, 40(1): 171-177.
[9]	FU Jun-qiang, LI Rong, ZHAO Cheng-lin, LI Bin. Sequential Bayesian inference based adaptive modulation recognition algorithm [J]. Systems Engineering and Electronics, 2015, 37(12): 2860-2864.
[10]	YANG Fa-quan, LI Zan, LI Hong-yan, HAO Ben-jian, PAN Zhong-xian. Research of communication modulation recognition based on bee colony algorithm and neural network [J]. Systems Engineering and Electronics, 2013, 35(10): 2186-2191.
[11]	LI Yi-bing, Ge Juan, LIN Yun. Modulation recognition using entropy features and SVM [J]. Journal of Systems Engineering and Electronics, 2012, 34(8): 1691-1695.
[12]	TAN Xiao-heng, CHEN Yin. Automatic digital modulation recognition based on combined feature parameters [J]. Journal of Systems Engineering and Electronics, 2011, 33(12): 2732-2736.
[13]	TAN Xiao-heng, LIU Juan, HU You-qiang. New algorithm for digital modulation recognition under low SNR [J]. Journal of Systems Engineering and Electronics, 2009, 31(6): 1520-1524.

Modulation recognition method based on CWD and residual shrinkage network

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 20

Related Articles 13

Recommended Articles

Metrics

Comments