Recognition of Electromagnetic Signals Based on the Spiking Convolutional Neural Network

被引：0

作者：

Tao S. ^{[1
,2
]}

Xiao S. ^{[2
]}

Gong S. ^{[1
]}

Wang H. ^{[2
]}

Ding H. ^{[3
]}

Wang H. ^{[2
]}

机构：

[1] State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System, Luoyang

[2] School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing

[3] Engineering Training Center, Nanjing University of Science and Technology, Nanjing

来源：

Wireless Communications and Mobile Computing | 2022年 / 2022卷

关键词：

Extraction;

D O I：

10.1155/2022/2395996

中图分类号：

学科分类号：

摘要：

Feature extraction and recognition of signals are the bases of a cognitive radio. Traditional manual extraction for signals' features becomes difficult in the complex electromagnetic environment. Although convolutional neural networks (CNNs) can extract signal features automatically, they have low accuracy in recognizing electromagnetic signals at low signal-to-noise ratios (SNRs) due to the agility of signals. Considering the great potential of spiking neural networks (SNNs) in classification, a spiking convolution neural network (SCNN) for the recognition of electromagnetic signals is proposed in this paper. The SCNN effectively integrates the extraction ability of spatial features in CNNs and temporal features in SNNs. Since the SCNN is difficult to train, the strategy of surrogate gradient is proposed to train it. By taking the 2-dimensional time-frequency distribution of 6 signals as input, the SCNN can effectively identify different signals at low SNRs. The method proposed in this paper contributes to promote the research and application of SNNs in the recognition of electromagnetic signals. © 2022 Shifei Tao et al.

引用

共 29 条

[1] Mu J.S., Tan Y.H., Xie D.L., Zhang F., Jing X., CNN and DCGAN for spectrum sensors over rayleigh fading channel, Wireless Communications and Mobile Computing, 2021, (2021)
[2] Wang G.M., Chen S.W., Huang J., Qin X., Yuan J.J., Radar emitter sorting and recognition based on multi-synchrosqueezing transform, Modern Radar, 42, 3, pp. 49-56, (2020)
[3] Li X.F., Dong F.W., Zhang S., Guo W., A survey on deep learning techniques in wireless signal recognition, Wireless Communications and Mobile Computing, 2019, (2019)
[4] Qin X., Zha X., Huang J., Luo L., Radar Waveform Recognition Based on Deep Residual Network, pp. 892-896
[5] Huynh-The T., Hua C.H., Doan V.S., Pham Q.V., Kim D.S., Accurate deep CNN-based waveform recognition for intelligent radar systems, IEEE Communications Letters, 25, 9, pp. 2938-2942, (2021)
[6] Ahmed R., Chen Y., Hassan B., Deep learning-driven opportunistic spectrum access (OSA) framework for cognitive 5G and beyond 5G (B5G) networks, Ad Hoc Networks, 123, pp. 102632-102645, (2021)
[7] Xu M., Hou J., Wu P., Liu Y., Lv Z., Convolutional neural networks based on time frequency characteristics for modulation classification, Journal of Computer Science and Technology, 47, 2, pp. 175-179, (2020)
[8] Ye W.Q., Yu Z.F., Wang H.B., Zhang K., Recognition algorithm of emitter signals based on CNN, Computer Simulation, 36, 9, pp. 33-37, (2019)
[9] Yao Y., Wang Z.H., Radar signal recognition based on time-frequency and CNN preprocessing, Journal of Detection & Control, 40, 6, pp. 99-105, (2018)
[10] Xiao Y.H., Wang L., Guo Y.X., Radar signal modulation type recognition based on denoising convolutional neural network, Journal of Electronics & Information Technology, 43, 8, pp. 2300-2307, (2021)

← 1 2 3 →