Radio signal classification based on deep learning

Abstract

Abstract: The related technologies of radio signal classification are first studied, and then a novel deep learning network based on residual neural network and group convolutional neural network is proposed to realize radio signal classification. The neural network is trained based on sample composed of in-phase component signal and quadrature component signal. The experimental results show that the classification accuracy of 24 kinds of signals reaches 95.69% at 10 dB, and the effectiveness and practicability of the network architecture are revealed.

Key words: deep learning, residual neural network, group convolutional neural network, radio signal classification

CLC Number:

TP315

LIU Jin-xia. Radio signal classification based on deep learning[J]. Journal of Lanzhou University of Technology, 2021, 47(4): 106-110.

References

[1] SAPIANO P C,MARTIN J D.Maximum likelihood PSK classifier[C]//IEEE Communications Society.Proceedings of MILCOM’96 IEEE Military Communications Conference.McLean,VA,USA:IEEE,1996:1010-1014.
[2] BEIDAS B F,WEBER C L.Asynchronous classification of MFSK signals using the higher order correlation domain [J].IEEE Transactions on Communications,1998,46(4):480-493.
[3] SILL J A.Maximum-likelihood modulation classification for PSK/QAM [C]//IEEE Communications Society.Proceedings of MILCOM’99 IEEE Military Communications Conference.Atlantic City,NJ,USA:IEEE,1999:217-220.
[4] PANAGIOTOU P,ANASTASOPOULOS A,POLYDOROS A.Likelihood ratio tests for modulation classification [C]//IEEE Communications Society.21st Century Military Communications (2).Los Angeles,CA,USA:IEEE,2000:670-674.
[5] HONG Liang,HO K C.Antenna array likelihood modulation classifier for BPSK and QPSK signals [C]//IEEE Communications Society.MILCOM 2002(1).Anaheim,CA,USA:IEEE,2002:647-651.
[6] HEUE S,SOLIMAN S S.Automatic modulation recognition of digitally modulated signals [C]//IEEE Communications Society.IEEE Military Communications Conference(3).Boston,MA,USA:IEEE,1989:645-649.
[7] HONG Liang,HO K C.Identification of digital modulation types using the wavelet transform [C]//IEEE Military Communications.MILCOM 1999 (1).Atlantic City,NJ,USA:IEEE,1999:427-431.
[8] SWAMI A,SADLER B M.Hierarchical digital modulation classification using cumulants [J].IEEE Transactions on Communications,2000,48(3):416-429.
[9] HATZICHRISTOS G,FARGUES M P.A hierarchical approach to the classification of digital modulation types in multipath environments [C]//IEEE Communications Society.Conference Record of the Thirty-Fifth Asilomar Conference(2).Pacific Grove,CA,USA:IEEE,2001:1494-1498.
[10] SOLIMAN S S,HSUE S Z.Signal classification using statistical moments [J].IEEE Transactions on Communications,1992,40(5):908-916.
[11] LU Mingquan,XIAO Xianci,LI Lemin.AR modeling-based features extraction of multiple signals for modulation recognition [C]//IEEE Communications Society.1998 Fourth International Conference on Signal Processing (2).Beijing,China:IEEE,1998:1385-1388.
[12] MOBASSERI B G.Digital modulation classification using constellation shape [J].Signal Processing:The Official Publication of the European Association for Signal Processing (EURASIP),2000,80(2):251-277.
[13] LU Mingquan,XIAO Xianci,LI Leming.Cyclic spectral features based modulation recognition [C]//IEEE Communications Society.Proceedings of International Conference on Communication Technology (2).Beijing,China:IEEE,1996:792-795.
[14] NANDI A K,AZZOUZ E E.Modulation recognition using artificial neural networks [J].Signal Processing:The Official Publication of the European Association for Signal Processing(EURASIP),1997,56(2):165-175.
[15] DOYLE L,NOLAN K,O’MAHONY D.Modulation scheme classification for 4G software radio wireless networks [C]//IASTED International Conference on Signal Processing,Pattern Recognition,and Application.Grete,Greece:ACTA,2002:25-31.
[16] O’SHEA T,CORGAN J,CLANCY T C.Convolutional radio modulation recognition networks [C]//International Conference on Engineering Applications of Neural Networks.Aberdeen,United Kingdom:Springer,2016:213-226.
[17] HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition [C]//IEEE Communications Society.IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA:IEEE,2016:770-778.
[18] O’SHEA T J,ROY T,CLANCY T C.Over-the-air deep learning based radio signal classification [J].IEEE Journal of Selected Topics in Signal Processing,2018,12(1):168-179.
[19] RAMJEE S,JU S,YANG D,et al.Fast deep learning for automatic modulation classification [C/OL].[2021-04-02].https://arxiv.org/pdf/1901.05850.pdf.
[20] WANG Danshi.Intelligent constellation diagram analyzer using convolutional neural network-based deep learning [J].Optics Express,2017,25(15):17150-17166.
[21] WANG Y,LIU M,YANG J,et al.Data-driven deep learning for automatic modulation recognition in cognitive radios [J].IEEE Transactions on Vehicular Technology,2019,68(4):4074-4077.