分离通道联合卷积神经网络的自动调制识别
|
摘要
针对通信信号的自动调制识别需要大量特征提取的问题,提出了一种分离通道卷积神经网络自动调制识别算法。该算法通过结合深度学习中卷积神经网络(CNN),分别提取时域信号的多通道和分离通道调制特征,再利用融合特征实现不同信号的分类。仿真结果表明,相比基于CNN的算法,所提算法在高信噪比下针对两个数据集的识别率分别提升7%和18%;此外,相比于基于特征提取的传统识别算法,其高阶调制识别性能平均提升3 d B。
An automatic modulation recognition algorithm based on Separate Channel Combined Convolutional Neural Network(SCC-CNN) is proposed to solve the mass computation of feature extraction in conventional automatic modulation recognition methods.The algorithm can extract features from multi-channel and separate channels of time domain data respectively by combining the convolutional neural network of deep learning,and then different signals can be classified by combined features. The simulation results reveal that compared with the methods based on CNN the proposed algorithm can improve the accuracy under high signal-to-noise ratio(SNR) more than 7% and 18% on two different datasets; furthermore,high order modulation recognition performance is improved more than 3 d B compared with the methods based on feature extraction.
An automatic modulation recognition algorithm based on Separate Channel Combined Convolutional Neural Network(SCC-CNN) is proposed to solve the mass computation of feature extraction in conventional automatic modulation recognition methods.The algorithm can extract features from multi-channel and separate channels of time domain data respectively by combining the convolutional neural network of deep learning,and then different signals can be classified by combined features. The simulation results reveal that compared with the methods based on CNN the proposed algorithm can improve the accuracy under high signal-to-noise ratio(SNR) more than 7% and 18% on two different datasets; furthermore,high order modulation recognition performance is improved more than 3 d B compared with the methods based on feature extraction.
引文
[1]王宇扬.数字通信信号调制识别与参数估计[D].南京:南京理工大学,2014.WANG Yuyang.Modulation recognition and parameter estimation of digital communication signal[D].Nanjing:Nanjing University of Science and Technology,2014.(in Chinese)
[2]DOBRE O A,ABDI A,BAR-NESS Y,et al.Survey of automatic modulation classification techniques:classical approaches and new trends[J].IET Communications,2007,1(2):137-156.
[3]张琴,田宝玉.通信信号调制模式的自动识别技术及发展前景[J].电讯技术,2008,48(2):6-10.ZHANG Qin,TIAN Baoyu.Automatic recognition technology for communication modulation signal and its prospects[J].Telecommunication Engineering,2008,48(2):6-10.(in Chinese)
[4]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[5]FU J,ZHAO C,LI B,et al.Deep learning based digital signal modulation recognition[C]//Proceedings of the Third International Conference on Communications,Signal Processing,and Systems.Berlin:Springer International Publishing,2015:955-964.
[6]MA L,YANG Y,WANG H.DBN based automatic modulation recognition for ultra-low SNR RFID signals[C]//Proceedings of 2036 35th Chinese Control Conference.Chengdu:IEEE,2016:7054-7057.
[7]KIM B,KIM J,CHAE H,et al.Deep neural networkbased automatic modulation classification technique[C]//Proceedings of International Conference on Information and Communication Technology Convergence.Jeju,South Korea:IEEE,2016:579-582.
[8]ZHU X,FUJII T.Modulation classification for cognitive radios using stacked denoising autoencoders[J].International Journal of Satellite Communications&Networking,2016,35(5):517-531.
[9]ZHANG Z,HUA Z,LIU Y.Modulation classification in multipath fading channels using sixth-order cumulants and stacked convolutional auto-encoders[J].IET Communications,2017,11(6):910-915.
[10]ZHANG H,SUN H.Automatic modulation classification using stacked sparse auto-encoders[C]//Proceedings of 2016 IEEE 13th International Conference on Signal Processing.Chengdu:IEEE,2017:248-252.
[11]PENG S,JIANG H,WANG H,et al.Modulation classification using convolutional Neural Network based deep learning model[C]//Proceedings of 2017 26th Wireless and Optical Communication Conference.Newark,NJ,USA:IEEE,2017:1-5.
[12]O’SHEA T J,CORGAN J,CLANCY T C.Convolutional radio modulation recognition networks[C]//Proceedings of17th International Conference on Engineering Applications of Neural Networks.Aberdeen,UK:IEEE,2016:213-226.
[13]WEST N E,O'SHEA T.Deep architectures for modulation recognition[C]//Proceedings of 2017 IEEE International Symposium on Dynamic Spectrum Access Networks(Dy SPAN).Piscataway,NJ,USA:IEEE,2017:1-6.
[14]WU H,YUAN Y J,HUANG Z T,et al.APSK modulation recognition for DVB-S2 using GLRT and radius-constellation under frequency offset[J].Wireless Personal Communications,2015,82(3):1-12.
[15]CHOU Z D,JIANG W N,XIANG C B,et al.Modulation recognition based on constellation diagram for M-QAM signals[C]//Proceedings of 2014 IEEE International Conference on Electronic Measurement&Instruments.Harbin:IEEE,2014:70-74.
[16]赵知劲,强芳芳,陈颖.利用高阶累积量的数字调相信号识别[J].杭州电子科技大学学报(自然科学版),2016,36(3):1-5.ZHAO Zhijin,QIANG Fangfang,CHEN Ying.Modulationrecognition of MPSK signals using higher order cumulants[J].Journal of Hangzhou Dianzi University(Natural Science),2016,36(3):1-5.(in Chinese)
[2]DOBRE O A,ABDI A,BAR-NESS Y,et al.Survey of automatic modulation classification techniques:classical approaches and new trends[J].IET Communications,2007,1(2):137-156.
[3]张琴,田宝玉.通信信号调制模式的自动识别技术及发展前景[J].电讯技术,2008,48(2):6-10.ZHANG Qin,TIAN Baoyu.Automatic recognition technology for communication modulation signal and its prospects[J].Telecommunication Engineering,2008,48(2):6-10.(in Chinese)
[4]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[5]FU J,ZHAO C,LI B,et al.Deep learning based digital signal modulation recognition[C]//Proceedings of the Third International Conference on Communications,Signal Processing,and Systems.Berlin:Springer International Publishing,2015:955-964.
[6]MA L,YANG Y,WANG H.DBN based automatic modulation recognition for ultra-low SNR RFID signals[C]//Proceedings of 2036 35th Chinese Control Conference.Chengdu:IEEE,2016:7054-7057.
[7]KIM B,KIM J,CHAE H,et al.Deep neural networkbased automatic modulation classification technique[C]//Proceedings of International Conference on Information and Communication Technology Convergence.Jeju,South Korea:IEEE,2016:579-582.
[8]ZHU X,FUJII T.Modulation classification for cognitive radios using stacked denoising autoencoders[J].International Journal of Satellite Communications&Networking,2016,35(5):517-531.
[9]ZHANG Z,HUA Z,LIU Y.Modulation classification in multipath fading channels using sixth-order cumulants and stacked convolutional auto-encoders[J].IET Communications,2017,11(6):910-915.
[10]ZHANG H,SUN H.Automatic modulation classification using stacked sparse auto-encoders[C]//Proceedings of 2016 IEEE 13th International Conference on Signal Processing.Chengdu:IEEE,2017:248-252.
[11]PENG S,JIANG H,WANG H,et al.Modulation classification using convolutional Neural Network based deep learning model[C]//Proceedings of 2017 26th Wireless and Optical Communication Conference.Newark,NJ,USA:IEEE,2017:1-5.
[12]O’SHEA T J,CORGAN J,CLANCY T C.Convolutional radio modulation recognition networks[C]//Proceedings of17th International Conference on Engineering Applications of Neural Networks.Aberdeen,UK:IEEE,2016:213-226.
[13]WEST N E,O'SHEA T.Deep architectures for modulation recognition[C]//Proceedings of 2017 IEEE International Symposium on Dynamic Spectrum Access Networks(Dy SPAN).Piscataway,NJ,USA:IEEE,2017:1-6.
[14]WU H,YUAN Y J,HUANG Z T,et al.APSK modulation recognition for DVB-S2 using GLRT and radius-constellation under frequency offset[J].Wireless Personal Communications,2015,82(3):1-12.
[15]CHOU Z D,JIANG W N,XIANG C B,et al.Modulation recognition based on constellation diagram for M-QAM signals[C]//Proceedings of 2014 IEEE International Conference on Electronic Measurement&Instruments.Harbin:IEEE,2014:70-74.
[16]赵知劲,强芳芳,陈颖.利用高阶累积量的数字调相信号识别[J].杭州电子科技大学学报(自然科学版),2016,36(3):1-5.ZHAO Zhijin,QIANG Fangfang,CHEN Ying.Modulationrecognition of MPSK signals using higher order cumulants[J].Journal of Hangzhou Dianzi University(Natural Science),2016,36(3):1-5.(in Chinese)