Modulation recognition method based on high-order cumulant feature learning

被引：2
|
作者：
Yuan L. [1 ]
Ning S. [1 ]
He Y. [1 ]
Lyu M. [2 ]
Lu J. [3 ]
机构：
[1] College of Electrical Engineering and Automation, Hefei University of Technology, Hefei
[2] College of Engineering, Texas Agricultural &Mechanical University, 77843, TX
[3] State Grid Hefei Power Supply Company, Hefei
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2019年 / 41卷 / 09期
关键词：
Deep learning; High-order cumulant; Low signal-to-noise ratio (Low-SNR); Modulation characteristics; Modulation classification;
D O I：
10.3969/j.issn.1001-506X.2019.09.28
中图分类号：
学科分类号：
摘要：
Automatic modulation classification is one of the key technologies to ensure communication security and reliability. In a low signal-to-noise ratio (Low-SNR) environment, the automatic modulation classification recognition rate is low and the recognition type is limited. By using the property that the high-order cumulant is equal to zero of zero-mean white Gaussian noise (WGN), the high-order cumulant is introduced to protect the system from WGN in the signal analysis process. Moreover, the deep learning network structure is introduced to complete the characterization of weak features, which can effectively solve the problem of the limited modulation method. And it can also solve the problem of low recognition rate under Low-SNR. The experimental results show that the classification accuracy of the proposed method is better than the existing methods in the Gaussian channel environment, and it has a higher recognition rate in different channel environments with Low-SNR. And, it makes the model's time, phase and frequency offset more robust. © 2019, Editorial Office of Systems Engineering and Electronics. All right reserved.
引用
收藏
页码：2122 / 2131
页数：9
相关论文
共 20 条
  • [1] Menguc O., On the classification of binary space shift keying modulation, IEEE Communications Letters, 22, 8, pp. 1584-1587, (2018)
  • [2] Shi Z.Y., Wu H., Shen W.D., Et al., Feature extraction for complicated radar PRI modulation modes based on auto-correlation function, Proc.of the IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, pp. 1617-1620, (2016)
  • [3] Kofidisk E., Preamble-based estimation of highly frequency selective channels in FBMC/OQAM systems, IEEE Trans.on Signal Processing, 65, 7, pp. 1855-1868, (2017)
  • [4] Dobre O.A., Signal identification for emerging intelligent radios: classical problems and new challenges, IEEE Instrumentation and Measurement Magazine, 18, 2, pp. 11-18, (2015)
  • [5] Wang L., Gao Q., Zhang K., Et al., Modulation classification of mixed signals using fast independent component analysis, Proc.of the Wireless Communications and Networking Conference, pp. 1-5, (2016)
  • [6] Zhou D., Dai J., Niu K., Et al., Polar-coded modulation based on the amplitude phase shift keying constellations, China Communications, 14, 9, pp. 166-177, (2017)
  • [7] Fu J.Q., Li R., Zhao C.L., Et al., Adaptive modulation recognition algorithm based on sequential Bayesian inference, Systems Engineering and Electronics, 37, 12, pp. 2860-2864, (2015)
  • [8] Almohamad T.A., Salleh M.F.M., Mahmud M.N., Et al., Simultaneous determination of modulation types and signal-to-noise ratios using feature-based approach, IEEE Access, 6, 99, pp. 9262-9271, (2018)
  • [9] Jayatunga E.H., Dobre O.A., A robust higher-order cyclic cumulants feature-based vector for QAM classification, Proc.of the IEEE International Symposium on Communication Systems, Networks and Digital Signal Processing, pp. 417-421, (2014)
  • [10] Liu P., Ji X.J., Zhao G.Q., Asynchronous classification of digital modulations in multipath flat-fading channel using fourth-order cumulant, Proc.of the IEEE International Conference on Signal Processing, pp. 1435-1439, (2016)
12