Convolutional recurrent neural network-based channel equalization: An experimental study

In this paper, we revisit the idea of using deep neural network for channel equalization to account for nonlinear channel distortions as well as temporal variations of radio signals. Our insight is leveraging the the shift-invariant properties of the convolutional neural network (CNN) to learn matched filters analogous to the tap weights of conventional equalizer. Then we feed the learned filters into a subsequent recurrent neural network (RNN) with long-short-term-memory (LSTM) cells for temporal modeling of the channel. We train our proposed CNN-RNN (CRNN) equalizer based on real testbed collected data and enlarge the generalization ability of the learned network model as much as we can to adapt to different channel conditions. Experimental results show that the SER performance for our designated single-input single-output (SISO) system which utilises quadrature phase shift keying (QPSK) modulation scheme with the proposed CRNN-based channel equalizer outperforms that of other equalizers by average 2 to 5 dB at low signal-to-noise ratio (SNR).

[1]  J.M.T. Romano,et al.  MLP-Based Equalization and Pre-Distortion Using an Artificial Immune Network , 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

[2]  Xiangping Zeng,et al.  Low-Complexity Nonlinear Adaptive Filter Based on a Pipelined Bilinear Recurrent Neural Network , 2011, IEEE Transactions on Neural Networks.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[5]  Yang Wang,et al.  Channel Equalization Using a Robust Recursive Least-Squares Adaptive-Filtering Algorithm , 2012, 2012 IEEE 12th International Conference on Computer and Information Technology.

[6]  Tiilay Adalrl,et al.  CHANNEL EQUALIZATION WITH PERCEPTRONS: AN INFORMATION-THEORETIC APPROACH , 1994 .

[7]  T. Charles Clancy,et al.  Convolutional Radio Modulation Recognition Networks , 2016, EANN.

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  Wan-de Weng,et al.  Application of Neural Network Techniques on Nonlinear Channel Equalization for 16-QAM Modulation Systems , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[10]  Kavita Burse,et al.  Channel Equalization Using Neural Networks: A Review , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[11]  Po-Rong Chang,et al.  Adaptive Decision Feedback Equalization for Digital Satellite Channels Using Multilayer Neural Networks , 1995, IEEE J. Sel. Areas Commun..

[12]  C. Caraiscos,et al.  A roundoff error analysis of the LMS adaptive algorithm , 1984 .

[13]  Goutam Chakraborty,et al.  Legendre-FLANN-based nonlinear channel equalization in wireless communication system , 2008, 2008 IEEE International Conference on Systems, Man and Cybernetics.

[14]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[15]  Rui Shi,et al.  Artificial neural network-based nonlinear channel equalization: A soft-output perspective , 2015, 2015 22nd International Conference on Telecommunications (ICT).

[16]  J.C. Patra,et al.  Nonlinear channel equalization with QAM signal using Chebyshev artificial neural network , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[17]  Mu-Song Chen,et al.  Adaptive equalization using complex-valued multilayered neural network based on the extended Kalman filter , 2000, WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000.