Echo state network based symbol detection in chaotic baseband wireless communication

In some Internet of Things (IoT) applications, multipath propagation is a main constraint of communication channel. Recently, the chaotic baseband wireless communication system (CBWCS) is promising to eliminate the inter-symbol interference (ISI) caused by multipath propagation. However, the current technique is only capable of removing the partial effect of ISI, due to only past decoded bits are available for the suboptimal decoding threshold calculation. However, the future transmitting bits also contribute to the threshold. The unavailable future information bits needed by the optimal decoding threshold are an obstacle to further improve the bit error rate (BER) performance. Different from the previous method using echo state network (ESN) to predict one future information bit, the proposed method in this paper predicts the optimal threshold directly using ESN. The proposed ESN-based threshold prediction method simplifies the symbol decoding operation by removing the threshold calculation from the transmitting symbols and channel information, which achieves better BER performance as compared to the previous method. The reason for this superior result lies in two folds, first, the proposed ESN is capable of using more future symbols information conveyed by the ESN input to get more accurate threshold; second, the proposed method here does not need to estimate the channel information using Least Square method, which avoids the extra error caused by inaccurate channel information estimation. By this way, the calculation complexity is decreased as compared to the previous method. Simulation results and experiment based on a wireless openaccess research platform under a practical wireless channel, show the effectiveness and superiority of the proposed method.

[1]  Ned J Corron,et al.  A matched filter for chaos. , 2010, Chaos.

[2]  M. C. Soriano,et al.  Advances in photonic reservoir computing , 2017 .

[3]  Chen Li,et al.  Chaos-based wireless communication resisting multipath effects. , 2016, Physical review. E.

[4]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[5]  Hai-Peng Ren,et al.  Performance Improvement of Chaotic Baseband Wireless Communication Using Echo State Network , 2020, IEEE Transactions on Communications.

[6]  Jonathan N. Blakely,et al.  Chaos in optimal communication waveforms , 2015, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[7]  Marc Moonen,et al.  Optimal training design for MIMO OFDM systems in mobile wireless channels , 2003, IEEE Trans. Signal Process..

[8]  Hui Gao,et al.  Echo State Network for Fast Channel Prediction in Ricean Fading Scenarios , 2017, IEEE Communications Letters.

[9]  Ned J. Corron,et al.  A new approach to communications using chaotic signals , 1997 .

[10]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[11]  Celso Grebogi,et al.  NOISE FILTERING IN COMMUNICATION WITH CHAOS , 1997 .

[12]  Zhuo Sun,et al.  Learning Time-Frequency Analysis in Wireless Sensor Networks , 2018, IEEE Internet of Things Journal.

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[15]  Yahong Rosa Zheng,et al.  Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Laurent Larger,et al.  Chaos-based communications at high bit rates using commercial fibre-optic links , 2005, Nature.

[17]  Celso Grebogi,et al.  Secure Communication Based on Hyperchaotic Chen System with Time-Delay , 2017, Int. J. Bifurc. Chaos.

[18]  Celso Grebogi,et al.  Experimental Wireless Communication Using Chaotic Baseband Waveform , 2019, IEEE Transactions on Vehicular Technology.

[19]  Jian Sun,et al.  Convolutional neural networks at constrained time cost , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Ulrich Parlitz,et al.  Observing spatio-temporal dynamics of excitable media using reservoir computing. , 2018, Chaos.

[21]  Celso Grebogi,et al.  Experimental validation of wireless communication with chaos. , 2016, Chaos.

[22]  Edward Ott,et al.  Attractor reconstruction by machine learning. , 2018, Chaos.

[23]  Grebogi,et al.  Communicating with chaos. , 1993, Physical review letters.

[24]  Chao Bai,et al.  Double-Sub-Stream M-ary Differential Chaos Shift Keying Wireless Communication System Using Chaotic Shape-Forming Filter , 2020, IEEE Transactions on Circuits and Systems I: Regular Papers.

[25]  Ursula Challita,et al.  Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial , 2017, IEEE Communications Surveys & Tutorials.

[26]  Tommaso Melodia,et al.  Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey , 2019, Ad Hoc Networks.

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Celso Grebogi,et al.  Chaos-Based Underwater Communication With Arbitrary Transducers and Bandwidth , 2018 .

[29]  Wenchang Li,et al.  Channel Estimation Based on Echo State Networks in Wireless MIMO Systems , 2015, 2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC).

[30]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[31]  Mitra Mirhassani,et al.  Efficient VLSI Implementation of Neural Networks With Hyperbolic Tangent Activation Function , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[32]  Georges Kaddoum,et al.  Wireless Chaos-Based Communication Systems: A Comprehensive Survey , 2016, IEEE Access.

[33]  Sudharman K. Jayaweera,et al.  A Survey on Machine-Learning Techniques in Cognitive Radios , 2013, IEEE Communications Surveys & Tutorials.

[34]  Celso Grebogi,et al.  Chaotic shape-forming filter and corresponding matched filter in wireless communication , 2019, World Scientific Series on Nonlinear Science Series B.

[35]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[36]  Herbert Jaeger,et al.  Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks , 2013, Neural Computation.

[37]  Martin Döttling,et al.  Radio technologies and concepts for IMT-Advanced , 2009 .

[38]  R. Brockett,et al.  Reservoir observers: Model-free inference of unmeasured variables in chaotic systems. , 2017, Chaos.

[39]  Jie Li,et al.  A differential chaos-shift keying scheme based on hybrid system for underwater acoustic communication , 2016, 2016 IEEE/OES China Ocean Acoustics (COA).

[40]  Celso Grebogi,et al.  Digital underwater communication with chaos , 2019, Commun. Nonlinear Sci. Numer. Simul..

[41]  Serge Massar,et al.  Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography , 2018, Physical review. E.

[42]  Mugen Peng,et al.  Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues , 2018, IEEE Communications Surveys & Tutorials.

[43]  Celso Grebogi,et al.  Wireless communication with chaos. , 2013, Physical review letters.

[44]  Matthew M Botvinick,et al.  Short-term memory for serial order: a recurrent neural network model. , 2006, Psychological review.

[45]  B. Schrauwen,et al.  Reservoir computing and extreme learning machines for non-linear time-series data analysis , 2013, Neural Networks.