Performance of Cellular Neural Network Based Channel Equalizers

Abstract—In this paper, a popular dynamic neural network structure called Cellular Neural Network (CNN) is employed as a channel equalizer in digital communications. It is shown that, this nonlinear system is capable of suppressing the effect of intersymbol interference (ISI) and the noise at the channel. The architecture is a small-scaled, simple neural network containing only 25 neurons (cells) with a neighborhood of r = 2 , thus including only 51 weight coefficients. Furthermore, a special technique called repetitive codes in equalization process is also applied to the mentioned CNN based system to show that the two-dimensional structure of CNN is capable of processing such signals, where performance improvement is observed. Simula-tions are carried out to compare the proposed structures with minimum mean square error (MMSE) and multilayer perceptron (MLP) based equalizers.

PDF

___

[1] C. Berrou, A. Glavieux, P. Thitimajshima, “”Near Shannon limit error-correcting coding and decoding: Turbo-codes,” in Proceeding of EEE International Conference on Communications, Geneva, Switzerland, Nov. 30 - Dec. 4 1993, pp. 1064–1070.
[2] M.K. Lee, K. Yang, “Scheduling for an adaptive number of iterations in turbo equalizers combined with LDPC decoders,” IEEE T Commun, vol. 58, no. 10, pp. 2759–2764, 2010.
[3] M. Tuchler, R. Koetter, A. Singer, “Turbo equalization: Principles and new results,” IEEE T Commun, vol. 50, no. 5, pp. 754–767, 2002.
[4] S. Talakoub S., L. Sabeti, B. Shahrrava, M. Ahmadi, “An improved max-log-MAP algorithm for turbo decoding and turbo equalization,” IEEE T Instrum Meas, vol. 56, no. 3, pp. 1058–1063, 2007.
[5] C. He, L. Jing, R. Xi, H. Wang, F. Hua, Q. Dang, Q. Zhang, “ Time-Frequency Domain Turbo Equalization for Single-Carrier Underwater Acoustic Communications,” IEEE Access, vol. 7, pp. 73 324 – 73 335, 2019.
[6] N. Sharma, J. Sharma, S. Mishra, “Design & implementation of efficient turbo equalizer for noise reduction,” in In: 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), Chennai, India, August 2017, pp. 2193–2198.
[7] P. J.G., Digital Communications 4th ed. McGraw Hill, 2001.
[8] B.Gupta, G. Gupta, D. S. Saini, “BER performance improvement in OFDM system with ZFE and MMSE equalizers,” in In: 2011 3rd In-ternational Conference on Electronics Computer Technology, Kanyaku-mari, India, April 2011, pp. 193–197.
[9] J. Lee, C. Beach, N. Tepedelenlioglu, “A practical radial basis function equalizer,” IEEE T Neural Networ, vol. 10, no. 2, pp. 450–455, 1999.
[10] L. Biao, BL. Evans , “Channel equalization by feed forward neural networks,” in In: Proceeding of IEEE International Symposium on Circuits and Systems, Orlando, FL, USA, May 30 - June 2 1999, pp. 587–590.
[11] R. Perfetti, “CNN for fast adaptive equalization,” J Circ Theor, vol. 21, no. 2, pp. 165–175, March 1993.
[12] A. Ozmen, B. Tander, “Channel equalization with cellular neural networks,” in In: IEEE Mediterranean Electrotechnical Conference, Valletta, Malta, April 2010, pp. 1597–1599.
[13] L.O. Chua, L. Yang, “A Cellular neural networks: Theory,” IEEE Trans CAS, vol. 35, no. 10, pp. 1257–1272, 1988
[14] G. Costantini, D. Casali, M. Carota, “Detection of moving objects in 2-D images based on a CNN algorithm and density based spatial clustering,” WSEAS Trans CAS, vol. 4, no. 5, pp. 440–447, 2005.
[15] K. S. M., Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice Hall, 1993.
[16] T. Tozek, T. Roska, L.O. Chua, “ Genetic algorithm for CNN template learning,” IEEE Trans. CAS I: Fund. Theo. and Apps, vol. 40, no. 6, pp. 392–402, 1993.
[17] W. Ali, A. A. Ahmed, “ Hybrid intelligent phishing website prediction using deep neural networks with genetic algorithm-based feature selec-tion and weighting,” IET Information Security, vol. 13, no. 6, pp. 659 – 669, 2019.