Support Vector Machine Regression and Artificial Neural Network for Channel Estimation of LTE Downlink in High-Mobility Environments

  • Anis Charrada Carthage University
  • Abdel Aziz INRS, EMT Center, 800 de la Gauchetire W., Suite 6900, Montreal, QC, H5A 1K6, Canada
Keywords: Complex SVR, ANN, nonlinear noise, OFDM, LTE

Abstract

In this paper we apply and assess the performance of support vector machine regression (SVR) and  artificial neural network (ANN) channel estimation algorithms to the reference signal structure standardized for LTE Downlink system. SVR and ANN where applied to estimate real channel environment such as vehicular A channel defined by the International Telecommunications Union
(ITU) in the presence of nonlinear impulsive noise.The proposed algorithms use the information provided by the received reference symbols to estimate the total frequency response of the time variant multipath fading channel in two phases. In the first phase, each method learns to adapt to 
the channel variations, and in the second phase it predicts all the channel frequency responses.
Finally, in order to evaluate the capabilities of the designed channel estimators, we provide performance of SVR and ANN, which is compared with traditional Least Squares (LS) and Decision Feedback (DF). The simulation results show that SVRhas a better accuracy than other estimation techniques.

Author Biography

Anis Charrada, Carthage University

Anis Charrada received the B.S. degree in te-lecommunication engineering from The Academy
of Aviation (EABA), Tunisia, in 2007, and the
research master degree in Electrical Engineering
from the Engineering National School of Monas-tir (ENIM)/Monastir University, Tunisia, in 2010
and the Ph.D. degree from the Engineering National
School of Tunis (ENIT)/Tunis El Manar University,
Tunisia, in 2014. In 2015, he joined the Department
of Telecommunication Engineering, Tunisian Military Academy, as an Assis-tant Professor. His research interests span the general area of digital commu-nication and signal processing theories and its applications to performance
evaluation of mobile radio wireless communication systems such as LTE and
LTE-A. Current specific research interests include support vector machines,
neural networks, scheduling algorithms, IoT and 5G.

References

(1). Dahlman, E., S. Parkvall, J. Skold and P. Berning, 3G Evolution-HSPA and LTE for mobile broadband. 2nd edition 2008, New York: vol. Academic.

(2). Colieri, S., M. Ergen, A. Puri and A. Bahai. A study of channel estimation in OFDM systems. In Proceedings of the IEEE 56 th

Vehicular Technology Conference, 2002, vol. 2: p. 894–898.

(3). Colieri, S., M. Ergen, A. Puri and A. Bahai. Channel estimation techniques based on pilot arrangement in OFDM systems. IEEE Transactions on Broadcasting, 2002, vol. 48,no. 3: p. 223–229.

(4). Patra, J. C., R. N. Pal, R. Baliarsingh and G. Panda. Nonlinear channel equalization for QAM signal constellation using artificial neural networks. IEEE Transactions on Systems, Man, and Cybernetics,

, vol. 29, no. 2, p. 254–262.

(5). Naveed, A., I. M. Qureshi, T. A. Cheema, and A. Jalil. Blind equalization and estimation of channel using artificial neural network, 8th International Multitopic Conference, INMIC, 2004, p. 184–190.

(6). Fernández-Getino García, M. J., J. M. Páez-Borrallo, and S. Zazo. DFT-based channel estimation in 2D-pilot-symbol-aided OFDM wireless systems. IEEE Vehicular Technology Conf., 2001, vol. 2, p.815–819.

(7). Sliskovic, M. Signal processing algorithm for OFDM channel with impulse noise. IEEE conf. on Electronics, Circuits and Systems, 2000, p. 222–225.

(8). Rojo-Álvarez, J. L., C. Figuera-Pozuelo, C. E. Martínez-Cruz, G. Camps-Valls, F. Alonso-Atienza, M. Martínez-Ramón. Nonuniform interpolation of noisy signals using support vector machines. IEEE Trans.

Signal process., 2007, vol. 55, no.48, p. 4116–4126.

(9). Nanping, L., Y. Yuan, X. Kewen, and Z. Zhiwei. Study on channel estimation technology in OFDM system. IEEE Computer Society Conf., 2009, p. 773–776.

(10). Çiikli, C., A. T. Özsahin, A. C. Yapici. Artificial neural network channel estimation based on Levenberg-Marquardt for OFDM systems. Wireless Pers. Commun., 2009, p. 221–229.

(11). Charrada, A and A. Samet. Estimation of highly selective channels for OFDM system by complex least squares support vector machines. Int. J. Electron. Commun. (AEÜ), 2012, vol. 66, p. 687-692.

(12). Nanping, L., Y. Yuan, X. Kewen and Z. Zhiwei. Study on channel estimation technology in OFDM system. IEEE Computer Society Conf., 2009, p. 773–776.

(13). Charrada, A and A. Samet. Nonlinear Complex LS-SVM for Highly Selective OFDM Channel with Impulse Noise. 6th International Conference on Sciences of Electronics, Technologies of Information and

Telecommunications (SETIT), 2012, p. 696-700.

(14). Fernández-Getino García, M. J., J. L. Rojo-Álvarez,F. Alonso-Atienza, and M. Martínez-Ramón. Support vector machines for robust channel estimation in OFDM. IEEE signal process. J., 2006, vol. 13, no. 7.

(15). 3rd Generation Partnership Project. Technical Specification Group Radio Access Network: evolved Universal Terrestrial Radio Access (UTRA): Base Station (BS) radio transmission and reception. TS

104, September 2009, V8.7.0.

(16). 3rd Generation Partnership Project. Technical Specification Group Radio Access Network: evolved Universal Terrestrial Radio Access (UTRA): PhysicalChannels and Modulation layer. TS 36.211,

September 2009, V8.8.0.

(17). 3rd Generation Partnership Project. Technical Specification Group Radio Access Network: Physical layer aspects for evolved Universal Terrestrial Radio Access (UTRA). TR 25.814, September 2006, V7.1.0.

(18). 3rd Generation Partnership Project. Technical Specification Group Radio Access Network: evolved Universal Terrestrial Radio Access (UTRA): Physicallayer procedures. TS 36.213, September 2009,

V8.8.0

Published
2016-09-14
How to Cite
Charrada, A., & Aziz, A. (2016). Support Vector Machine Regression and Artificial Neural Network for Channel Estimation of LTE Downlink in High-Mobility Environments. Transactions on Machine Learning and Artificial Intelligence, 4(4), 36. https://doi.org/10.14738/tmlai.44.2145