Channel estimation based on neural network in space time block coded MIMO–OFDM system

• Published in: Digital signal processing Vol. 23; no. 1; pp. 275 - 280
• Main Authors: Seyman, Muhammet Nuri, Taşpınar, Necmi
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2013
• Subjects: Channel impulse response (CIR); Feed-forward neural network; Levenberg–Marquardt algorithm; MIMO–OFDM; Feed-forward neural network; Levenberg–Marquardt algorithm; Channel impulse response (CIR); MIMO–OFDM
• ISSN: 1051-2004; 1095-4333
• DOI: 10.1016/j.dsp.2012.08.003

In this study, we propose feed-forward multilayered perceptron (MLP) neural network trained with the Levenberg–Marquardt algorithm to estimate channel parameters in MIMO–OFDM systems. Bit error rate (BER) and mean square error (MSE) performances of least square (LS) and least mean square error (LMS) algorithms are also compared to our proposed neural network to evaluate the performances. Neural network channel estimator has got much better performance than LS and LMS algorithms. Furthermore it doesnʼt need channel statistics and sending pilot tones, contrary to classical algorithms.