Seyman, Muhammet NuriTaspinar, Necmi2020-06-252020-06-252013closedAccess1051-20041095-4333https://doi.org/10.1016/j.dsp.2012.08.003https://hdl.handle.net/20.500.12587/5667In 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 doesn't need channel statistics and sending pilot tones, contrary to classical algorithms. Crown Copyright (C) 2012 Published by Elsevier Inc. All rights reserved.eninfo:eu-repo/semantics/closedAccessMIMO-OFDMFeed-forward neural networkChannel impulse response (CIR)Levenberg-Marquardt algorithmArticle23127528010.1016/j.dsp.2012.08.0032-s2.0-84869497336Q1WOS:000312171000026Q2