Channel Estimation and Data Detection Using Machine Learning for MIMO 5G Communication Systems in Fading Channel

In multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems, multi-user detection (MUD) algorithms play an important role in reducing the effect of multi-access interference (MAI). A combination of the estimation of channel and multi-user detection is proposed for eliminating various interferences and reduce the bit error rate (BER). First, a novel sparse based k-nearest neighbor classifier is proposed to estimate the unknown activity factor at a high data rate. The active users are continuously detected and their data are decoded at the base station (BS) receiver. The activity detection considers both the pilot and data symbols. Second, an optimal pilot allocation method is suggested to select the minimum mutual coherence in the measurement matrix for optimal pilot placement. The suggested algorithm for designing pilot patterns significantly improves the results in terms of mean square error (MSE), symbol error rate (SER) and bit error rate for channel detection. An optimal pilot placement reduces the computational complexity and maximizes the accuracy of the system. The performance of the channel estimation (CE) and MUD for the proposed scheme was good as it provided significant results, which were validated through simulations.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.