Machine Learning-Based Adaptive Receive Filtering: Proof-Of-Concept On An Sdr Platform

Conventional multiuser detection techniques either require a large number of antennas at the receiver for the desired performance, or they are too complex for practical implementation. Moreover, many of these techniques, such as successive interference cancellation (SIC), suffer from errors in parameter estimation (user channels, covariance matrix, noise variance, etc.) that are performed before the detection of user data symbols. As an alternative to conventional methods, this paper proposes and demonstrates a low-complexity practical machine learning-based receiver that achieves similar (and at times better) performance to the SIC receiver. The proposed receiver does not require parameter estimation. Instead, it uses supervised learning to detect user modulation symbols directly. We perform comparisons with minimum mean square error (MMSE) and SIC receivers in terms of symbol error rate (SER) and complexity.