Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform

TL;DR

This paper introduces a low-complexity machine learning-based receiver for multiuser detection that directly detects user symbols without parameter estimation, demonstrating comparable or better performance than traditional SIC methods.

Contribution

It presents a novel ML-based receiver that bypasses parameter estimation, simplifying implementation and maintaining high detection accuracy in multiuser scenarios.

Findings

ML-based receiver achieves similar or better SER than SIC.

The proposed method reduces complexity compared to traditional techniques.

No parameter estimation required for the ML receiver.

Abstract

Conventional multiuser detection techniques either require a large number of antennas at the receiver for a 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 is performed before detection of user data symbols. As an alternative to conventional methods, this paper proposes and demonstrates a low-complexity practical Machine Learning (ML) 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 the 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.