Deep Learning Based Cooperative MIMO Systems for Wireless Body Area Networks

Abstract

Wireless Body Area Network (WBAN) is widely applied in various fields, including healthcare, sports, wellness, and assistive technologies, by offering the benefits of convenience, reliability, low latency, privacy, and customization. However, the propagation characteristics of the WBAN channel can impact the reliability of transmission, which is particularly crucial in healthcare systems. To address this issue, this article presents a novel approach using deep learning-based cooperative Multiple-Input Multiple-Output (MIMO) systems that leverage the autoencoder (AE) technique. In our proposed approach, we utilize the AE-based cooperative MIMO systems with two different techniques: Amplify-and-Forward (AE-AF) and Decode-and-Forward (AE-DF). The AE-AF scheme operates without needing training parameters at the relay node, whereas the AE-DF scheme necessitates training parameters at the relay node. Both schemes aim to overcome challenges such as multipath propagation phenomena, thereby enhancing the performance of on-body communication systems. Additionally, we introduce two combinators, Minimum Mean Square Error (MMSE) scheme and Radio Transformation Network (RTN), to effectively mitigate co-channel interference (CCI) in the received signal streams and improve the bit error rate performance of the AE-AF and AE-DF systems. We assess the performance of these systems in scenarios with and without direct links. Simulation results demonstrate significant performance improvements compared to baseline cooperative MIMO systems using MMSE combining, namely AF-MMSE and DF-MMSE systems. Notably, the proposed systems employing RTN combination, including both direct and relay paths, achieve a 7.5 dB gain over the baseline when all nodes are equipped with two transceiver antennas.