Attention Aided CSI Wireless Localization

TL;DR

This paper introduces an attention-based approach to CSI feature learning for wireless localization, enhancing robustness and performance in complex environments using deep neural networks.

Contribution

It proposes an attention mechanism for CSI feature extraction, improving localization accuracy and robustness over traditional raw CSI inputs in massive MIMO systems.

Findings

Attention-based CSI outperforms raw CSI in localization tasks.

The method achieves superior accuracy in non-stationary railway environments.

Robustness to environmental changes is significantly improved.

Abstract

Deep neural networks (DNNs) have become a popular approach for wireless localization based on channel state information (CSI). A common practice is to use the raw CSI in the input and allow the network to learn relevant channel representations for mapping to location information. However, various works show that raw CSI can be very sensitive to system impairments and small changes in the environment. On the contrary, hand-designing features may hinder the limits of channel representation learning of the DNN. In this work, we propose attention-based CSI for robust feature learning. We evaluate the performance of attended features in centralized and distributed massive MIMO systems for ray-tracing channels in two non-stationary railway track environments. By comparison to a base DNN, our approach provides exceptional performance.