Accuracy-Aware Compression of Channel Impulse Responses using Deep Learning

Ultra-wideband (UWB) systems based on Channel State Information (CSI) estimate the position of mobile nodes within an environment by using Channel Impulse Responses (CIRs) of multiple stationary nodes. These contain spatial information caused by environment interactions such as reflections and scattering. To estimate positions from CSI of stationary nodes, we must transmit them to a centralized node. This introduces considerable communication overhead.We present a large-scale study to determine whether CSI can be compressed into a small set of underlying latent variables that describe the most valuable information. We evaluate multiple neural network architectures containing encoding (compressing) and decoding (reconstructing) components and compare them to the state-of-the-art compression techniques Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT). We show that fully connected autoencoders achieve the lowest error, outperforming both DCT and DWT. Further experiments prove that the reconstructed CSI can be used for positioning with only mild performance deterioration at a compression of >97% and even when trained on a different environment.

I. Introduction

Precise radio frequency (RF) indoor positioning systems (IPS) are key to many location-based services such as indoor navigation and object tracking [1]. Recently, Ultra-wideband (UWB) gained a lot of attention as an accurate and resilient, yet cost-efficient technology [2], [3]. While under ideal line-of-sight (LOS) conditions UWB ranging may yield sub-centimeter accuracy [2], non-line-of-sight (NLOS) propagation caused by obstructions and reflections is still challenging.