Millimeter Wave Localization with Imperfect Training Data using Shallow Neural Networks

TL;DR

This paper introduces a shallow neural network for indoor millimeter wave localization that requires fewer training samples and less complex hardware, and it effectively leverages imperfect geometric localization estimates for training.

Contribution

The work presents a resource-efficient shallow neural network model that uses imperfect geometric localization data to achieve competitive accuracy in mmWave indoor localization.

Findings

The proposed neural network performs as well as or better than state-of-the-art methods.

It requires fewer training samples and less complex hardware.

It effectively utilizes imperfect geometric localization estimates for training.

Abstract

Millimeter wave (mmWave) localization algorithms exploit the quasi-optical propagation of mmWave signals, which yields sparse angular spectra at the receiver. Geometric approaches to angle-based localization typically require to know the map of the environment and the location of the access points. Thus, several works have resorted to automated learning in order to infer a device's location from the properties of the received mmWave signals. However, collecting training data for such models is a significant burden. In this work, we propose a shallow neural network model to localize mmWave devices indoors. This model requires significantly fewer weights than those proposed in the literature. Therefore, it is amenable for implementation in resource-constrained hardware, and needs fewer training samples to converge. We also propose to relieve training data collection efforts by retrieving (inherently imperfect) location estimates from geometry-based mmWave localization algorithms. Even in this case, our results show that the proposed neural networks perform as good as or better than state-of-the-art algorithms.