Simple and Effective Augmentation Methods for CSI Based Indoor Localization

TL;DR

This paper introduces two simple data augmentation techniques for CSI-based indoor localization that significantly reduce data collection efforts and improve localization accuracy, demonstrating effectiveness with real WiFi datasets.

Contribution

It proposes novel, physically motivated data augmentation algorithms that enhance ML-based indoor localization performance with minimal additional data collection.

Findings

Reducing dataset size to 10% maintains original accuracy.

Augmentation improves test accuracy over three times.

Effective with real WiFi indoor measurement data.

Abstract

Indoor localization is a challenging task. Compared to outdoor environments where GPS is dominant, there is no robust and almost-universal approach. Recently, machine learning (ML) has emerged as the most promising approach for achieving accurate indoor localization. Nevertheless, its main challenge is requiring large datasets to train the neural networks. The data collection procedure is costly and laborious, requiring extensive measurements and labeling processes for different indoor environments. The situation can be improved by Data Augmentation (DA), a general framework to enlarge the datasets for ML, making ML systems more robust and increasing their generalization capabilities. This paper proposes two simple yet surprisingly effective DA algorithms for channel state information (CSI) based indoor localization motivated by physical considerations. We show that the number of measurements for a given accuracy requirement may be decreased by an order of magnitude. Specifically, we demonstrate the algorithm's effectiveness by experiments conducted with a measured indoor WiFi measurement dataset. As little as 10% of the original dataset size is enough to get the same performance as the original dataset. We also showed that if we further augment the dataset with the proposed techniques, test accuracy is improved more than three-fold.