Data Augmentation and Attention for massive MIMO-based Indoor Localization in Changing Environments

TL;DR

This paper presents data augmentation and attention mechanisms to improve massive MIMO indoor localization accuracy in dynamic environments, achieving near-static accuracy levels without training on changing scenarios.

Contribution

It introduces novel data augmentation techniques and attention modules to enhance deep learning models for indoor localization in changing environments.

Findings

Localization error reduced from 286 mm to 66 mm with proposed methods.

Models trained with data augmentation and attention perform well in dynamic scenarios.

High accuracy maintained without training data from changing environments.

Abstract

The demand for high-precision indoor localization has grown significantly with the rise of smart environments, industrial automation, and location-aware applications. While massive Multiple-Input and Multiple-Output (MIMO) systems enable millimeter-level accuracy by leveraging rich Channel State Information (CSI), most existing solutions are optimized for static environments, where users or devices remain fixed during data collection and inference. Real-world applications, however, often require real-time localization in changing environments, where rapid movement, unpredictable blockages, and dynamic channel conditions pose significant challenges. To address these challenges, we introduce two data augmentation techniques designed to resemble blocked antennas, enhancing the generalizability of localization models to dynamic scenarios. Additionally, we enhance an existing Deep Learning (DL) model by incorporating attention modules, improving its ability to focus on relevant channel features and antennas. We train our model on data from a static scenario, augmented with the proposed techniques, and evaluate it on a dataset collected in changing scenarios. We investigate the performance enhancements achieved by the data augmentation techniques and the Attention modules, and observe a localization accuracy improvement from a mean error of 286 mm, when trained without Attention and without data augmentations, to 66 mm, when trained with Attention and data augmentation. This shows that high localization accuracy can be maintained in changing environments, even without training data from those scenarios.