Reconfigurable Intelligent Surfaces and Machine Learning for Wireless Fingerprinting Localization

TL;DR

This paper introduces a method combining reconfigurable intelligent surfaces and machine learning to improve wireless fingerprinting localization by generating differentiable radio maps and reducing complexity for better accuracy.

Contribution

It presents a novel approach that exploits RIS diversity and machine learning for efficient, accurate wireless localization with reduced computational complexity.

Findings

Enhanced localization accuracy through RIS-based radio map differentiation

Reduced complexity via machine learning feature selection

Validated approach with radio propagation simulations

Abstract

Reconfigurable Intelligent Surfaces (RISs) promise improved, secure and more efficient wireless communications. We propose and demonstrate how to exploit the diversity offered by RISs to generate and select easily differentiable radio maps for use in wireless fingerprinting localization applications. Further, we apply machine learning feature selection methods to prune the large state space of the RIS, thus reducing complexity and enhancing localization accuracy and position acquisition time. We evaluate our proposed approach by generation of radio maps with a novel radio propagation modelling and simulations.