Reconfigurable Intelligent Surfaces and Machine Learning for Wireless Fingerprinting Localization
This work addresses localization challenges in wireless communications, but it appears incremental as it builds on existing RIS and machine learning techniques.
The paper tackled the problem of wireless fingerprinting localization by using Reconfigurable Intelligent Surfaces (RISs) to generate differentiable radio maps and applying machine learning for feature selection, resulting in reduced complexity and enhanced localization accuracy and acquisition time.
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.