Rafael Aguiar got the paper “A Deep Learning Approach in RIS-based Indoor Localization” accepted at the European Conference on Networks and Communications (EuCNC 2024), co-authored by Nuno Paulino and Luís M. Pessoa. This research is part of the ongoing TERRAMETA project.
This work focuses on the domain of Reconfigurable Intelligent Surfaces (RIS)-based indoor localization. The paper introduces two distinct approaches. The first method is based on deep learning employing a Long Short-Term Memory (LSTM) network. The second method, a novel LSTM-PSO hybrid, strategically uses deep learning and optimization techniques. The simulations encompass practical scenarios, including variations in RIS placement and the intricate dynamics of multipath effects, all in non-line-of-sight conditions. The proposed methods can achieve very high reliability, obtaining centimeter-level accuracy.
Congratulations!