Low-dimensional Representation Learning for Wireless CSI-based Localisation

In this work, we investigate the potential of deep feedforward neural networks for user position estimation for a multi-path directional channel model in presence as well as absence of the line of sight path. Furthermore, we take advantage of a triplet network architecture combined with a triplet loss function, which allows us to exploit intrinsic properties of channel state information. We show that despite the high-dimensional nature of CSI, the proposed network can be trained to learn from the low-dimensional space and with less amount of training samples compared to the long-established approaches in the literature for fingerprinting localization. Finally, in order to investigate the performance and emphasize the benefits of triplet loss, we compare it to another network based on classification.