Similarity-based prediction for channel mapping and user positioning
Abstract
In a wireless network, gathering information at the base station about mobile users based only on uplink channel measurements is an interesting challenge. Indeed, accessing the users locations and predicting their downlink channels would be particularly useful in order to optimize the network efficiency. In this paper, we propose a supervised machine learning approach addressing these tasks in an unified way. It relies on a labeled database that can be acquired in a simple way by the base station while operating. The proposed regression method can be seen as a computationally efficient two layers neural network. It is illustrated on realistic channel data, both for the positioning and channel mapping tasks, achieving better results than previously proposed approaches, at a lower cost.
Fichier principal
sim_based_pred.pdf (222.99 Ko)
Télécharger le fichier
channel_mapping.pdf (13.81 Ko)
Télécharger le fichier
localization.pdf (15.12 Ko)
Télécharger le fichier
localization_hist.pdf (14.13 Ko)
Télécharger le fichier
schema_sim_pred.pdf (41.27 Ko)
Télécharger le fichier
| Origin | Files produced by the author(s) |
|---|
| Origin | Files produced by the author(s) |
|---|