Similarity-based prediction for channel mapping and user positioning
This work addresses the problem of optimizing wireless network efficiency for base stations by predicting user locations and downlink channels.
This paper proposes a supervised machine learning approach to predict user locations and downlink channels from uplink channel measurements. The method achieves better results than previous approaches at a lower computational cost on realistic channel data.
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, a supervised machine learning approach addressing these tasks in an unified way is proposed. 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 initialized with a non-parametric estimator. 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.