Semi-supervised Localisation utilizing CSI at Large Antenna Array Base Stations

Conference: WSA 2020 - 24th International ITG Workshop on Smart Antennas
02/18/2020 - 02/20/2020 at Hamburg, Germany

Proceedings: ITG-Fb. 291: WSA 2020

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Salihu, Artan; Schwarz, Stefan (Institute of Telecommunications & Christian Doppler Laboratory for Dependable Wireless Connectivity for the Society in Motion, Technische Universität Wien, Austria)
Rupp, Markus (Institute of Telecommunications, Technische Universität Wien, Austria)

In this paper we present a localization method that exploits intrinsic properties of channel state information (CSI) acquired at a massive MIMO base station. This method combines dimensionality reduction techniques to extract spatial information with trilateration on K-reference locations to estimate the position of the transmitter. We show that the map constructed by dimensionality reduction techniques can be utilized to achieve different levels of accuracy solely from CSI samples from different transmitters depending on the density of reference point locations.