Abstract
This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning purposes. We evaluate the positioning accuracy of state-of-the-art CNNs with channel fingerprints generated from a channel model with a rich clustered structure: the COST 2100 channel model. We find that moderately deep CNNs can achieve fractional-wavelength positioning accuracies, provided that an enough representative data set is available for training.
Originalsprache | englisch |
---|---|
Titel | 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC |
Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers |
Seiten | 1 - 6 |
Seitenumfang | 6 |
ISBN (elektronisch) | 978-153863531-5 |
DOIs | |
Publikationsstatus | Veröffentlicht - Feb. 2018 |
Extern publiziert | Ja |
Veranstaltung | 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: PIMRC 2017 - Montreal, Kanada Dauer: 8 Okt. 2017 → 13 Okt. 2017 |
Konferenz
Konferenz | 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications |
---|---|
Land/Gebiet | Kanada |
Ort | Montreal |
Zeitraum | 8/10/17 → 13/10/17 |