Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning

Vieira, Joao LU ; Leitinger, Erik LU ; Sarajlic, Muris LU ; Li, Xuhong LU and Tufvesson, Fredrik LU orcid (2018) 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2017
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, measured 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.
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017.
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2017
conference location
Montreal, Canada
conference dates
2017-10-08 - 2017-10-13
external identifiers
  • scopus:85045258482
DOI
10.1109/PIMRC.2017.8292280
language
English
LU publication?
yes
id
4e3ace37-4634-414e-be93-a26fd6d96e5d
date added to LUP
2017-06-14 11:24:42
date last changed
2025-10-14 10:33:00
@inproceedings{4e3ace37-4634-414e-be93-a26fd6d96e5d,
  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, measured 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.}},
  author       = {{Vieira, Joao and Leitinger, Erik and Sarajlic, Muris and Li, Xuhong and Tufvesson, Fredrik}},
  booktitle    = {{28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017.}},
  language     = {{eng}},
  month        = {{02}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning}},
  url          = {{http://dx.doi.org/10.1109/PIMRC.2017.8292280}},
  doi          = {{10.1109/PIMRC.2017.8292280}},
  year         = {{2018}},
}