Deep convolutional neural networks for massive MIMO fingerprint-based positioning

Joao Vieira; Erik Leitinger; Muris Sarajlic; Xuhong Li; Fredrik Tufvesson

doi:10.1109/PIMRC.2017.8292280

Deep convolutional neural networks for massive MIMO fingerprint-based positioning

Joao Vieira, Erik Leitinger, Muris Sarajlic, Xuhong Li, Fredrik Tufvesson

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

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.

Original language	English
Title of host publication	2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC
Publisher	Institute of Electrical and Electronics Engineers
Pages	1 - 6
Number of pages	6
ISBN (Electronic)	978-153863531-5
DOIs	https://doi.org/10.1109/PIMRC.2017.8292280
Publication status	Published - Feb 2018
Externally published	Yes
Event	28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: PIMRC 2017 - Montreal, Canada Duration: 8 Oct 2017 → 13 Oct 2017

Conference

Conference	28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications
Country/Territory	Canada
City	Montreal
Period	8/10/17 → 13/10/17

Keywords

stat.ML
cs.IT
math.IT

Access to Document

10.1109/PIMRC.2017.8292280

https://arxiv.org/abs/1708.06235

Cite this

Vieira, J., Leitinger, E., Sarajlic, M., Li, X., & Tufvesson, F. (2018). Deep convolutional neural networks for massive MIMO fingerprint-based positioning. In 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC (pp. 1 - 6). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/PIMRC.2017.8292280

Deep convolutional neural networks for massive MIMO fingerprint-based positioning. / Vieira, Joao; Leitinger, Erik; Sarajlic, Muris; Li, Xuhong; Tufvesson, Fredrik.

2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC. Institute of Electrical and Electronics Engineers, 2018. p. 1 - 6.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Vieira, J, Leitinger, E, Sarajlic, M, Li, X & Tufvesson, F 2018, Deep convolutional neural networks for massive MIMO fingerprint-based positioning. in 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC. Institute of Electrical and Electronics Engineers, pp. 1 - 6, 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, Montreal, Quebec, Canada, 8/10/17. https://doi.org/10.1109/PIMRC.2017.8292280

@inproceedings{b9aea2dce098459e9207391b8adf1ae3,

title = "Deep convolutional neural networks for massive MIMO fingerprint-based positioning",

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. ",

keywords = "stat.ML, cs.IT, math.IT",

author = "Joao Vieira and Erik Leitinger and Muris Sarajlic and Xuhong Li and Fredrik Tufvesson",

note = "Accepted in the IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) 2017; 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications : PIMRC 2017 ; Conference date: 08-10-2017 Through 13-10-2017",

year = "2018",

month = feb,

doi = "10.1109/PIMRC.2017.8292280",

language = "English",

pages = "1 -- 6",

booktitle = "2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - Deep convolutional neural networks for massive MIMO fingerprint-based positioning

AU - Vieira, Joao

AU - Leitinger, Erik

AU - Sarajlic, Muris

AU - Li, Xuhong

AU - Tufvesson, Fredrik

N1 - Accepted in the IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) 2017

PY - 2018/2

Y1 - 2018/2

N2 - 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.

AB - 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.

KW - stat.ML

KW - cs.IT

KW - math.IT

U2 - 10.1109/PIMRC.2017.8292280

DO - 10.1109/PIMRC.2017.8292280

M3 - Conference paper

SP - 1

EP - 6

BT - 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC

PB - Institute of Electrical and Electronics Engineers

T2 - 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications

Y2 - 8 October 2017 through 13 October 2017

ER -

Deep convolutional neural networks for massive MIMO fingerprint-based positioning

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this