A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks

Ben Marinberg; Ariel Cohen; Eilam Ben-Dror; Haim H. Permuter

doi:10.1109/ANTS50601.2020.9342797

A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks

Ben Marinberg, Ariel Cohen, Eilam Ben-Dror, Haim H. Permuter

Department of Electrical & Computer Engineering

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

11 Scopus citations

Abstract

In this paper we study the usage of Convolutional Neural Network (CNN) estimators for the task of Multiple-Input-Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) Channel Estimation (CE). Specifically, the CNN estimators interpolate the channel values of reference signals for estimating the channel of the full OFDM resource element (RE) matrix. We have designed a 2D CNN architecture based on U-net, and a 3D CNN architecture for handling spatial correlation. We investigate the performance of various CNN architectures for a diverse data set generated according to 5G NR standard, and in particular we investigate the influence of spatial correlation, Doppler and reference signal resource allocation. The CE CNN estimators are then integrated with MIMO detection algorithms for testing their influence on the system level Bit Error Rate (BER) performance.

Original language	English
Title of host publication	2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781728192901
DOIs	https://doi.org/10.1109/ANTS50601.2020.9342797
State	Published - 14 Dec 2020
Event	2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020 - New Delhi, India Duration: 14 Dec 2020 → 17 Dec 2020

Publication series

Name	International Symposium on Advanced Networks and Telecommunication Systems, ANTS
Volume	2020-December
ISSN (Print)	2153-1684

Conference

Conference	2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020
Country/Territory	India
City	New Delhi
Period	14/12/20 → 17/12/20

Keywords

2D CNN
3D CNN
Channel estimation
Deep learning
MIMO detection
Reference signal

ASJC Scopus subject areas

Computer Networks and Communications
Communication

Access to Document

10.1109/ANTS50601.2020.9342797

Cite this

Marinberg, B., Cohen, A., Ben-Dror, E., & Permuter, H. H. (2020). A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks. In 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020 Article 9342797 (International Symposium on Advanced Networks and Telecommunication Systems, ANTS; Vol. 2020-December). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ANTS50601.2020.9342797

Marinberg, Ben ; Cohen, Ariel ; Ben-Dror, Eilam et al. / A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks. 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020. Institute of Electrical and Electronics Engineers, 2020. (International Symposium on Advanced Networks and Telecommunication Systems, ANTS).

@inproceedings{5d320bba080b4f54bcd7309bb29c3084,

title = "A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks",

abstract = "In this paper we study the usage of Convolutional Neural Network (CNN) estimators for the task of Multiple-Input-Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) Channel Estimation (CE). Specifically, the CNN estimators interpolate the channel values of reference signals for estimating the channel of the full OFDM resource element (RE) matrix. We have designed a 2D CNN architecture based on U-net, and a 3D CNN architecture for handling spatial correlation. We investigate the performance of various CNN architectures for a diverse data set generated according to 5G NR standard, and in particular we investigate the influence of spatial correlation, Doppler and reference signal resource allocation. The CE CNN estimators are then integrated with MIMO detection algorithms for testing their influence on the system level Bit Error Rate (BER) performance.",

keywords = "2D CNN, 3D CNN, Channel estimation, Deep learning, MIMO detection, Reference signal",

author = "Ben Marinberg and Ariel Cohen and Eilam Ben-Dror and Permuter, \{Haim H.\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020 ; Conference date: 14-12-2020 Through 17-12-2020",

year = "2020",

month = dec,

day = "14",

doi = "10.1109/ANTS50601.2020.9342797",

language = "English",

series = "International Symposium on Advanced Networks and Telecommunication Systems, ANTS",

publisher = "Institute of Electrical and Electronics Engineers",

booktitle = "2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020",

address = "United States",

}

Marinberg, B, Cohen, A, Ben-Dror, E & Permuter, HH 2020, A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks. in 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020., 9342797, International Symposium on Advanced Networks and Telecommunication Systems, ANTS, vol. 2020-December, Institute of Electrical and Electronics Engineers, 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020, New Delhi, India, 14/12/20. https://doi.org/10.1109/ANTS50601.2020.9342797

A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks. / Marinberg, Ben; Cohen, Ariel; Ben-Dror, Eilam et al.
2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020. Institute of Electrical and Electronics Engineers, 2020. 9342797 (International Symposium on Advanced Networks and Telecommunication Systems, ANTS; Vol. 2020-December).

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

TY - GEN

T1 - A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks

AU - Marinberg, Ben

AU - Cohen, Ariel

AU - Ben-Dror, Eilam

AU - Permuter, Haim H.

PY - 2020/12/14

Y1 - 2020/12/14

N2 - In this paper we study the usage of Convolutional Neural Network (CNN) estimators for the task of Multiple-Input-Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) Channel Estimation (CE). Specifically, the CNN estimators interpolate the channel values of reference signals for estimating the channel of the full OFDM resource element (RE) matrix. We have designed a 2D CNN architecture based on U-net, and a 3D CNN architecture for handling spatial correlation. We investigate the performance of various CNN architectures for a diverse data set generated according to 5G NR standard, and in particular we investigate the influence of spatial correlation, Doppler and reference signal resource allocation. The CE CNN estimators are then integrated with MIMO detection algorithms for testing their influence on the system level Bit Error Rate (BER) performance.

AB - In this paper we study the usage of Convolutional Neural Network (CNN) estimators for the task of Multiple-Input-Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) Channel Estimation (CE). Specifically, the CNN estimators interpolate the channel values of reference signals for estimating the channel of the full OFDM resource element (RE) matrix. We have designed a 2D CNN architecture based on U-net, and a 3D CNN architecture for handling spatial correlation. We investigate the performance of various CNN architectures for a diverse data set generated according to 5G NR standard, and in particular we investigate the influence of spatial correlation, Doppler and reference signal resource allocation. The CE CNN estimators are then integrated with MIMO detection algorithms for testing their influence on the system level Bit Error Rate (BER) performance.

KW - 2D CNN

KW - 3D CNN

KW - Channel estimation

KW - Deep learning

KW - MIMO detection

KW - Reference signal

UR - https://www.scopus.com/pages/publications/85101262163

U2 - 10.1109/ANTS50601.2020.9342797

DO - 10.1109/ANTS50601.2020.9342797

M3 - Conference contribution

AN - SCOPUS:85101262163

T3 - International Symposium on Advanced Networks and Telecommunication Systems, ANTS

BT - 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020

PB - Institute of Electrical and Electronics Engineers

T2 - 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020

Y2 - 14 December 2020 through 17 December 2020

ER -

Marinberg B, Cohen A, Ben-Dror E, Permuter HH. A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks. In 2020 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2020. Institute of Electrical and Electronics Engineers. 2020. 9342797. (International Symposium on Advanced Networks and Telecommunication Systems, ANTS). doi: 10.1109/ANTS50601.2020.9342797

A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this