A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios

Zhi Wei Tan; Yuan Liu; Andy W.H. Khong

doi:10.23919/APSIPAASC55919.2022.9980340

A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios

Zhi Wei Tan, Yuan Liu, Andy W.H. Khong

Nanyang Technological University

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

3 Citations (Scopus)

Abstract

This paper addresses the direction-of-arrival (DOA) estimation-based source localization problem by using the convolutional neural network (CNN) and root-MUltiple SIgnal Classification (MUSIC) technique. Existing grid-less neural network-based approach employs a LeNet-based CNN, where its network complexity depends on the number of sensors. To overcome this issue, we propose a LeDIM-net CNN that works for a uniform linear array with an arbitrary number of sensors. The proposed LeDIM-net architecture maintains spatial resolution throughout the network while exploiting non-local spatial information. Simulation results demonstrate the effectiveness of the proposed LeDIM-net over the existing grid-less LeNet-based approach and root-MUSIC at low SNRs for arrays with different sensors by maintaining the same network complexity.

Original language	English
Title of host publication	Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	760-764
Number of pages	5
ISBN (Electronic)	9786165904773
DOIs	https://doi.org/10.23919/APSIPAASC55919.2022.9980340
Publication status	Published - 2022
Externally published	Yes
Event	2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 - Chiang Mai, Thailand Duration: Nov 7 2022 → Nov 10 2022

Publication series

Name	Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

Conference

Conference	2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
Country/Territory	Thailand
City	Chiang Mai
Period	11/7/22 → 11/10/22

Bibliographical note

Publisher Copyright:
© 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).

ASJC Scopus Subject Areas

Computer Networks and Communications
Information Systems
Signal Processing

Keywords

array signal processing
convolution neural network
deep learning
Direction-of-arrival (DOA) estimation
gridless DOA estimation

Access to Document

10.23919/APSIPAASC55919.2022.9980340

Cite this

Tan, Z. W., Liu, Y., & Khong, A. W. H. (2022). A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios. In Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 (pp. 760-764). (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPAASC55919.2022.9980340

Tan, Zhi Wei ; Liu, Yuan ; Khong, Andy W.H. / A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 760-764 (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

@inproceedings{007ea4aab194496e889b79f3340c2cdd,

title = "A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios",

abstract = "This paper addresses the direction-of-arrival (DOA) estimation-based source localization problem by using the convolutional neural network (CNN) and root-MUltiple SIgnal Classification (MUSIC) technique. Existing grid-less neural network-based approach employs a LeNet-based CNN, where its network complexity depends on the number of sensors. To overcome this issue, we propose a LeDIM-net CNN that works for a uniform linear array with an arbitrary number of sensors. The proposed LeDIM-net architecture maintains spatial resolution throughout the network while exploiting non-local spatial information. Simulation results demonstrate the effectiveness of the proposed LeDIM-net over the existing grid-less LeNet-based approach and root-MUSIC at low SNRs for arrays with different sensors by maintaining the same network complexity.",

keywords = "array signal processing, convolution neural network, deep learning, Direction-of-arrival (DOA) estimation, gridless DOA estimation",

author = "Tan, \{Zhi Wei\} and Yuan Liu and Khong, \{Andy W.H.\}",

note = "Publisher Copyright: {\textcopyright} 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).; 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 ; Conference date: 07-11-2022 Through 10-11-2022",

year = "2022",

doi = "10.23919/APSIPAASC55919.2022.9980340",

language = "English",

series = "Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "760--764",

booktitle = "Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022",

address = "United States",

}

Tan, ZW, Liu, Y & Khong, AWH 2022, A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios. in Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 760-764, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022, Chiang Mai, Thailand, 11/7/22. https://doi.org/10.23919/APSIPAASC55919.2022.9980340

A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios. / Tan, Zhi Wei; Liu, Yuan; Khong, Andy W.H.
Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 760-764 (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

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

TY - GEN

T1 - A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios

AU - Tan, Zhi Wei

AU - Liu, Yuan

AU - Khong, Andy W.H.

PY - 2022

Y1 - 2022

N2 - This paper addresses the direction-of-arrival (DOA) estimation-based source localization problem by using the convolutional neural network (CNN) and root-MUltiple SIgnal Classification (MUSIC) technique. Existing grid-less neural network-based approach employs a LeNet-based CNN, where its network complexity depends on the number of sensors. To overcome this issue, we propose a LeDIM-net CNN that works for a uniform linear array with an arbitrary number of sensors. The proposed LeDIM-net architecture maintains spatial resolution throughout the network while exploiting non-local spatial information. Simulation results demonstrate the effectiveness of the proposed LeDIM-net over the existing grid-less LeNet-based approach and root-MUSIC at low SNRs for arrays with different sensors by maintaining the same network complexity.

AB - This paper addresses the direction-of-arrival (DOA) estimation-based source localization problem by using the convolutional neural network (CNN) and root-MUltiple SIgnal Classification (MUSIC) technique. Existing grid-less neural network-based approach employs a LeNet-based CNN, where its network complexity depends on the number of sensors. To overcome this issue, we propose a LeDIM-net CNN that works for a uniform linear array with an arbitrary number of sensors. The proposed LeDIM-net architecture maintains spatial resolution throughout the network while exploiting non-local spatial information. Simulation results demonstrate the effectiveness of the proposed LeDIM-net over the existing grid-less LeNet-based approach and root-MUSIC at low SNRs for arrays with different sensors by maintaining the same network complexity.

KW - array signal processing

KW - convolution neural network

KW - deep learning

KW - Direction-of-arrival (DOA) estimation

KW - gridless DOA estimation

UR - http://www.scopus.com/inward/record.url?scp=85146294572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85146294572&partnerID=8YFLogxK

U2 - 10.23919/APSIPAASC55919.2022.9980340

DO - 10.23919/APSIPAASC55919.2022.9980340

M3 - Conference contribution

AN - SCOPUS:85146294572

T3 - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

SP - 760

EP - 764

BT - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

Y2 - 7 November 2022 through 10 November 2022

ER -

Tan ZW, Liu Y, Khong AWH. A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios. In Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 760-764. (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022). doi: 10.23919/APSIPAASC55919.2022.9980340

A Dilated Inception Convolutional Neural Network for Gridless DOA Estimation Under Low SNR Scenarios

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this