Direction of Arrival Estimation Using Hybrid CNN-GRU

Abdulmajid Lawal; Kabiru N. Aliyu; Azzedine Zerguine; Ali Muqaibel

doi:10.1109/SSD64182.2025.10989880

Direction of Arrival Estimation Using Hybrid CNN-GRU

Abdulmajid Lawal, Kabiru N. Aliyu, Azzedine Zerguine, Ali Muqaibel

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

Abstract

This paper presents a novel hybrid deep-learning network for accurate direction of arrival (DOA) estimation. The proposed method leverages the columns of the covariance matrix to construct a model-assisted deep-learning framework, integrating the strengths of the Gated Recurrent Units (GRU) and the Convolutional Neural Networks (CNN). This hybrid architecture utilizes selected elements from the received signal's covariance matrix as input features, while the corresponding angles serve as labels for training. Numerical results demonstrate that the proposed method outperforms existing deep learning approaches, showcasing superior performance across various conditions.

Original language	English
Title of host publication	22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	574-577
Number of pages	4
ISBN (Electronic)	9798331542726
DOIs	https://doi.org/10.1109/SSD64182.2025.10989880
State	Published - 2025
Event	22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025 - Monastir, Tunisia Duration: 17 Feb 2025 → 20 Feb 2025

Publication series

Name	22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025

Conference

Conference	22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025
Country/Territory	Tunisia
City	Monastir
Period	17/02/25 → 20/02/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

Convolutional neural network
Direction of arrival
Gated recurrent unit

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems
Signal Processing
Safety, Risk, Reliability and Quality
Control and Optimization
Instrumentation

Access to Document

10.1109/SSD64182.2025.10989880

Cite this

Lawal, A., Aliyu, K. N., Zerguine, A., & Muqaibel, A. (2025). Direction of Arrival Estimation Using Hybrid CNN-GRU. In 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025 (pp. 574-577). (22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD64182.2025.10989880

@inproceedings{478987ae992245b7b78e87ad6e1658ba,

title = "Direction of Arrival Estimation Using Hybrid CNN-GRU",

abstract = "This paper presents a novel hybrid deep-learning network for accurate direction of arrival (DOA) estimation. The proposed method leverages the columns of the covariance matrix to construct a model-assisted deep-learning framework, integrating the strengths of the Gated Recurrent Units (GRU) and the Convolutional Neural Networks (CNN). This hybrid architecture utilizes selected elements from the received signal's covariance matrix as input features, while the corresponding angles serve as labels for training. Numerical results demonstrate that the proposed method outperforms existing deep learning approaches, showcasing superior performance across various conditions.",

keywords = "Convolutional neural network, Direction of arrival, Gated recurrent unit",

author = "Abdulmajid Lawal and Aliyu, {Kabiru N.} and Azzedine Zerguine and Ali Muqaibel",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025 ; Conference date: 17-02-2025 Through 20-02-2025",

year = "2025",

doi = "10.1109/SSD64182.2025.10989880",

language = "English",

series = "22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025",

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

pages = "574--577",

booktitle = "22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025",

address = "United States",

}

Lawal, A, Aliyu, KN, Zerguine, A & Muqaibel, A 2025, Direction of Arrival Estimation Using Hybrid CNN-GRU. in 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025. 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025, Institute of Electrical and Electronics Engineers Inc., pp. 574-577, 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025, Monastir, Tunisia, 17/02/25. https://doi.org/10.1109/SSD64182.2025.10989880

Direction of Arrival Estimation Using Hybrid CNN-GRU. / Lawal, Abdulmajid; Aliyu, Kabiru N.; Zerguine, Azzedine et al.
22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 574-577 (22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025).

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

TY - GEN

T1 - Direction of Arrival Estimation Using Hybrid CNN-GRU

AU - Lawal, Abdulmajid

AU - Aliyu, Kabiru N.

AU - Zerguine, Azzedine

AU - Muqaibel, Ali

PY - 2025

Y1 - 2025

N2 - This paper presents a novel hybrid deep-learning network for accurate direction of arrival (DOA) estimation. The proposed method leverages the columns of the covariance matrix to construct a model-assisted deep-learning framework, integrating the strengths of the Gated Recurrent Units (GRU) and the Convolutional Neural Networks (CNN). This hybrid architecture utilizes selected elements from the received signal's covariance matrix as input features, while the corresponding angles serve as labels for training. Numerical results demonstrate that the proposed method outperforms existing deep learning approaches, showcasing superior performance across various conditions.

AB - This paper presents a novel hybrid deep-learning network for accurate direction of arrival (DOA) estimation. The proposed method leverages the columns of the covariance matrix to construct a model-assisted deep-learning framework, integrating the strengths of the Gated Recurrent Units (GRU) and the Convolutional Neural Networks (CNN). This hybrid architecture utilizes selected elements from the received signal's covariance matrix as input features, while the corresponding angles serve as labels for training. Numerical results demonstrate that the proposed method outperforms existing deep learning approaches, showcasing superior performance across various conditions.

KW - Convolutional neural network

KW - Direction of arrival

KW - Gated recurrent unit

UR - http://www.scopus.com/inward/record.url?scp=105007283264&partnerID=8YFLogxK

U2 - 10.1109/SSD64182.2025.10989880

DO - 10.1109/SSD64182.2025.10989880

M3 - Conference contribution

AN - SCOPUS:105007283264

T3 - 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025

SP - 574

EP - 577

BT - 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025

Y2 - 17 February 2025 through 20 February 2025

ER -

Lawal A, Aliyu KN, Zerguine A , Muqaibel A. Direction of Arrival Estimation Using Hybrid CNN-GRU. In 22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 574-577. (22nd IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2025). doi: 10.1109/SSD64182.2025.10989880

Direction of Arrival Estimation Using Hybrid CNN-GRU

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this