A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network
This article aims to constitute a noteworthy contribution to the domain of direction-of-arrival (DoA) estimation through the application of deep learning algorithms. We approach the DoA estimation challenge as a binary classification task, employing a novel grid in the output layer and a deep convol...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Vehicular Technology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10504989/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582347760861184 |
|---|---|
| author | Constantinos M. Mylonakis Zaharias D. Zaharis |
| author_facet | Constantinos M. Mylonakis Zaharias D. Zaharis |
| author_sort | Constantinos M. Mylonakis |
| collection | DOAJ |
| description | This article aims to constitute a noteworthy contribution to the domain of direction-of-arrival (DoA) estimation through the application of deep learning algorithms. We approach the DoA estimation challenge as a binary classification task, employing a novel grid in the output layer and a deep convolutional neural network (DCNN) as the classifier. The input of the DCNN is the correlation matrix of signals received by a <inline-formula><tex-math notation="LaTeX">$4 \times 4$</tex-math></inline-formula> uniformly spaced patch antenna array. The proposed model's performance is evaluated based on its capacity to predict angles of arrival from any direction in a three-dimensional space, encompassing azimuth angles within the interval <inline-formula><tex-math notation="LaTeX">$[0^\circ, 360^\circ)$</tex-math></inline-formula> and polar angles within <inline-formula><tex-math notation="LaTeX">$[0^\circ, 60^\circ ]$</tex-math></inline-formula>. We aim to optimize the utilization of spatial information and create a robust, precise, and efficient DoA estimator. To address this, we conduct comprehensive testing in diverse scenarios, encompassing the simultaneous reception of multiple signals across a wide range of signal-to-noise ratio values. Both mean absolute error and root mean squared error are calculated to assess the performance of the DCNN. Rigorous comparison with conventional and state-of-the-art endeavors emphasizes the proposed model's efficacy. |
| format | Article |
| id | doaj-art-f4717cfa40ef4bc6bbd9876328f739c4 |
| institution | Kabale University |
| issn | 2644-1330 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Vehicular Technology |
| spelling | doaj-art-f4717cfa40ef4bc6bbd9876328f739c42025-01-30T00:04:31ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302024-01-01564365710.1109/OJVT.2024.339083310504989A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural NetworkConstantinos M. Mylonakis0https://orcid.org/0009-0006-6080-1995Zaharias D. Zaharis1https://orcid.org/0000-0002-4548-282XSchool of Electrical, Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceSchool of Electrical, Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceThis article aims to constitute a noteworthy contribution to the domain of direction-of-arrival (DoA) estimation through the application of deep learning algorithms. We approach the DoA estimation challenge as a binary classification task, employing a novel grid in the output layer and a deep convolutional neural network (DCNN) as the classifier. The input of the DCNN is the correlation matrix of signals received by a <inline-formula><tex-math notation="LaTeX">$4 \times 4$</tex-math></inline-formula> uniformly spaced patch antenna array. The proposed model's performance is evaluated based on its capacity to predict angles of arrival from any direction in a three-dimensional space, encompassing azimuth angles within the interval <inline-formula><tex-math notation="LaTeX">$[0^\circ, 360^\circ)$</tex-math></inline-formula> and polar angles within <inline-formula><tex-math notation="LaTeX">$[0^\circ, 60^\circ ]$</tex-math></inline-formula>. We aim to optimize the utilization of spatial information and create a robust, precise, and efficient DoA estimator. To address this, we conduct comprehensive testing in diverse scenarios, encompassing the simultaneous reception of multiple signals across a wide range of signal-to-noise ratio values. Both mean absolute error and root mean squared error are calculated to assess the performance of the DCNN. Rigorous comparison with conventional and state-of-the-art endeavors emphasizes the proposed model's efficacy.https://ieeexplore.ieee.org/document/10504989/Direction-of-arrival (DoA) estimationconvolutional neural network (CNN)deep learning (DL)binary classificationantenna array analysis and synthesisspatial signal processing |
| spellingShingle | Constantinos M. Mylonakis Zaharias D. Zaharis A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network IEEE Open Journal of Vehicular Technology Direction-of-arrival (DoA) estimation convolutional neural network (CNN) deep learning (DL) binary classification antenna array analysis and synthesis spatial signal processing |
| title | A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network |
| title_full | A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network |
| title_fullStr | A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network |
| title_full_unstemmed | A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network |
| title_short | A Novel Three-Dimensional Direction-of-Arrival Estimation Approach Using a Deep Convolutional Neural Network |
| title_sort | novel three dimensional direction of arrival estimation approach using a deep convolutional neural network |
| topic | Direction-of-arrival (DoA) estimation convolutional neural network (CNN) deep learning (DL) binary classification antenna array analysis and synthesis spatial signal processing |
| url | https://ieeexplore.ieee.org/document/10504989/ |
| work_keys_str_mv | AT constantinosmmylonakis anovelthreedimensionaldirectionofarrivalestimationapproachusingadeepconvolutionalneuralnetwork AT zahariasdzaharis anovelthreedimensionaldirectionofarrivalestimationapproachusingadeepconvolutionalneuralnetwork AT constantinosmmylonakis novelthreedimensionaldirectionofarrivalestimationapproachusingadeepconvolutionalneuralnetwork AT zahariasdzaharis novelthreedimensionaldirectionofarrivalestimationapproachusingadeepconvolutionalneuralnetwork |