Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.17284545 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902204964667392 |
|---|---|
| author | Mylonakis, Constantinos Evangelidis, Nikolaos Velanas, Pantelis Margariti, Aikaterini Lazaridis, Pavlos Kantartzis, Nikolaos V. Goudos, Sotirios Zaharis, Zaharias |
| author_facet | Mylonakis, Constantinos Evangelidis, Nikolaos Velanas, Pantelis Margariti, Aikaterini Lazaridis, Pavlos Kantartzis, Nikolaos V. Goudos, Sotirios Zaharis, Zaharias |
| contents | <p>Accurate and computationally efficient direction-ofarrival (DoA) estimation remains a fundamental requirement in wireless communications, radar, and array signal processing. This paper presents novel residual network, a deep learning architecture that incorporates ghost blocks and squeeze-andexcitation (SE) modules into the ResNet framework to address the trade-off between accuracy and complexity. The introduction of ghost blocks reduces parameters and floating-point operations by approximately 50%, while SE modules improve feature discrimination with negligible overhead. Experimental evaluations demonstrate that the proposed architecture achieves high estimation accuracy, with F1 scores reaching 96.80% in single-signal scenarios and 89.21% with five simultaneous signals, alongside mean absolute errors between 0.016◦ and 0.161◦. The proposed approach thus provides a balanced solution that combines precision with computational efficiency, supporting real-time deployment.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17284545 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Lightweight Residual Networks with Ghost Blocks for Efficient Direction-of-Arrival Estimation Mylonakis, Constantinos Evangelidis, Nikolaos Velanas, Pantelis Margariti, Aikaterini Lazaridis, Pavlos Kantartzis, Nikolaos V. Goudos, Sotirios Zaharis, Zaharias direction of arrival deep learning <p>Accurate and computationally efficient direction-ofarrival (DoA) estimation remains a fundamental requirement in wireless communications, radar, and array signal processing. This paper presents novel residual network, a deep learning architecture that incorporates ghost blocks and squeeze-andexcitation (SE) modules into the ResNet framework to address the trade-off between accuracy and complexity. The introduction of ghost blocks reduces parameters and floating-point operations by approximately 50%, while SE modules improve feature discrimination with negligible overhead. Experimental evaluations demonstrate that the proposed architecture achieves high estimation accuracy, with F1 scores reaching 96.80% in single-signal scenarios and 89.21% with five simultaneous signals, alongside mean absolute errors between 0.016◦ and 0.161◦. The proposed approach thus provides a balanced solution that combines precision with computational efficiency, supporting real-time deployment.</p> |
| title | Lightweight Residual Networks with Ghost Blocks for Efficient Direction-of-Arrival Estimation |
| topic | direction of arrival deep learning |
| url | https://doi.org/10.5281/zenodo.17284545 |