EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations

Constantinos M. Mylonakis, Pantelis Velanas, Pavlos I. Lazaridis, Panagiotis Sarigiannidis, Sotirios K. Goudos, Zaharias D. Zaharis

Technologies · 24.01.2025 · 13 (2) · 46

DOI: 10.3390/technologies13020046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 24.01.2025. Verfasst von Constantinos M. Mylonakis und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union, through the Horizon Europe Marie Skłodowska-Curie Staff Exchanges Programme “6G intelligent connectivity and interaction for users and infrastr….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid advancement of wireless communication systems and the increasing need for accurate, real-time signal processing have driven innovations in direction-of-arrival (DoA) estimation techniques. This paper introduces a novel convolutional neural network (CNN) architecture that combines spatial attention mechanisms with a transfer learning framework to enhance both accuracy and versatility in DoA estimation. The model integrates spatial attention layers to dynamically prioritize signal regions with the highest information value, allowing it to isolate relevant signals and suppress interference in noisy or crowded signal environments. In addition, we utilize a transfer learning framework that enables the model to generalize across various antenna array configurations (i.e., planar, linear, and circular arrays) with minimal additional training. Extensive simulation results benchmark the proposed model against existing state-of-the-art methods for DoA estimation, achieving improved absolute error across diverse conditions. This hybrid approach not only enhances DoA estimation precision, but also significantly reduces retraining requirements when adapting to new array configurations, positioning it as a robust, scalable tool for next-generation wireless communication systems.

Förderung

  • European Union, through the Horizon Europe Marie Skłodowska-Curie Staff Exchanges Programme “6G intelligent connectivity and interaction for users and infrastr…

Zitieren

APA

Mylonakis, C. M., Velanas, P., Lazaridis, P. I., Sarigiannidis, P., Goudos, S. K., & Zaharis, Z. D. (2025). Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations. Technologies, 13(2), 46. https://doi.org/10.3390/technologies13020046

Vancouver

Mylonakis CM, Velanas P, Lazaridis PI, Sarigiannidis P, Goudos SK, Zaharis ZD. Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations. Technologies. 2025;13(2):46. doi:10.3390/technologies13020046

BibTeX
@article{Mylonakis2025,
  author = {Mylonakis, Constantinos M. and Velanas, Pantelis and Lazaridis, Pavlos I. and Sarigiannidis, Panagiotis and Goudos, Sotirios K. and Zaharis, Zaharias D.},
  title = {Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations},
  journal = {Technologies},
  year = {2025},
  volume = {13},
  number = {2},
  pages = {46},
  doi = {10.3390/technologies13020046}
}
Kostenlos starten →