Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations
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 atten...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/2/46 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850231553307705344 |
|---|---|
| author | Constantinos M. Mylonakis Pantelis Velanas Pavlos I. Lazaridis Panagiotis Sarigiannidis Sotirios K. Goudos Zaharias D. Zaharis |
| author_facet | Constantinos M. Mylonakis Pantelis Velanas Pavlos I. Lazaridis Panagiotis Sarigiannidis Sotirios K. Goudos Zaharias D. Zaharis |
| author_sort | Constantinos M. Mylonakis |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-b80a8db656bc4890a961b30797268c8a |
| institution | OA Journals |
| issn | 2227-7080 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj-art-b80a8db656bc4890a961b30797268c8a2025-08-20T02:03:30ZengMDPI AGTechnologies2227-70802025-01-011324610.3390/technologies13020046Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array ConfigurationsConstantinos M. Mylonakis0Pantelis Velanas1Pavlos I. Lazaridis2Panagiotis Sarigiannidis3Sotirios K. Goudos4Zaharias D. Zaharis5School of Electrical and Computer Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceAcceligence Ltd., Nicosia 1066, CyprusSchool of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UKInformatics & Telecommunications Engineering, University of Western Macedonia, 50100 Kozani, GreeceELEDIA@AUTH, School of Physics Aristotle University of Thessaloniki, 54635 Thessaloniki, GreeceSchool of Electrical and Computer Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceRapid 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.https://www.mdpi.com/2227-7080/13/2/46direction-of-arrival (DoA) estimationmachine learningconvolutional neural networksspatial attentiontransfer learningmultiple-input multiple-output (MIMO) systems |
| spellingShingle | Constantinos M. Mylonakis Pantelis Velanas Pavlos I. Lazaridis Panagiotis Sarigiannidis Sotirios K. Goudos Zaharias D. Zaharis Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations Technologies direction-of-arrival (DoA) estimation machine learning convolutional neural networks spatial attention transfer learning multiple-input multiple-output (MIMO) systems |
| title | Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations |
| title_full | Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations |
| title_fullStr | Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations |
| title_full_unstemmed | Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations |
| title_short | Deep Learning Framework Using Spatial Attention Mechanisms for Adaptable Angle Estimation Across Diverse Array Configurations |
| title_sort | deep learning framework using spatial attention mechanisms for adaptable angle estimation across diverse array configurations |
| topic | direction-of-arrival (DoA) estimation machine learning convolutional neural networks spatial attention transfer learning multiple-input multiple-output (MIMO) systems |
| url | https://www.mdpi.com/2227-7080/13/2/46 |
| work_keys_str_mv | AT constantinosmmylonakis deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations AT pantelisvelanas deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations AT pavlosilazaridis deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations AT panagiotissarigiannidis deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations AT sotirioskgoudos deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations AT zahariasdzaharis deeplearningframeworkusingspatialattentionmechanismsforadaptableangleestimationacrossdiversearrayconfigurations |