EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion

Yonghong Zhao iD, Xiumei Fan, Jisong Liu

Sensors · 15.05.2025 · 25 (10) · 3142

DOI: 10.3390/s25103142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.05.2025. Verfasst von Yonghong Zhao und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710048, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of the People's Republic of China, Ministry of Science and Technology, Shaanxi province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a robust deep learning (DL)-based method for Direction-of-Arrival (DOA) estimation. Specifically, we develop a novel CRDCNN-LSTM network architecture, which integrates a Cross-Residual Depthwise Convolutional Neural Network (CRDCNN) with a Long Short-Term Memory (LSTM) module for effective capture of both spatial and temporal features. The CRDCNN employs multi-level cross-residual connections and depthwise separable convolutions to enhance feature diversity while mitigating issues such as gradient vanishing and overfitting. Furthermore, a customized FD loss function, combining Focal Loss and Dice Loss, is introduced to emphasize low-confidence samples and promote sparsity in the spatial spectrum, thereby improving the precision and overall effectiveness of DOA estimation. A post-processing strategy based on peak detection and quadratic interpolation is also employed to refine DOA estimations and reduce quantization errors. Simulation results demonstrate that the proposed approach achieves significantly higher estimation accuracy and resolution than conventional methods and current DL models under varying SNR and snapshot conditions. In addition, it offers distinct advantages in terms of generalization and computational efficiency.

Schlagwörter

Stichwörter der Autor:innen

LSTMdeep learningdepthwise separable convolutiondirection-of-arrival estimation

Autor:innen und Institutionen

  • School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710048, China.
  • Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing, Xi'an University of Technology, Xi'an 710048, China.

ORCID-Profile: Yonghong Zhao

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • Ministry of Science and Technology
  • Shaanxi province

Zitieren

APA

Zhao, Y., Fan, X., & Liu, J. (2025). Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion. Sensors, 25(10), 3142. https://doi.org/10.3390/s25103142

Vancouver

Zhao Y, Fan X, Liu J. Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion. Sensors. 2025;25(10):3142. doi:10.3390/s25103142

BibTeX
@article{Zhao2025,
  author = {Zhao, Yonghong and Fan, Xiumei and Liu, Jisong},
  title = {Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {10},
  pages = {3142},
  doi = {10.3390/s25103142}
}
Kostenlos starten →