EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RadSpecFusion: Dynamic attention weighting for multi-radar human activity recognition

Ayesha Ibrahim, Muhammad Zakir Khan, Muhammad Imran, Hadi Larijani, Qammer H. Abbasi, Muhammad Usman

Internet of Things · 2025-09 · 33 · 101682

DOI: 10.1016/j.iot.2025.101682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Internet of Things, 2025-09. Verfasst von Ayesha Ibrahim und 5 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents RadSpecFusion, a novel dynamic attention-based fusion architecture for multi-radar human activity recognition (HAR). Our method learns activity-specific importance weights for each radar modality (24 GHz, 77 GHz, and Xethru sensors). Unlike existing concatenation or averaging approaches, our method dynamically adapts radar contributions based on motion characteristics. This addresses cross-frequency generalization challenges, where transfer learning methods achieve only 11%–34% accuracy. Using the CI4R dataset with spectrograms from 11 activities, our approach achieves 99.21% accuracy, representing a 15.8% improvement over existing fusion methods (83.4%). This demonstrates that different radar frequencies capture complementary information about human motion. Ablation studies show that while the three-radar system optimizes performance, dual-radar combinations achieve comparable accuracy (24GHz+77GHz: 96.1%, 24GHz+Xethru: 95.8%, 77GHz+Xethru: 97.2%), enabling flexible deployment for resource-constrained applications. The attention mechanism reveals interpretable patterns: 77 GHz radar receives higher weights for fine movements (superior Doppler resolution), while 24 GHz dominates gross body movements (better range resolution). The system maintains 71.4% accuracy at 10 dB SNR, demonstrating environmental robustness. This research establishes a new paradigm for multimodal radar fusion, moving from cross-frequency transfer learning to adaptive fusion with implications for healthcare monitoring, smart environments, and security applications.

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Ibrahim, A., Khan, M. Z., Imran, M., Larijani, H., Abbasi, Q. H., & Usman, M. (2025). RadSpecFusion: Dynamic attention weighting for multi-radar human activity recognition. Internet of Things, 33, 101682. https://doi.org/10.1016/j.iot.2025.101682

Vancouver

Ibrahim A, Khan MZ, Imran M, Larijani H, Abbasi QH, Usman M. RadSpecFusion: Dynamic attention weighting for multi-radar human activity recognition. Internet of Things. 2025;33:101682. doi:10.1016/j.iot.2025.101682

BibTeX
@article{Ibrahim2025,
  author = {Ibrahim, Ayesha and Khan, Muhammad Zakir and Imran, Muhammad and Larijani, Hadi and Abbasi, Qammer H. and Usman, Muhammad},
  title = {RadSpecFusion: Dynamic attention weighting for multi-radar human activity recognition},
  journal = {Internet of Things},
  year = {2025},
  volume = {33},
  pages = {101682},
  doi = {10.1016/j.iot.2025.101682}
}
Kostenlos starten →