EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Radar Signal Processing and Its Impact on Deep Learning-Driven Human Activity Recognition

Fahad Ayaz iD, Basim Alhumaily iD, Sajjad Hussain iD, Muhammad Ali Imran iD, Kamran Arshad iD, Khaled Assaleh, Ahmed Zoha iD

Sensors · 2025

DOI: 10.3390/s25030724 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Fahad Ayaz und 6 weiteren Autor:innen. Beteiligte Einrichtung: James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK. Hauptthemen laut MEDLINE: Radar, Deep Learning, Signal Processing, Computer-Assisted, Human Activities. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ajman University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) using radar technology is becoming increasingly valuable for applications in areas such as smart security systems, healthcare monitoring, and interactive computing. This study investigates the integration of convolutional neural networks (CNNs) with conventional radar signal processing methods to improve the accuracy and efficiency of HAR. Three distinct, two-dimensional radar processing techniques, specifically range-fast Fourier transform (FFT)-based time-range maps, time-Doppler-based short-time Fourier transform (STFT) maps, and smoothed pseudo-Wigner–Ville distribution (SPWVD) maps, are evaluated in combination with four state-of-the-art CNN architectures: VGG-16, VGG-19, ResNet-50, and MobileNetV2. This study positions radar-generated maps as a form of visual data, bridging radar signal processing and image representation domains while ensuring privacy in sensitive applications. In total, twelve CNN and preprocessing configurations are analyzed, focusing on the trade-offs between preprocessing complexity and recognition accuracy, all of which are essential for real-time applications. Among these results, MobileNetV2, combined with STFT preprocessing, showed an ideal balance, achieving high computational efficiency and an accuracy rate of 96.30%, with a spectrogram generation time of 220 ms and an inference time of 2.57 ms per sample. The comprehensive evaluation underscores the importance of interpretable visual features for resource-constrained environments, expanding the applicability of radar-based HAR systems to domains such as augmented reality, autonomous systems, and edge computing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadarDeep LearningSignal Processing, Computer-AssistedHuman ActivitiesHumansNeural Networks, ComputerFourier AnalysisAlgorithms

Stichwörter der Autor:innen

computational costdeep learninghuman activity classificationradar domain representationstransfer learning

Autor:innen und Institutionen

  • James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK.
  • Department of Electrical and Computer Engineering, College of Engineering and Information Technology, Ajman University, Ajman P.O. Box 346, United Arab Emirates.
  • Artificial Intelligence Research Centre, Ajman University, Ajman P.O. Box 346, United Arab Emirates.

ORCID-Profile: Fahad Ayaz, Basim Alhumaily, Sajjad Hussain, Muhammad Ali Imran, Kamran Arshad, Ahmed Zoha

Förderung

  • Ajman University

Zitieren

APA

Ayaz, F., Alhumaily, B., Hussain, S., Imran, M. A., Arshad, K., Assaleh, K., & Zoha, A. (2025). Radar Signal Processing and Its Impact on Deep Learning-Driven Human Activity Recognition. Sensors. https://doi.org/10.3390/s25030724

Vancouver

Ayaz F, Alhumaily B, Hussain S, Imran MA, Arshad K, Assaleh K, et al. Radar Signal Processing and Its Impact on Deep Learning-Driven Human Activity Recognition. Sensors. 2025. doi:10.3390/s25030724

BibTeX
@article{Ayaz2025,
  author = {Ayaz, Fahad and Alhumaily, Basim and Hussain, Sajjad and Imran, Muhammad Ali and Arshad, Kamran and Assaleh, Khaled and Zoha, Ahmed},
  title = {Radar Signal Processing and Its Impact on Deep Learning-Driven Human Activity Recognition},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25030724}
}
Kostenlos starten →