EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence

Hafeez Ur Rehman Siddiqui iD, Ambreen Akmal, Muhammad Iqbal iD, Adil Ali Saleem iD, Muhammad Amjad Raza iD, Kainat Zafar, Aqsa Zaib, Sandra Dudley iD, Jon Arambarri, Ángel Kuc Castilla, Furqan Rustam iD

Sensors · 2024

DOI: 10.3390/s24123754 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Hafeez Ur Rehman Siddiqui und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Paki…. Hauptthemen laut MEDLINE: Radar, Artificial Intelligence, Neural Networks, Computer, Automobile Driving. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European University of the Atlantic.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driving while drowsy poses significant risks, including reduced cognitive function and the potential for accidents, which can lead to severe consequences such as trauma, economic losses, injuries, or death. The use of artificial intelligence can enable effective detection of driver drowsiness, helping to prevent accidents and enhance driver performance. This research aims to address the crucial need for real-time and accurate drowsiness detection to mitigate the impact of fatigue-related accidents. Leveraging ultra-wideband radar data collected over five minutes, the dataset was segmented into one-minute chunks and transformed into grayscale images. Spatial features are retrieved from the images using a two-dimensional Convolutional Neural Network. Following that, these features were used to train and test multiple machine learning classifiers. The ensemble classifier RF-XGB-SVM, which combines Random Forest, XGBoost, and Support Vector Machine using a hard voting criterion, performed admirably with an accuracy of 96.6%. Additionally, the proposed approach was validated with a robust k-fold score of 97% and a standard deviation of 0.018, demonstrating significant results. The dataset is augmented using Generative Adversarial Networks, resulting in improved accuracies for all models. Among them, the RF-XGB-SVM model outperformed the rest with an accuracy score of 99.58%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadarArtificial IntelligenceNeural Networks, ComputerAutomobile DrivingSupport Vector MachineHumansAlgorithmsMachine Learning

Stichwörter der Autor:innen

convolutional neural networkdrowsinessensemble modelsspatial featuresultra-wideband radar

Autor:innen und Institutionen

  • Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Abu Dhabi Road, Rahim Yar Khan 64200, Punjab, Pakistan.
  • Institute of Computer and Software Engineering, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan 64200, Punjab, Pakistan.
  • Bioengineering Research Centre, School of Engineering, London South Bank University, 103 Borough Road, London SE1 0AA, UK.
  • Universidade Internacional do Cuanza, Cuito EN250, Angola.
  • Fundación Universitaria Internacional de Colombia, Bogotá 111321, Colombia.
  • Universidad Internacional Iberoamericana, Campeche 24560, Mexico.

ORCID-Profile: Hafeez Ur Rehman Siddiqui, Muhammad Iqbal, Adil Ali Saleem, Muhammad Amjad Raza, Sandra Dudley, Furqan Rustam

Förderung

  • European University of the Atlantic

Zitieren

APA

Siddiqui, H. U. R., Akmal, A., Iqbal, M., Saleem, A. A., Raza, M. A., Zafar, K., Zaib, A., Dudley, S., Arambarri, J., Castilla, Á. K., & Rustam, F. (2024). Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence. Sensors. https://doi.org/10.3390/s24123754

Vancouver

Siddiqui HUR, Akmal A, Iqbal M, Saleem AA, Raza MA, Zafar K, et al. Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence. Sensors. 2024. doi:10.3390/s24123754

BibTeX
@article{Siddiqui2024,
  author = {Siddiqui, Hafeez Ur Rehman and Akmal, Ambreen and Iqbal, Muhammad and Saleem, Adil Ali and Raza, Muhammad Amjad and Zafar, Kainat and Zaib, Aqsa and Dudley, Sandra and Arambarri, Jon and Castilla, Ángel Kuc and Rustam, Furqan},
  title = {Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24123754}
}
Kostenlos starten →