EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach

Mohammad Peivandi, Sevda Zafarmandi Ardabili, Sobhan Sheykhivand iD, Sebelan Danishvar iD

Sensors · 2023

DOI: 10.3390/s23198171 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Mohammad Peivandi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Wayne State University, Detroit, MI 48202, USA. Hauptthemen laut MEDLINE: Automobile Driving, Deep Learning. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A large share of traffic accidents is related to driver fatigue. In recent years, many studies have been organized in order to diagnose and warn drivers. In this research, a new approach was presented in order to detect multi-level driver fatigue. A multi-level driver tiredness diagnostic database based on physiological signals including ECG, EEG, EMG, and respiratory effort was developed for this aim. The EEG signal was used for processing and other recorded signals were used to confirm the driver’s fatigue so that fatigue was not confirmed based on self-report questionnaires. A customized architecture based on adversarial generative networks and convolutional neural networks (end-to-end) was utilized to select/extract features and classify different levels of fatigue. In the customized architecture, with the objective of eliminating uncertainty, type 2 fuzzy sets were used instead of activation functions such as Relu and Leaky Relu, and the performance of each was investigated. The final accuracy obtained in the three scenarios considered, two-level, three-level, and five-level, were 96.8%, 95.1%, and 89.1%, respectively. Given the suggested model’s optimal performance, which can identify five various levels of driver fatigue with high accuracy, it can be employed in practical applications of driver fatigue to warn drivers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile DrivingDeep LearningHumansElectroencephalographyAccidents, TrafficFatigue

Stichwörter der Autor:innen

CNNEEGGANdeep learningdriver fatiguefeature extractionmachine learningphysiological signals

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Wayne State University, Detroit, MI 48202, USA.
  • Electrical and Computer Engineering Department, Southern Methodist University, Dallas, TX 75205, USA.
  • Department of Biomedical Engineering, University of Bonab, Bonab 55517-61167, Iran.
  • College of Engineering, Design and Physical Sciences, Brunel University London, Uxbridge UB8 3PH, UK.

ORCID-Profile: Sobhan Sheykhivand, Sebelan Danishvar

Zitieren

APA

Peivandi, M., Ardabili, S. Z., Sheykhivand, S., & Danishvar, S. (2023). Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach. Sensors. https://doi.org/10.3390/s23198171

Vancouver

Peivandi M, Ardabili SZ, Sheykhivand S, Danishvar S. Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach. Sensors. 2023. doi:10.3390/s23198171

BibTeX
@article{Peivandi2023,
  author = {Peivandi, Mohammad and Ardabili, Sevda Zafarmandi and Sheykhivand, Sobhan and Danishvar, Sebelan},
  title = {Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23198171}
}
Kostenlos starten →