Deep Learning for Single-Channel EEG-Based Driver Drowsiness: Comparative Study

Imene Latreche, Sihem Slatnia, Okba Kazar, Saad Harous, Belkacem Athamena, Zina Houhamdi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To prevent car accidents caused by drowsiness, a transitional state between alertness and sleepiness, numerous authors have conducted studies employing various monitoring approaches and detecting techniques. However, the Electroencephalogram (EEG) was the most used monitoring approach due to its advantages compared to other techniques. Also, Deep Learning (DL) techniques have been widely used in this context and have given prominent results. In this paper, we have established a comparative study between four deep learning methods. The aim of this comparison is to determine the optimal DL model for detecting EEG-Based Drowsiness using a small balanced dataset. We evaluated the performance of the models using the hold-out method and the Leave-One-Subject-Out Cross-Validation (LOSO CV) techniques. With an accuracy of 77% with the Hold-Out method and 70.31% with the LOSO CV method, the GRU model outperforms other deep learning and machine learning models, followed by the BI-LSTM with 74.88% and 68.07, respectively.

Original languageEnglish
Title of host publicationProceedings - 2022 23rd International Arab Conference on Information Technology, ACIT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350320244
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event23rd International Arab Conference on Information Technology, ACIT 2022 - Abu Dhabi, United Arab Emirates
Duration: Nov 22 2022Nov 24 2022

Publication series

NameProceedings - 2022 23rd International Arab Conference on Information Technology, ACIT 2022

Conference

Conference23rd International Arab Conference on Information Technology, ACIT 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period11/22/2211/24/22

Keywords

  • Bi-LSTM
  • CNN
  • Cross-Subject
  • Deep Learning
  • Driver Drowsiness
  • Electroencephalogram (EEG)
  • GRU
  • LSTM

ASJC Scopus subject areas

  • Education
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Health Informatics

Fingerprint

Dive into the research topics of 'Deep Learning for Single-Channel EEG-Based Driver Drowsiness: Comparative Study'. Together they form a unique fingerprint.

Cite this