Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MRI-based radiomics interpretable model predicts microsatellite instability status in endometrioid adenocarcinoma.

BMC medical imaging·2026
Same author

Protective Effects of Tuber sinoaestivum-Derived Exosome-Like Nanovesicles Against Cisplatin-Induced Acute Liver Injury and Acute Kidney Injury.

Journal of food science·2026
Same author

Non-invasive assessment of glymphatic dysfunction in middle cerebral artery stenosis based on DTI-ALPS and ro-ALPS.

Frontiers in neurology·2026
Same author

Correction to: The Cerebrovascular Reactivity Adjusted Fractional Amplitude of Low-Frequency Fluctuations Abnormalities in Middle Cerebral Artery Stenosis and Occlusive Disease.

Translational stroke research·2026
Same author

Roles and applications of artificial intelligence in fetal and placental MRI: a literature review.

BMC pregnancy and childbirth·2026
Same author

Clinical profiling of AML1::ETO and KIT exon 17 mutation in pediatric AML by high-throughput drug sensitivity.

BMC cancer·2026

Related Experiment Video

Updated: Aug 5, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.2K

EEG driving fatigue detection based on log-Mel spectrogram and convolutional recurrent neural networks.

Dongrui Gao1, Xue Tang1, Manqing Wan1

  • 1School of Computer Science, Chengdu University of Information Technology, Chengdu, China.

Frontiers in Neuroscience
|March 27, 2023
PubMed
Summary

This study introduces a new electroencephalographic (EEG) based driver fatigue detection system using a Convolution Recurrent Neural Network (CRNN). The model accurately identifies driver fatigue, enhancing traffic safety by overcoming environmental limitations of facial recognition methods.

Keywords:
EEGconvolutional neural networkdriving fatigue detectionlog-Mel spectrogramrecurrent neural network

More Related Videos

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

20.4K
Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.6K

Related Experiment Videos

Last Updated: Aug 5, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.2K
Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

20.4K
Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.6K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Traffic Safety Engineering

Background:

  • Driver fatigue is a major cause of road accidents.
  • Current detection methods using facial expressions are unreliable due to environmental factors like lighting.
  • Electroencephalographic (EEG) signals offer a direct measure of mental state, unaffected by external conditions.

Purpose of the Study:

  • To develop an accurate and robust driver fatigue detection system.
  • To leverage electroencephalographic (EEG) signals for fatigue monitoring.
  • To utilize a Convolution Recurrent Neural Network (CRNN) model for enhanced detection performance.

Main Methods:

  • Signal processing of EEG data using one-dimensional convolution and Short Time Fourier Transform (STFT).
  • Generation of log-Mel spectrograms from EEG signals.
  • Implementation of a CRNN model comprising a 6-layer Convolutional Neural Network (CNN) and bi-directional Recurrent Neural Networks (Bi-RNNs) for feature extraction and classification.

Main Results:

  • The proposed EEG-based CRNN model accurately distinguishes between alert and fatigued states.
  • The method demonstrated high stability in fatigue detection.
  • Comparative analysis showed superior performance against four existing driver fatigue detection methods.

Conclusions:

  • The log-Mel spectrogram and CRNN model based on EEG signals provide a highly accurate and stable solution for driver fatigue detection.
  • This approach effectively overcomes the limitations of facial expression-based methods.
  • The findings suggest a significant advancement in improving road safety through reliable fatigue monitoring.