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

Narcolepsy01:07

Narcolepsy

237
Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.
237

You might also read

Related Articles

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

Sort by
Same author

Retraction Note: AI-optimized GRU-based self-attention model for predictive diabetes staging in IoT healthcare 5.0.

Scientific reports·2026
Same author

Optimized CNN-based ensemble deep learning approach for potato leaf disease detection with data augmentation.

Scientific reports·2026
Same author

A dynamic light image enhancement algorithm using generative adversarial network for group activity recognition.

Scientific reports·2026
Same author

Color image security technique combining encryption and data hiding for healthcare applications.

Computer methods and programs in biomedicine·2026
Same author

Improving predictive reliability and automation of smart grids using the StarNet ensemble model.

Scientific reports·2026
Same author

Retraction Note: Sentimental analysis based federated learning privacy detection in fake web recommendations using blockchain model.

Scientific reports·2026

Related Experiment Video

Updated: Oct 17, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.6K

Extended-Range Prediction Model Using NSGA-III Optimized RNN-GRU-LSTM for Driver Stress and Drowsiness.

Kwok Tai Chui1, Brij B Gupta2,3,4, Ryan Wen Liu5

  • 1Department of Technology, School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China.

Sensors (Basel, Switzerland)
|October 13, 2021
PubMed
Summary

Predicting driver stress and drowsiness using a hybrid algorithm significantly improves road safety. The NSGA-III-optimized RNN-GRU-LSTM model enhances prediction accuracy, offering a novel approach to prevent traffic accidents.

Keywords:
NSGA-IIIat-risk drivingdriver drowsinessdriver stressgated recurrent unitintelligent transportationlong short-term memory networkmulti-objective optimizationrecurrent neural network

More Related Videos

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

729

Related Experiment Videos

Last Updated: Oct 17, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.6K
Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

729

Area of Science:

  • Road safety and artificial intelligence
  • Machine learning for predictive analytics
  • Transportation engineering

Background:

  • Road traffic accidents remain a leading global cause of death, with driver impairment (stress, drowsiness) a significant contributing factor.
  • Traditional accident prevention methods have shown limited success in mitigating risks associated with undesirable driver states.
  • Predictive modeling offers a proactive approach to identify at-risk drivers and implement timely interventions.

Purpose of the Study:

  • To develop and evaluate a novel hybrid algorithm for predicting driver stress and drowsiness.
  • To compare the performance of the proposed hybrid model against individual recurrent neural network (RNN), gated recurrent unit (GRU), and long short-term memory (LSTM) algorithms.
  • To enhance the accuracy of driver status prediction for proactive road safety measures.

Main Methods:

  • Development of a hybrid algorithm, nondominated sorting genetic algorithm-III (NSGA-III)-optimized RNN-GRU-LSTM, integrating multiple deep learning models.
  • Comparative analysis of the proposed NSGA-III-optimized RNN-GRU-LSTM model against individual RNN, GRU, and LSTM algorithms.
  • Utilized a real-world driving dataset with a large sample size, incorporating key factors and cross-validation for robust evaluation.

Main Results:

  • The NSGA-III-optimized RNN-GRU-LSTM model demonstrated significant improvements in prediction accuracy.
  • Achieved accuracy enhancements of 11.2-13.6% for driver stress prediction and 10.2-12.2% for driver drowsiness prediction compared to individual algorithms.
  • Outperformed boosting learning with multiple RNNs, GRUs, and LSTMs, showing accuracy improvements of 6.9-12.7% and 6.9-8.9% respectively.

Conclusions:

  • The proposed NSGA-III-optimized RNN-GRU-LSTM hybrid model offers superior accuracy in predicting driver stress and drowsiness.
  • This advanced predictive capability can significantly contribute to reducing road traffic accidents.
  • Future research should explore further enhancements and applications of hybrid algorithms in driver behavior analysis.