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

Large Language Model-Based Agents for Physical Activity and Cognitive Training: Scoping Review.

JMIR AI·2026
Same author

Validation of the immersion in digital life and quality of digital experience scales in German, French, Spanish, Polish and Czech.

Frontiers in psychiatry·2026
Same author

Retention and Engagement in Culturally Adapted Digital Mental Health Interventions: Systematic Review of Dropout, Attrition, and Adherence in Non-Western, Educated, Industrialized, Rich, Democratic Settings.

JMIR mental health·2026
Same author

Exploring cross-cultural effectiveness of internet-based depression treatment (IBAT-D) with peer-to-peer support vs. without across WEIRD and non-WEIRD samples: a research protocol for a randomized controlled trial.

Trials·2025
Same author

A new telemonitoring feature for detection of long-term CPAP adherence.

Sleep medicine: X·2025
Same author

Aesthetics, illusion of success and age interactions: disentangling effects in the closed-loop design with sham neurofeedback training.

Frontiers in human neuroscience·2025

Related Experiment Video

Updated: Nov 15, 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

4.7K

Classification of Drivers' Workload Using Physiological Signals in Conditional Automation.

Quentin Meteier1, Marine Capallera1, Simon Ruffieux1

  • 1HumanTech Institute, University of Applied Sciences of Western Switzerland, Haute École Spécialisée de Suisse Occidentale, Fribourg, Switzerland.

Frontiers in Psychology
|March 8, 2021
PubMed
Summary
This summary is machine-generated.

Detecting driver mental workload in automated vehicles is crucial for safety. Machine learning accurately identifies high workload using physiological signals like respiration and skin conductance, improving conditional automation safety.

Keywords:
automated drivingclassificationdrivermachine learningphysiologysecondary taskworkload

More Related Videos

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.7K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K

Related Experiment Videos

Last Updated: Nov 15, 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

4.7K
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.7K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K

Area of Science:

  • Human-Computer Interaction
  • Automotive Engineering
  • Cognitive Science

Background:

  • Increasing automation in vehicles shifts driving tasks from humans to machines.
  • Drivers in conditionally automated vehicles may perform secondary tasks, potentially increasing mental workload.
  • High mental workload can impair driver performance during critical takeover situations.

Purpose of the Study:

  • To investigate the use of physiological signals for real-time detection of driver mental workload.
  • To evaluate the effectiveness of machine learning models in classifying workload levels during conditional automation.
  • To determine optimal data processing strategies, including sensor fusion and data segmentation, for workload detection.

Main Methods:

  • Collected physiological data (respiration, skin conductance) from 90 participants in a driving simulator.
  • Induced varying mental workload levels by assigning secondary cognitive tasks.
  • Compared three machine learning classifiers, sensor fusion, and different data segmentation levels.

Main Results:

  • The best-performing model achieved 95% accuracy in classifying driver workload.
  • Sensor fusion sometimes enhanced classification performance.
  • Optimal performance was observed with data segmentation windows smaller than 4 minutes.

Conclusions:

  • High driver mental workload in conditional automation can be accurately detected using physiological data.
  • Respiration and skin conductance, analyzed over 4-minute intervals, are effective indicators.
  • This technology can enhance safety in future automated driving systems.