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 Experiment Videos

An algorithm for detecting startle state based on physiological signals.

Kohzoh Yoshino1, Motonari Edamatsu, Masaki Yoshida

  • 1Institute for Human Science and Biomedical Engineering, National Institute of Advanced Industrial Science and Technology (AIST), 1-8-31 Midorigaoka, Ikeda, Osaka 563-8577, Japan. yoshino-k@aist.go.jp

Accident; Analysis and Prevention
|October 19, 2006
PubMed
Summary
This summary is machine-generated.

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

[A QUESTIONNAIRE SURVEYON TREATMENT SELECTION FOR PATIENTS WITH ADVANCED PROSTATE CANCER IN JAPAN].

Hinyokika kiyo. Acta urologica Japonica·2026
Same author

Vapor-Controlled Full-Color Luminescence in Platinum(II) Complexes Bearing N-Heterocyclic Carbene and a Flexible Alkyl Chain.

Angewandte Chemie (International ed. in English)·2026
Same author

Switchable photoluminescence of europium(III) complexes with chromonylhydrazones.

Chemical communications (Cambridge, England)·2026
Same author

Clinical utility of urinary microRNA (miR-1273g-3p) in male patients with detrusor underactivity.

World journal of urology·2026
Same author

Genetic Predictors of Progression and Skin Rash in Japanese mCSPC Patients Treated With Apalutamide: CUARTET Study.

Cancer science·2026
Same author

Respiratory phase alignment across memory encoding and retrieval improves task efficiency.

Scientific reports·2026

This study introduces an algorithm detecting human startle responses to danger using physiological signals. Optimized for accuracy, it shows high sensitivity and specificity in virtual and real-world scenarios, enhancing safety technology.

Area of Science:

  • Physiological computing
  • Human-computer interaction
  • Safety engineering

Background:

  • Automatic detection of dangerous situations is crucial for creating safe environments.
  • Human physiological responses, such as increased finger skin conductance and decreased heart rate, indicate stress or startle.
  • Developing reliable algorithms to interpret these signals is key for proactive safety measures.

Purpose of the Study:

  • To develop and optimize an algorithm for automatically detecting human startle states in response to dangerous situations.
  • To validate the algorithm's performance across different conditions, including static and dynamic activities.
  • To assess the algorithm's applicability in real-world hazardous scenarios.

Main Methods:

  • An algorithm was developed based on increased finger skin conductance and decreased instantaneous heart rate.

Related Experiment Videos

  • Algorithm parameters were optimized using experimental data from 21 subjects in a virtual reality system presenting dangerous scenarios.
  • Performance was evaluated using detection sensitivity and specificity metrics.

    • Main Results:

    • The optimized algorithm achieved 100% sensitivity in static and cycling conditions.
    • Detection specificity was 90% for static and 87% for cycling conditions.
    • In a real-world car driving scenario, the algorithm demonstrated 87% sensitivity and 80% specificity.

    Conclusions:

    • The developed algorithm effectively detects human startle responses to dangerous situations using physiological signals.
    • The algorithm shows high accuracy and robustness across various conditions, including physical activity and real-world driving.
    • This technology holds promise for enhancing safety in workspaces and daily life by enabling automatic detection of hazardous events.