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

Structure aware graph community cluster pruning for efficient neural network compression in Parkinson's disease diagnosis.

Scientific reports·2026
Same author

A distribution-level statistical framework for reliable pipeline leak detection using multi-domain signal analysis.

Scientific reports·2026
Same author

Attention mechanism-based CNN-LSTM hybrid deep learning model for industrial pipeline leak detection.

Scientific reports·2026
Same author

A multistage transfer learning framework for intelligent fault diagnosis of rotating machinery under variable operating conditions.

Scientific reports·2026
Same author

Physics guided fused image learning with enhanced squeeze excitation for failure analysis of multistage centrifugal pumps.

Scientific reports·2026
Same author

Gaussian process regression with physics-guided pseudo-sample augmentation for wear prediction under sparse measurements in milling.

Scientific reports·2026

Related Experiment Video

Updated: Jan 1, 2026

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

5.2K

A Hybrid Feature Pool-Based Emotional Stress State Detection Algorithm Using EEG Signals.

Md Junayed Hasan1, Jong-Myon Kim1

  • 1Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Korea.

Brain Sciences
|December 19, 2019
PubMed
Summary

This study introduces a hybrid feature pool for analyzing electroencephalogram (EEG) signals to detect human stress. The novel approach achieved 73.38% accuracy, outperforming other methods.

Keywords:
EEG signalsfeature selectork-NNstress analysis

More Related Videos

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

14.3K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.9K

Related Experiment Videos

Last Updated: Jan 1, 2026

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

5.2K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

14.3K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.9K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Accurate human stress analysis from electroencephalogram (EEG) signals necessitates comprehensive, domain-specific data.
  • Developing effective machine learning models requires robust feature extraction from complex physiological signals.

Purpose of the Study:

  • To design a multi-domain hybrid feature pool for enhanced information identification from EEG signals.
  • To evaluate the efficacy of a wrapper-based feature selection method (Boruta) and k-nearest neighbor (k-NN) classification for stress detection.

Main Methods:

  • A hybrid feature pool combining time-domain statistical parametric analysis and time-frequency domain wavelet-based features was created.
  • The Boruta algorithm was employed for feature ranking, prioritizing relevant features over non-redundant ones.
  • The k-nearest neighbor (k-NN) algorithm was utilized for the final classification of stress levels.

Main Results:

  • The proposed model achieved an overall accuracy of 73.38% on the dataset.
  • Comparison with non-linear dimensionality reduction techniques and models without feature ranking demonstrated the superiority of the hybrid feature pool approach.

Conclusions:

  • The developed hybrid feature pool effectively captures crucial information from EEG signals for stress analysis.
  • Feature ranking using the Boruta algorithm is essential for optimizing machine learning model performance in this domain.