PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
October 27, 2025Indonesian Journal of Computer ScienceOpen Access

Multi-Level Stress Classification Using the Electroencephalogram Based on Mental Load Tasks

View Full Paper
Ask AI
Bookmark
Share

Authors

WAWalaa Alajali

Discussion

Loading...

Member takes

Overview

Analysis reveals machine learning accurately classifies stress levels in cognitive load tasks, suggesting EEG's potential for mental health monitoring.

Key Points

  • Naive Bayes classifiers achieved 98.82% and 98.87% accuracy for Stroop and arithmetic tasks, respectively, indicating excellent model performance.
  • Empirical Mode Decomposition and Butterfly Optimization Algorithm were employed for feature extraction and dimensionality reduction from EEG data.
  • Five different classifiers including Naive Bayes and Random Forest effectively categorized four stress levels based on cognitive load.
  • Results support the application of machine learning on EEG data, pointing to advancements in mental health monitoring and task optimization.

Cite This Study

Walaa Alajali (2025) studied this question.

synapsesocial.com/papers/68ff87d8c8c50a61f2bdca78https://doi.org/10.33022/ijcs.v14i5.5022
View Full Paper
Ask AI
Bookmark
Share