Related Experiment Video
Updated: Sep 22, 2025
08:31
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
Published on: July 31, 2016
13.6K
Innovative Poincare's plot asymmetry descriptors for EEG emotion recognition
Atefeh Goshvarpour1, Ateke Goshvarpour2
1Department of Biomedical Engineering, Faculty of Electrical Engineering, Sahand University of Technology, Tabriz, Iran.
Cognitive Neurodynamics
|May 23, 2022
Summary
This study introduces novel electroencephalogram (EEG) asymmetry measures to enhance emotion recognition accuracy. The k-nearest neighbor (kNN) classifier achieved high performance, outperforming other methods on benchmark datasets.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Machine Learning
Background:
- Emotion recognition is crucial for medical and non-medical applications.
- Current electroencephalogram (EEG)-based emotion recognition systems lack desired accuracy.
- Developing automated systems for emotion recognition is an active research area.
Purpose of the Study:
- To introduce novel EEG asymmetry measures for improving emotion recognition accuracy.
- To evaluate the effectiveness of different feature selection strategies.
- To compare the performance of k-nearest neighbor (kNN), support vector machine, and Naïve Bayes classifiers.
Main Methods:
- Classification of four emotional states using kNN, support vector machine, and Naïve Bayes.
- Implementation of feature selection to identify optimal feature subsets.
- Validation using the SEED-IV and DEAP public EEG datasets.
Main Results:
- The k-nearest neighbor (kNN) classifier achieved the highest accuracy rates.
- Maximum accuracies of 95.49% on SEED-IV and 98.63% on DEAP were recorded.
- The proposed novel EEG-asymmetry measures demonstrated superior performance compared to existing methods.
Conclusions:
- The novel EEG-asymmetry measures significantly improve emotion recognition rates.
- The developed framework offers a superior approach for EEG-based emotion recognition.
- The findings contribute to advancing automated emotion analysis systems.
