Related Experiment Video
Updated: Jun 27, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.3K
Detecting emotions through EEG signals based on modified convolutional fuzzy neural network.
Nasim Ahmadzadeh Nobari Azar1,2, Nadire Cavus3,4, Parvaneh Esmaili5
1Department of Biomedical Engineering, Near East University, 99138, Nicosia, Cyprus. nasim.ahmadzadeh@neu.edu.tr.
Scientific Reports
|May 6, 2024
Summary
This study enhances emotion recognition using Electroencephalography (EEG) signals with a novel Convolutional Fuzzy Neural Network (CFNN). The improved CFNN model achieves high accuracy in detecting emotional valence and arousal, outperforming existing methods.
Area of Science:
- Neuroscience and Artificial Intelligence
- Computational Psychology
Background:
- Facial expression analysis for emotion recognition is unreliable due to deliberate concealment.
- Electroencephalography (EEG) signals offer a more objective measure for emotion detection.
- Conventional machine learning methods struggle with the complexity of EEG data, leading to inconsistent results.
Purpose of the Study:
- To develop a reliable emotion recognition system using EEG signals.
- To improve the performance of emotion detection by enhancing the Convolutional Fuzzy Neural Network (CFNN).
- To achieve high accuracy with a model that prioritizes fewer parameters.
Main Methods:
- Pre-processing and feature extraction were applied to EEG signals to ensure data quality.
- A modified Convolutional Fuzzy Neural Network (CFNN) architecture was developed and trained for emotion classification.
- Parametric and comparative experiments were conducted to evaluate the model's performance.
Main Results:
- The proposed CFNN model demonstrated reliable performance in emotion recognition.
- The system achieved an average accuracy of 98.21% for valence (pleasantness).
- The system achieved an average accuracy of 98.08% for arousal (intensity), surpassing state-of-the-art methods.
Conclusions:
- The enhanced CFNN provides a robust and accurate method for emotion recognition from EEG signals.
- This approach addresses the limitations of traditional methods in analyzing complex EEG data.
- The model's high accuracy and efficiency make it a promising tool for various applications.
