Hybrid hunt-based deep convolutional neural network for emotion recognition using EEG signals

Area of Science:

• Neuroscience
• Artificial Intelligence
• Biomedical Engineering

Background:

• Emotion recognition from electroencephalogram (EEG) signals is a growing field.
• Advanced methods like deep learning are crucial for effective emotion recognition.
• Existing methods require further optimization for enhanced accuracy.

Purpose of the Study:

• To develop an optimized deep convolutional neural network (Deep CNN) model for emotion recognition using EEG signals.
• To enhance the accuracy of emotion recognition by integrating hybrid optimization techniques.
• To leverage frequency-based features for improved recognition efficiency.

Main Methods:

• Utilized a hybrid hunt optimization algorithm to select informative electrodes and tune Deep CNN hyperparameters.
• Analyzed frequency bands and extracted frequency-based features from EEG signals.
• Employed DEAP and SEED-IV datasets for model evaluation.

Main Results:

• Achieved a high accuracy of 96.68% on the DEAP dataset.
• Obtained an accuracy of 95.89% on the SEED-IV dataset.
• Demonstrated the effectiveness of frequency-based features and optimized electrode selection.

Conclusions:

• The proposed optimized Deep CNN model significantly improves emotion recognition accuracy from EEG signals.
• Hybrid optimization and frequency-based features are key to enhancing EEG-based emotion recognition.
• EEG is a highly accurate modality for recognizing human emotions with advanced computational methods.