Electroencephalogram-Based Emotion Classification Using Machine Learning and Deep Learning Techniques

Abstract

 Electroencephalogram (EEG) records brain activity as electrical currents to discern emotions. As interest in human-computer emotional connections rises, reliable and implementable emotion recognition algorithms are essential. This study classifies EEG waves using machine and deep learning. A four-channel Muse EEG headband recorded neutral, negative, and positive emotions for the publicly available Feeling Emotions EEG dataset. Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) were utilized for deep learning, while SVM, K-NN, and MLP were used for machine learning. The models were assessed for accuracy, precision, recall, and F1-Score. SVM, K-NN, and MLP have accuracy scores of 0.98, 0.95, and 0.97. Deep learning methods CNN, LSTM, and GRU had 0.98, 0.82, and 0.97 accuracy. SVM and CNN surpassed other approaches in accuracy, precision, recall, and F1-Score. The research shows that machine learning and deep learning can classify EEG signals to identify emotions. High accuracy results, especially from SVM and CNN, suggest these models could be used in emotion-aware human-computer interaction systems. This study adds to EEG-based emotion classification research by revealing model selection and parameter tweaking strategies for better categorization.