EMOTION CLASSIFICATION ON PHYSIOLOGICAL DATA

Abstract

A person interacts with many different machines throughout their lifetime. Emotions also play a crucial and inevitable role in everyone's life, as they can trigger various thoughts, feelings, and behavioural responses. The Electroencephalogram (EEG) signal, which measures brain activity in the scalp region, is the most effective tool for tracing response changes. Emotion classification utilizing the physiological signal EEG has been conducted using the AMIGOS dataset. Before the emotion classification, the study extracted features from the EEG signals using the time domain feature Power Spectral Density (PSD) and time and frequency domain feature Wavelet entropy. Data cleaning and preprocessing were performed to prevent biased results caused by missing values among different users, which involved handling and addressing missing values. The study utilized Support Vector Machine, Artificial Neural Network (ANN), and Convolutional Neural Network with Overlapping and Non Overlapping Sliding Window techniques, all based on machine learning and deep learning. Finally, the study classified emotions regarding Arousal, Valence, and Dominance.