Emotion Recognition with Machine Learning Using EEG Signals

TL;DR

This paper presents an EEG-based emotion recognition system using spectral features, PCA, and machine learning classifiers, achieving over 91% accuracy in classifying emotional states based on valence and arousal.

Contribution

It introduces a novel combination of wavelet-based spectral features, PCA, and SVM for improved emotion recognition accuracy from EEG signals.

Findings

SVM with RBF kernel achieved 91.3% accuracy for arousal.

The method outperforms existing algorithms on the DEAP dataset.

Beta frequency band features yielded the best classification results.

Abstract

In this research, an emotion recognition system is developed based on valence/arousal model using electroencephalography (EEG) signals. EEG signals are decomposed into the gamma, beta, alpha and theta frequency bands using discrete wavelet transform (DWT), and spectral features are extracted from each frequency band. Principle component analysis (PCA) is applied to the extracted features by preserving the same dimensionality, as a transform, to make the features mutually uncorrelated. Support vector machine (SVM), K-nearest neighbor (KNN) and artificial neural network (ANN) are used to classify emotional states. The cross-validated SVM with radial basis function (RBF) kernel using extracted features of 10 EEG channels, performs with 91.3% accuracy for arousal and 91.1% accuracy for valence, both in the beta frequency band. Our approach shows better performance compared to existing algorithms applied to the "DEAP" dataset.