Evaluation of Classical Features and Classifiers in Brain-Computer Interface Tasks

TL;DR

This study evaluates classical features and classifiers for brain signal classification in BCI tasks, finding that energy features in alpha and beta bands combined with Bayesian and SVM classifiers yield higher accuracy.

Contribution

It systematically compares classical features and classifiers across multiple datasets, providing insights into effective strategies for brain signal classification in BCI.

Findings

Energy features in alpha and beta bands are most effective.

Bayesian classifier with Gaussian assumption outperforms others.

SVM achieves high accuracy across datasets.

Abstract

Brain-Computer Interface (BCI) uses brain signals in order to provide a new method for communication between human and outside world. Feature extraction, selection and classification are among the main matters of concerns in signal processing stage of BCI. In this article, we present our findings about the most effective features and classifiers in some brain tasks. Six different groups of classical features and twelve classifiers have been examined in nine datasets of brain signal. The results indicate that energy of brain signals in {\alpha} and \b{eta} frequency bands, together with some statistical parameters are more effective, comparing to the other types of extracted features. In addition, Bayesian classifier with Gaussian distribution assumption and also Support Vector Machine (SVM) show to classify different BCI datasets more accurately than the other classifiers. We believe that the results can give an insight about a strategy for blind classification of brain signals in brain-computer interface.