Classification of EEG signals produced by musical notes as stimuli

Abstract

In this paper, we present the classification of electroencephalograph (EEG) signals produced by the first-octave musical notes of the piano as stimuli. The EEG classification of musical notes is attempted for the first time, to the best of our knowledge. This type of classification could be applied towards the development of Brain-Computer Interfaces (BCIs) for the composition of music via thought as well as the definition of mappings between different stimuli for Sensory Substitution Devices (SSDs) that are based on their actual impact on brain signals and thus serve better the purpose of SSDs, which is to translate between senses at the perceptual level. Event-Related Spectral Perturbations (ERSP) are extracted as features and are fed into a Support Vector Machine (SVM) classifier. Our aim was to classify musical notes as C, C#, D, D#, E, F, F#, G, G#, A, A#, B and we have achieved it with an average accuracy of 70%.