Open AccessA multivariate statistical analysis of EEG signals for differentiation of musicians and non-musicians
Author(s) -
Estela Ribeiro,
Carlos Eduardo Thomaz
Publication year - 2018
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/eniac.2018.4442
Subject(s) - electroencephalography , multivariate statistics , dance , active listening , linear discriminant analysis , speech recognition , computer science , multivariate analysis , statistical analysis , psychology , subject (documents) , pattern recognition (psychology) , artificial intelligence , machine learning , communication , mathematics , statistics , neuroscience , visual arts , art , library science
It is possible to reveal whether a subject received musical training through the neural activation patterns induced in response to music listening. We are particularly interested in analyzing the brain data on a global level, considering its activity registered in electroencephalogram electrodes signals. Our experiments results, with 13 musicians and 12 non-musicians who listened the song Hungarian Dance No 5 from Johannes Brahms, have shown that is possible to differentiate musicians and non-musicians with high classification accuracy (88%). Given this multivariate statistical framework, it has also been possible to highlight the most expressive and discriminant changes in the participants brain according to the acoustic features extracted from the audio.