Owing to its multidimensional nature and complexity, music requires a higher neural demand and the process of plasticity causes structural differences between the brains of people who practice (musicians) and do not practice (non-musicians) musical instruments. Recent studies have been conducted in order to understand these differences and the way the brain processes music. Musics are able to extract the components found in conventional studies of evoked potential in Electroencephalogram (EEG) and, from the selection of acoustic features extracted from the audio signals, it is possible to determine the time instants of the music where there is a high contrast (triggers), considered as stimuli in EEG signal analysis. The main objective of this work is to develop a computational model capable of classifying, through supervised learning, the EEG signals recorded by a group of volunteers in musicians and nonmusicians. This model is composed of the following 6 steps: (1-2) Extraction and selection of acoustic features; (3) Selection of triggers; (4-5) Processing and analysis of EEG signals; and (6) Classification. Experiments were carried out with 26 volunteers, 13 non-musicians and 13 amateur musicians, who listened to two classical music (Hungarian Dance No.5, from Johannes Brahms, and The Barber of Seville-Overture, from Gioachino Rossini), while it was performed the acquisition of EEG signals using dry electrodes. For the classification were proposed two scenarios that composed the input data of the classifiers, varying the latency in which the EEG signal was observed. As classifiers, the k-NN and the Neural Network were used. It was possible to obtain as a result an assertive rate above 80% for both songs using the k-NN.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.