CLASSIFICATION OF EEG SIGNAL BY METHODS OF MACHINE LEARNING

Electroencephalogram (EEG) signal of two healthy subjects that was available from literature, was studied using the methods of machine learning, namely, decision trees (DT), multilayer perceptron (MLP), K-nearest neighbours (kNN), and support vector machines (SVM). Since the data were imbalanced, th...

Full description

Saved in:
Bibliographic Details
Published inApplied Computer Science (Lublin) Vol. 16; no. 4; pp. 56 - 63
Main Authors ALYAMANI, Amina, YASNIY, Oleh
Format Journal Article
LanguageEnglish
Published 30.12.2020
Online AccessGet full text
ISSN1895-3735
2353-6977
DOI10.35784/acs-2020-29

Cover

More Information
Summary:Electroencephalogram (EEG) signal of two healthy subjects that was available from literature, was studied using the methods of machine learning, namely, decision trees (DT), multilayer perceptron (MLP), K-nearest neighbours (kNN), and support vector machines (SVM). Since the data were imbalanced, the appropriate balancing was performed by Kmeans clustering algorithm. The original and balanced data were classified by means of the mentioned above 4 methods. It was found, that SVM showed the best result for the both datasets in terms of accuracy. MLP and kNN produce the comparable results which are almost the same. DT accuracies are the lowest for the given dataset, with 83.82% for the original data and 61.48% for the balanced data.
ISSN:1895-3735
2353-6977
DOI:10.35784/acs-2020-29