Classification of EEG signals using Machine learning algorithms
S. Suganyadevi, S. Shanmuga Priya, B. Kiruba, M. Gomathi, Jagadevi. N. Kalshetty
Abstract
An alternative to human expert-performed manual identification is automatic detection of epilepsy using electroencephalogram (EEG) data. Automatic epilepsy detection from EEG data need high classification performance in order to eliminate false positives. A classification strategy for automated epilepsy identification using EEG data is being proposed in this work. The signals generated form the EEG device were transformed using the DWT before feature extraction was carried out. Based on various statistical parameters and crossing frequency features, an algorithm dubbed GBMs fusion was developed to identify EEG data. As an added bonus, the significant traits were first selected using a genetic algorithm. EEG data from the University of Bonn has been used to test the suggested method's ability to distinguish between normal and ictal EEG patterns. Experimentation has shown that the suggested GBMs fusion may increase the EEG classification performance. It is also possible to identify epilepsy from EEG data with a 100% accuracy using the suggested GBMs fusion.