Open AccessMACHINE LEARNING BASED EEG SIGNAL CLASSIFICATION
Author(s) -
Anjali Vasant Kadwe
Publication year - 2019
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2019.v04i03.027
Subject(s) - electroencephalography , computer science , signal (programming language) , artificial intelligence , pattern recognition (psychology) , speech recognition , machine learning , psychology , neuroscience , programming language
Epilepsy is a neurological disorder which is characterized by transient and unexpected electrical disturbance of the brain. The electroencephalogram (EEG) is a commonly used signal for detection of epileptic seizures. The proposed method is based on the classification of EEG signal with the less number of sample and more accurately by using the Matlab software. The Bonn University Data set use in this project provide classification of EEG signal by using the latest transform method. The project consist of Extraction of the data from text file,Frequency domain low pass filtering And Feature extraction by three most recent transform such as Coiflet Transform, Stationary Wavelet Transform (SWT) and Walsh Hadamard Transform (WHT). This transformed signal is the classified by KNN ensemble classification.This project provide an overall classification accuracy of 99%.