Classification of EEG signals in four groups, including healthy subjects with open/closed eyes and epilepsy subjects with/without seizure by PSD estimate (using the multitaper method) and ANN

Electroencephalography (EEG) analysis by physicians is intricate, time consuming and needs to experience. Therefore automated systems for EEG analysis and classification are able to help physician. EEG signal in the field of time is raw and complex so it's not suitable for automated system. The...

Full description

Saved in:
Bibliographic Details
Main Authors: Alipoor, Masoud, Pooyan, Mohammad, Suratgar, Amir Abolfazl
Format: Conference Proceeding
Language:English
Subjects:
Artificial Neural Network (ANN)
Artificial neural networks
Automatic Diagnosis
Classification
Electrodes
Electroencephalography
Electroencephalography (EEG)
Epilepsy
Eyes
Frequency
Neurons
Power Spectral Density (PSD)
Scalp
Signal analysis
Signal processing
Thomson Multitaper Method's (MTM)
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Electroencephalography (EEG) analysis by physicians is intricate, time consuming and needs to experience. Therefore automated systems for EEG analysis and classification are able to help physician. EEG signal in the field of time is raw and complex so it's not suitable for automated system. Therefore appropriate features of EEG signal becomes extraction using signal processing methods (in this paper used Thomson multi taper method's (MTM)), then these features becomes classification by ANN. Also we have to correct the ANN outputs by a threshold function. In this study, EEG signals are classified in three groups (including epileptic patients with seizure or without seizure and healthy volunteers) with 98.02% accuracy and in two groups (healthy with closed or open eyes) with 97.7% accuracy.
DOI:10.1109/HIBIT.2010.5478900