Analysis of EEG signals using mathematical morphology decomposition and kurtosis: Detection of epileptiforms
Epileptic seizures are indicators of epilepsy. Thorough analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diag...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
International Society of Computers and Their Applications (ISCA)
2014
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/58416/ http://irep.iium.edu.my/58416/ http://irep.iium.edu.my/58416/1/58416_Analysis%20of%20EEG%20signals_complete.pdf http://irep.iium.edu.my/58416/2/58416_Analysis%20of%20EEG%20signals_scopus.pdf |
| Summary: | Epileptic seizures are indicators of epilepsy. Thorough analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in diagnostic classification. This paper reviews the fundamental operations of Mathematical Morphology and its application in EEG signals processing. The nature of epileptic EEG is hidden in its geometric structure and Mathematical Morphology is applied to decompose and quantize EEG Signal based on its geometric structure. Kurtosis which gives measure of peakiness of a signal is calculated for each of the constituents from which the feature vector is constructed. Multi-layer Perceptron (MLP) is used for classification to differentiate between various types of EEG classes. The differentiation between epileptic and normal EEG is achieved with accuracy of around 90%. |
|---|