Volume 11, Issue 3 (9-2008)
J Arak Uni Med Sci 2008, 11(3): 89-97 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Arab M M, Suratgar A, Rezaei Ashtiani A. EEG Signals Processing for Diagnosis Petitmal (absence) and Grandmal Epilepsies Using Artificial Neural Network . J Arak Uni Med Sci 2008; 11 (3) :89-97
URL: http://jams.arakmu.ac.ir/article-1-208-en.html
URL: http://jams.arakmu.ac.ir/article-1-208-en.html
1- , m_r_arab@arakmu.ac.ir
Abstract: (28331 Views)
Background: Epileptic seizures are manifestation of epilepsy. Understanding of the mechanisms causing epileptic disorder needs careful analyses of the electroencephalograph (EEG) records. The detection of epileptic form discharges (spike wave) in the EEG is an important component in the diagnosis of epilepsy. Approximately one in every 100 persons will experience a seizure at some time in their life. Already intelligence spike detection method discucsed but purpose of this research is diagnosis of different kind of epilepsy (grandmal and Petitmal) by design of an intelligence diagnosis processing. Methods and Materials: In this descriptive study, 100 EEG signals of brain hemispheres from different person in healthy, interictal and ictal conditions were used. Fifty Hz noise and artifact signals were removed by soft ware procedure then signals separated by expert neurologist to three categories, healthy (frequency band 8-12 Hz), petitmal seizures (typical 3 Hz), grandmal seizures (clonic stage with 4 Hz frequency) and divided each of them to 6 seconds segments. Information of this signals (background alpha, spike and slow, poly spike and poly sharp) were extracted by wavelet transform and classified by soft ware procedure neural network to there groups healthy, ptitmal and grandmal epilepsy. Results: In designed software accuracy of diagnosis ptitmal and grandmal epilepsies was obtained about 80% Conclusion: This method introduced intelligent diagnosis of epilepsy (ptitmal and gradmal) and automatically detected healthy person from epileptic patients. One of the other advantages is help to neurologist for detection of sickness clearly and expendable different kinds of other epilepsy
Subject:
General
Received: 2009/03/4
Received: 2009/03/4
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
