Abstract

In this study, we introduce a novel automated system for the detection and prediction of epileptic seizures. Statistical features are extracted from the EEG signal and are passed to a modified Support Vector Machine (SVM) algorithm for classification. Epilepsy is one of the most commonly encountered neurological disorders. Epilepsy is associated with unpredictable seizures. The cause of these seizures is usually unknown. Seizures are embedded in the Electroencephalogram (EEG) signal which represents the brain’s electrical activities. The EEG signal can be recorded either from the scalp or invasively from the cortex using intracranial electrodes. This study reveals that the standard deviation and mean of the input EEG signal form discriminative features. Testing the performance of the proposed system on a publicly available epilepsy dataset provided by the University of Bonn, achieved 100% accuracy. The proposed system requires up to 83% fewer clock cycles than the lift algorithm and 88% fewer clock cycles than the convolution-based algorithm.

Keywords:

Epilepsy, Electroencephalogram (EEG), seizure detection, statistical moments, Support Vector, Machine (SVM), time complexity,

References

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.