Other Links

Indexed By

    •

Volume 9 Issue 3 - January 2018

  • 1. Hilbert transform and rbf-kernel based support vector machine synergy for automatic classification of eeg signals

    Authors : Raj Vipani, Sambit Hore, Souryadeep Basak, Saibal Dutta

    Pages : 22-28

    DOI : http://dx.doi.org/10.21172/1.93.04

    Keywords : EEG SignalsHilbert TransformSupport Vector Machine

    Abstract :

    This paper presents a machine learning approach for the development of a computer aided Radial Basis Function kernel based Support Vector Machine (SVM) used to analyze and classify EEG signals. The algorithm proposed in this work is used to achieve timely and accurate detection of the onset of epileptic seizures. As the brain’s electrical activity is composed of numerous signals with overlapping characteristics, it is important to develop a non-invasive method so that epileptic patients receive proper medical attention hours before the seizures occur. In this paper, a feature extractor is developed which is combined with a RBF Kernel based Support Vector Machine to classify epileptic subjects from healthy subjects. Analysis of real time EEG signals is simplified by using the Hilbert Transform which converts the signals into analytic signals. The proposed algorithm is developed using the MATLAB software and the average accuracy of classification is obtained to be 93.89%.

    Citing this Journal Article :

    Raj Vipani, Sambit Hore, Souryadeep Basak, Saibal Dutta, "Hilbert transform and rbf-kernel based support vector machine synergy for automatic classification of eeg signals", Volume 9 Issue 3 - January 2018, 22-28

    Click here to Submit Copyright Takedown Notice for this article.

    View Paper