English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Received: 14 November 2019 Accepted: 20 January 2020 The electroencephalogram (EEG) signal is known as a nonlinear and complex signal. The EEG signal has very important information about brain activities and disorders which can detect by an accurate Computer-aided diagnosis system. The performance of the Computer-aided diagnosis system directly depends on using features in the classifiers. In this paper, we proposed nonlinear geometrical features for the classification of EEG signals. The normal, interictal and ictal EEG signals of the Bonn university EEG database are plotted in 2D space by a novel approach and considering their patterns, six features namely: area of the octagon (AOO), circle area (CA), the summation of vectors length (SVL), centroid to centroid (CTC) and triangle area (TA) are extracted on different aspects of distance in Cartesian space. Based on the Kruskal–Wallis statistical test, all of the features were found statistically significant in the discrimination of normal vs. ictal and interictal vs. ictal EEG signals (p-value≈0). Also, the edges of 2D projection EEG signals in the ictal group were sharper than normal and interictal groups. Besides, 2D projection of normal and interictal EEG signals has more regular geometrical shapes than the ictal group. Our proposed features were applied as input on support vector machine (SVM) and k-nearest neighbors (KNN) classifiers which resulted in more than 99% classification accuracy in a ten-fold cross-validation strategy.

A Novel Geometrical Method for Discrimination of Normal, Interictal and Ictal EEG Signals