Evaluation of window size in classification of epileptic short-term EEG signals using a Brain Computer Interface software

Journal Title: Engineering, Technology & Applied Science Research - Year 2018, Vol 8, Issue 4

Abstract

The complexity of epilepsy created a fertile ground for further research in automated methods, attempting to help the epileptologists’ task. Over the past years, great breakthroughs have emerged in computer-aided analysis and the advent of Brain Computer Interface (BCI) systems has greatly facilitated the automated seizure analysis. In this study, an evaluation of the window size in automated seizure detection is proposed. The EEG signals from the University of Bonn was employed and segmented into 24 epochs of different window lengths with 50% overlap each time. Statistical and spectral features were extracted in the OpenViBE scenario that were used to train four different classifiers. Results in terms of accuracy were above 80% for the Decision Trees classifier. Also, results indicated that different window sizes provide small variations in classification accuracy.

Authors and Affiliations

K. D. Tzimourta, L. G. Astrakas, A. M. Gianni, A. T. Tzallas, N. Giannakeas, I. Paliokas, D. G. Tsalikakis, M. G. Tsipouras

Keywords

Related Articles

Photoelastic Analysis of the Vertebral Fixation System Using Different Screws

The purpose of this study was to compare using photoelasticity, the internal stresses produced by two types of pedicular screws (Synthes™) with three different diameters, when submitted to different pullout strengths. Th...

Design and Simulation of a Decentralized Railway Traffic Control System

With the increasing use of railway transportation, various methods have been developed for the control and management of train traffic. Train traffic control systems that are currently in use are overwhelmingly centraliz...

Utilization of Construction Waste Tiles as a Replacement for Fine Aggregates in Concrete

Ceramic wastes are found to be suitable for usage as substitution for fine and coarse aggregates in concrete production. This study is an investigation into the utilization of waste tiles as partial replacement for fine...

Optimal Power Factor for the Reactive Load of Small Hydro Power Plants

This article explores the operation algorithm of an excitation regulator of synchronous generators of small Hydro Power Plants (HPPs). The aim is to provide optimum economic parameters, consistent with the dynamically ch...

Perspectives on a Big Data Application: What Database Engineers and IT Students Need to Know

Cloud Computing and Big Data are important and related current trends in the world of information technology. They will have significant impact on the curricula of computer engineering and information systems at universi...

Download PDF file
  • EP ID EP168829
  • DOI -
  • Views 255
  • Downloads 0

How To Cite

K. D. Tzimourta, L. G. Astrakas, A. M. Gianni, A. T. Tzallas, N. Giannakeas, I. Paliokas, D. G. Tsalikakis, M. G. Tsipouras (2018). Evaluation of window size in classification of epileptic short-term EEG signals using a Brain Computer Interface software. Engineering, Technology & Applied Science Research, 8(4), -. https://europub.co.uk/articles/-A-168829