Journal of ICT Research and Applications ITB Bandung Vol. 15 No. 1 2021
Extraction of the Major Features of Brain Signals using Intelligent Networks

Journal of ICT Research and Applications ITB Bandung Vol. 15 No. 1 2021
Extraction of the Major Features of Brain Signals using Intelligent Networks

brain-computer interface; EEG signal; P300 component; recurrent neural network; twin support vector machine.

Abstract. The brain-computer interface is considered one of the main tools for implementing and designing smart medical software. The analysis of brain signal data, called EEG, is one of the main tasks of smart medical diagnostic systems. While EEG signals have many components, one of the most important brain activities pursued is the P300 component. Detection of this component can help detect abnormalities and visualize the movement of organs of the body. In this research, a new method for processing EEG signals is proposed with the aim of detecting the P300 component. Major features were extracted from the BCI Competition IV EEG data set in a number of steps, i.e. normalization with the purpose of noise reduction using a median filter, feature extraction using a recurrent neural network, and classification using Twin Support Vector Machine. Then, a series of evaluation criteria were used to validate the proposed approach and compare it with similar methods. The results showed that the proposed approach has high accuracy.

Shirin Salarian & Amir Shahab Shahabi

DOI: 10.5614/itbj.ict.res.appl.2021.15.1.5

IRCS-ITB

07 Mei 2021

Sri Wahyuni

ISSN: 2337-5787

PDF

English

Text

Journal of ICT Research and Applications ITB Bandung Vol. 15 No. 1 2021