Motor Imagery Classification Using Rough Neural Network
Ratio mathematica · 01.12.2022
DOI: 10.23755/rm.v44i0.902 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ratio mathematica, erschienen am 01.12.2022. Verfasst von J Anila Maily und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Brain Computer Interface is a system which provides a communication channel between the user and a computer without using the normal neuromuscular pathways. With BCI a user will be able to communicate with the mind. In a BCI system the brain activities are measured using EEG acquisition system. The acquired brain signals are analyzed and classified to identify the user’s intention. Motor imagery BCI works by making the user imagine their body parts without actually moving it. Prominent features are extracted from the acquired brain signals and the extracted features are classified to find the motor imagery performed by the user. This study uses datasets are provided by the Dr. Cichocki's Lab (Lab for Advanced Brain Signal Processing). We propose the Rough Neural Network (RNN) for Motor imagery classification. The experimental results show that RNN classifier gives higher accuracy than Backpropagation Classifier
Schlagwörter
Zitieren
APA
Maily, J. A., Velayutham, C., & Sathik, M. M. (2022). Motor Imagery Classification Using Rough Neural Network. Ratio mathematica. https://doi.org/10.23755/rm.v44i0.902
Vancouver
Maily JA, Velayutham C, Sathik MM. Motor Imagery Classification Using Rough Neural Network. Ratio mathematica. 2022. doi:10.23755/rm.v44i0.902
BibTeX
@article{Maily2022,
author = {Maily, J Anila and Velayutham, C and Sathik, M. Mohamed},
title = {Motor Imagery Classification Using Rough Neural Network},
journal = {Ratio mathematica},
year = {2022},
doi = {10.23755/rm.v44i0.902}
}
EUVIMED