Authors
Yasushi Bandou, Takuya Hayakawa, Jun Kobayashi*
Department of Systems Design and Informatics, Kyushu Institute of Technology,
Iizuka 820-8502, Japan
*
Corresponding author. Email: [email protected]
Corresponding Author
Jun Kobayashi
Received 16 October 2018, Accepted 19 November 2018, Available Online 30
March 2019.
DOI
https://doi.org/10.2991/jrnal.k.190220.014
Keywords
Brain computer interface; electroencephalography; support vector machine;
neural network; mobile robot control
Abstract
Here we present experimental results of Electroencephalogram (EEG)-based
Brain Computer Interface (BCI) for mobile robot control by means of Support
Vector Machine (SVM) and Neural Network (NN). The authors had trained NNs
using EEGs collected from subjects and verified the performance as BCI;
however, the results were unsatisfactory for practical use. In this study,
we have used SVM with Radial Basis Function (RBF) kernel function for further
improvement and compared the performance with the NNs. Consequently, the
SVMs outperformed the NNs in almost all cases.
Copyright
© 2019 The Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license
(http://creativecommons.org/licenses/by-nc/4.0/).