Improving EEG-based BCI Neural Networks for Mobile Robot Control by Bayesian Optimization

Authors
Takuya Hayakawa, Jun [email protected]
Department of Systems Design and Informatics, Kyushu Institute of Technology, Kawazu 680-4, Iizuka, 820-8502, Japan
lab.jkoba.net

Available Online 30 June 2018.
DOI
https://doi.org/10.2991/jrnal.2018.5.1.10
Keywords
brain computer interface; electroencephalography; neural network; hyperparameters; Bayesian optimization; mobile robot control
Abstract
The aim of this study is to improve classification performance of neural networks as an EEG-based BCI for mobile robot control by means of hyperparameter optimization in training the neural networks. The hyperparameters were intuitively decided in our preceding study. It is expected that the classification performance will improve if you determine the hyperparameters in a more appropriate way. Therefore, the authors have applied Bayesian optimization to training the EEG-based BCI neural networks and achieved the performance improvement.

Copyright
Copyright © 2018, the Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).

Download article (PDF)