Summary
International Symposium on Nonlinear Theory and Its Applications
2015
Session Number:A5L-D
Session:
Number:A5L-D-2
Time-Series Prediction and Classification of NIRS Data Using the Extreme Learning Machine
Hiroki Ogihara, Masaharu Adachi,
pp.381-384
Publication Date:2015/12/1
Online ISSN:2188-5079
DOI:10.34385/proc.47.A5L-D-2
PDF download (302.1KB)
Summary:
In recent years, brain activity measurement by near-infrared spectroscopy (NIRS) has been applied to brain--machine interfaces (BMIs). Classification of brain activity based on measurement data is a fundamental step in the development of BMIs. It has been reported that classification of NIRS data by support vector machines is promising. In this paper, we introduce the extreme learning machine (ELM) for the classification of brain activity measurement data by NIRS. As a result, ELM improves classification accuracy and reduces calculation times in comparison with conventional methods.