The Proceedings of the Transportation and Logistics Conference
Online ISSN : 2424-3175
2015.24
Session ID : 2309
Conference information
2309 Development of portable NIRS-BCI system using machine learning
Akari SHIMOSEKazuki YANAGISAWAHitoshi TSUNASHIMA
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
Brain Computer Interface (BCI) is a system that controls machines and devices by extracting neural information from human brain activity and it is expected for nursing robot such as an artificial hand. The present study focuses on BCI that uses near-infrared spectroscopy (NIRS). However a conventional detection method of brain activity is simple thresholding. Therefore, it is difficult obtain highly accurate control operations. In this study, we developed an NIRS-BCI system with the neural network. This system can detect the intention from human brain activity and output on/off signal in real time. Performance evaluation of the sysem showed the correct rate using virtual NIRS signal was 97.9% and the average correct rate using NIRS signal measured from 10 participants was 61.8%.
Content from these authors
© 2015 The Japan Society of Mechanical Engineers
Previous article Next article
feedback
Top