Design of brain machine interface using portable Near-InfraRed Spectroscopy

In recent years, robotics and medical sciences have focused on a new input interface, “the Brain-Machine Interface (BMI).” This measures human cerebral activities and uses them directly as an input signal to instruments, machines, robots, etc. In this research, we aim to design a practical BMI system using a portable Near-InfraRed Spectroscopy (NIRS) device that can be used reliably in the living environment. In this paper, we will discuss a method to improve the classification performance of human cerebral activities in the living environment. The influence of daily living activities and the effect of the image evoking training and the additional learning are investigated experimentally.