Development of estimation method about activity states for NIRS-based BCI system

In recent years, BCI (Brain-Computer Interface) is attracting attention as a method of providing an ALS (amyotrophic lateral sclerosis) patient with an alternative communication means. NIRS (near-infrared spectroscopy) is a non-invasive technology that is able to measure changes in cerebral blood flow. This research rewords development of a BCI system, which can be used to operate a machine by recollecting the image of hand movement. As the fundamental experiment, we measured brain activity during hand movement using a NIRS. In this paper, we describe the estimation approach about the start and end timings hand of movement using a neural network. In addition, we describe a method for classifying into right- or left-hand movement from NIRS signals.