ELECTROENCEPHALOGRAM PATTERN CLASSIFICATION DEVICE, ELECTROENCEPHALOGRAM PATTERN CLASSIFICATION METHOD, ELECTROENCEPHALOGRAM PATTERN CLASSIFICATION PROGRAM, AND NEURO-FEEDBACK SYSTEM

摘要

PROBLEM TO BE SOLVED: To provide an electroencephalogram pattern classification device capable of reducing a time until starting use by a user even in the case of performing processing of classifying electroencephalogram patterns by detecting an electroencephalogram signal in a non-invasive manner.;SOLUTION: An electroencephalogram pattern classification device, after executing filter processing in a predetermined frequency region on measurement data from an electroencephalograph (S100), asynchronously executes classification of brain action patterns using an adaptive CSP (Common Spatial Patterns) method. The electroencephalogram pattern classification device, therefore, performs adaptive whitening processing on a measurement signal (S102); subtracts a moving average from an extracted feature amount to perform adaptive conversion to a feature amount exerting a zero average (S106); and performs classification on the adapted feature amount using a classifier (S108).;SELECTED DRAWING: Figure 6;COPYRIGHT: (C)2018,JPO&INPIT