YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM LTD.;B. G. NEGEV TECHNOLOGIES AND APPLICATIONS LTD. AT BEN-GURION UNIVERSITY
发明人:
Leon Y. DEOUELL,Amir B. GEVA,Galit FUHRMANN ALPERT,Ran El MANOR,Shani SHALGI
申请号：
US14784314
公开号：
US20160051163A1
申请日:
2014.04.13
申请国别(地区):
US
年份:
2016
代理人:
摘要：
Systems and method for classifying EEG signals of a human subject generated responsive to a series of images containing target images and non-target images. The EEG signals are in a spatio-temporal representation. The time points are classified independently, using a linear discriminant classifier, to compute spatio-temporal discriminating weights that are used to amplify the spatio-temporal representation, to create a spatially-weighted representation. Principal Component Analysis is used on a temporal domain for dimensionality reduction, separately for each spatial channel of the signals, to create a projection, which is applied to the spatially-weighted representation onto a first plurality of principal components, to create a temporally approximated spatially weighted representation. The temporally approximated spatially weighted representation is classified over the channels, using said linear discriminant classifier, to yield a binary decisions series indicative of each image of the images series as either belonging to said target image or to said non-target image.
