Open AccessWavelet transform for the identification of P300
Author(s) -
Vladimir Bulanov,
А. В. Захаров,
Е В Хивинцева
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/862/5/052049
Subject(s) - pattern recognition (psychology) , wavelet transform , wavelet , artificial intelligence , event related potential , computer science , electroencephalography , identification (biology) , signal processing , speech recognition , psychology , digital signal processing , botany , psychiatry , computer hardware , biology
The reliability of a newly developed algorithm for the identification of the P300 component of event-related potentials based on a continuous wavelet transform was investigated. The electroencephalogram records of one participant made by using a three-stimulus paradigm (a kind of the odd-ball paradigm) were analyzed. The accuracy of identification of certain wavelet types for the detection of P300 was from 76.32 to 86.84%. Thus, relatively simple algorithms for processing and classifying the electroencephalogram record signal show acceptable results in terms of the accuracy of identification of the P300 component of event-related potentials based on randomly selected data.