Classification of EEG-P300 signals using phase locking value and pattern recognition classifiers

Rupesh Kumar Chikara, Li-Wei Ko*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

In this paper, we present a classification method based on electroencephalogram (EEG) signal during left hand and right hand response inhibition (stop success vs stop fail) from different participants. The system uses phase locking value (PLV) for the features extraction and pattern recognition algorithm for classification. There are four classifiers: QDC, KNNC, PARZENDC and LDC used in this paper to estimate the accuracy of our system. Based on the collected time-domain EEG signals, the phase locking value (PLV) from C3-CZ and C4-CZ electrodes are calculated and then used as the feature and input for the classifiers algorithm. The classification system demonstrate an accuracy of 92 % in LDC. The results of this study suggest the method could be utilized effectively for response inhibition identification.

Original languageEnglish
Title of host publicationTAAI 2015 - 2015 Conference on Technologies and Applications of Artificial Intelligence
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages367-372
Number of pages6
ISBN (Electronic)9781467396066
DOIs
StatePublished - 12 Feb 2016
EventConference on Technologies and Applications of Artificial Intelligence, TAAI 2015 - Tainan, Taiwan
Duration: 20 Nov 201522 Nov 2015

Publication series

NameTAAI 2015 - 2015 Conference on Technologies and Applications of Artificial Intelligence

Conference

ConferenceConference on Technologies and Applications of Artificial Intelligence, TAAI 2015
CountryTaiwan
CityTainan
Period20/11/1522/11/15

Keywords

  • BCI
  • Classification
  • EEG
  • PLV
  • Response Inhibition

Fingerprint Dive into the research topics of 'Classification of EEG-P300 signals using phase locking value and pattern recognition classifiers'. Together they form a unique fingerprint.

Cite this