Filter-bank local region complex-valued common spatial pattern for Motor imagery classification

Yongkoo Park, Wonzoo Chung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper represents a novel motor-imagery (MI) classification method based on a local region filter-bank common spatial pattern (LRFBCSP) using complexed form of electroencephalography (EEG) signals. LRFBCSP approach selects the MI-relevant local region which is constructed by individual channels and their neighbors by comparing their eigenvalue disparity. We propose an extension version of the LRFBCSP by considering the complex-valued spatial filtering rather than the real-valued spatial filtering. The complex-valued spatial filtering improves the discrimination of each local region and provides enhanced CSP features. Simulation result shows the performance improvement of the proposed method for BCI competition III dataset IVa by comparing the CSP-based methods.

Original languageEnglish
Title of host publication8th International Winter Conference on Brain-Computer Interface, BCI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728147079
DOIs
Publication statusPublished - 2020 Feb
Event8th International Winter Conference on Brain-Computer Interface, BCI 2020 - Gangwon, Korea, Republic of
Duration: 2020 Feb 262020 Feb 28

Publication series

Name8th International Winter Conference on Brain-Computer Interface, BCI 2020

Conference

Conference8th International Winter Conference on Brain-Computer Interface, BCI 2020
Country/TerritoryKorea, Republic of
CityGangwon
Period20/2/2620/2/28

Keywords

  • Bain-computer interfaces (BCIs)
  • common spatial pattern (CSP)
  • component
  • electroencephalography (EEG)

ASJC Scopus subject areas

  • Behavioral Neuroscience
  • Cognitive Neuroscience
  • Artificial Intelligence
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Filter-bank local region complex-valued common spatial pattern for Motor imagery classification'. Together they form a unique fingerprint.

Cite this