A robust and subject-specific sequential forward search method for effective channel selection in brain computer interfaces

AYDEMİR Ö., Ergün E.

JOURNAL OF NEUROSCIENCE METHODS, vol.313, pp.60-67, 2019 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 313
  • Publication Date: 2019
  • Doi Number: 10.1016/j.jneumeth.2018.12.004
  • Journal Name: JOURNAL OF NEUROSCIENCE METHODS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.60-67
  • Keywords: Brain computer interface, Channel selection, Feature extraction, Classification, COMMON SPATIAL-PATTERN, EEG SIGNALS, MOTOR-IMAGERY, CLASSIFICATION, MOVEMENT, ALGORITHM
  • Karadeniz Technical University Affiliated: Yes

Abstract

Background: The input signals of electroencephalography (EEG) based brain computer interfaces (BCI) are extensively acquired from scalp with a multi-channel system. However, multi-channel signals might contain redundant information and increase computational complexity. Furthermore, using only effective channels, rather than all channels, may enhance the performance of the BCI in terms of classification accuracy (CA).