Enhancement of classification accuracy of a time-frequency approach for an EEG-based brain-computer interface

N. Yamawaki, C. Wilke, L. Hue, Z. Liu, B. He

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Objectives: The aim of this paper is to develop a new algorithm to enhance the performance of EEG-based brain-computer interface (BCI). Methods: We improved our time-frequency approach of classification of motor imagery (MI) tasks for BCI applications. The approach consists of Loplacian filtering, band-pass filtering and classification by correlation of time-frequency-spatial patterns. Results and Conclusions: Through off-line analysis of data collected during a "cursor control" experiment, we evaluated the capability of our new method to reveal major features of the EEG control for enhancement of MI classification accuracy. The pilot results in a human subject are promising, with an accuracy rate of 96.1%.

Original languageEnglish (US)
Pages (from-to)155-159
Number of pages5
JournalMethods of information in medicine
Volume46
Issue number2
DOIs
StatePublished - 2007

Keywords

  • Brain-computer interface
  • EEG
  • Motor imagery
  • Time-frequency analysis

Fingerprint

Dive into the research topics of 'Enhancement of classification accuracy of a time-frequency approach for an EEG-based brain-computer interface'. Together they form a unique fingerprint.

Cite this