Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training

Thomas Bender, Troels W. Kjaer, Carsten E. Thomsen, Helge Bjarup Dissing Sørensen, Sadasivan Puthusserypady

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

This paper presents a novel and computationally simple tri-training based semi-supervised steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI). It is implemented with autocorrelation-based features and a Naïve-Bayes classifier (NBC). The system uses nine characters presented on a 100 Hz CRT-monitor, three scalp electrodes for signal acquisition, a gUSB-amp for preamplification and two PCs for data-processing and stimulus control respectively. Preliminary test results of the system on nine healthy subjects, with and without tri-training, indicates that the accuracy improves as a result of tri-training.
Original languageEnglish
Title of host publicationIEEE Engineering in medicine and biology society conference proceedings
Number of pages4
PublisherIEEE
Publication date2013
Pages4279-4282
ISBN (Print)978-1-4577-0216-7
DOIs
Publication statusPublished - 2013
Event35th Annual International Conference of the IEEE EMBS - Osaka, Japan
Duration: 3 Jul 20137 Jul 2013

Conference

Conference35th Annual International Conference of the IEEE EMBS
Country/TerritoryJapan
CityOsaka
Period03/07/201307/07/2013

Keywords

  • Engineered Materials, Dielectrics and Plasmas
  • Brain-Computer Interface
  • Steady-State Visual Evoked Potentials
  • Tri-training
  • Autocorrelation
  • Naïve-Bayes Classifier

Fingerprint

Dive into the research topics of 'Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training'. Together they form a unique fingerprint.

Cite this