Conference paper
Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training
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.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2013 |
Pages: | 4279-4282 |
Proceedings: | 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
ISBN: | 1457702150 , 1457702169 , 9781457702150 and 9781457702167 |
ISSN: | 1557170x |
Types: | Conference paper |
DOI: | 10.1109/EMBC.2013.6610491 |
ORCIDs: | Sørensen, Helge Bjarup Dissing and Puthusserypady, Sadasivan |
Autocorrelation Brain-Computer Interface Engineered Materials, Dielectrics and Plasmas Naïve-Bayes Classifier Steady-State Visual Evoked Potentials Tri-training
Accuracy Bayes methods Brain-computer interfaces CRT-monitor Correlation Error analysis Naive-Bayes classifier PC SSVEP-based brain-computer interface Signal to noise ratio Training Visualization accuracy autocorrelation-based feature biomedical electrodes brain-computer interfaces cathode-ray tubes correlation methods data processing feature extraction frequency 100 Hz gUSB-amp medical signal processing scalp electrode signal acquisition signal classification signal preamplification stimulus control tritraining based semisupervised steady-state visual evoked potential-based BCI visual evoked potentials