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

Thomas Bender; Troels W. Kjaer; Carsten E. Thomsen; Helge B D Sorensen; S. Puthusserypady

doi:10.1109/embc.2013.6610491

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

Thomas Bender, Troels W. Kjaer, Carsten E. Thomsen, Helge B D Sorensen, S. Puthusserypady

3 Citations (Scopus)

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 language	English
Title of host publication	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Number of pages	4
Publication date	31 Oct 2013
Pages	4279-4282
Article number	6610491
ISBN (Print)	9781457702167
DOIs	https://doi.org/10.1109/embc.2013.6610491
Publication status	Published - 31 Oct 2013

Keywords

Autocorrelation
Brain-Computer Interface
Naïve-Bayes Classifier
Steady-State Visual Evoked Potentials
Tri-training

Access to Document

10.1109/embc.2013.6610491

http://www.scopus.com/inward/record.url?scp=84886483574&partnerID=8YFLogxK

Cite this

Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training. / Bender, Thomas; Kjaer, Troels W.; Thomsen, Carsten E. et al.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 4279-4282 6610491.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

@inproceedings{d1c6bf690d7c481e98d27bae66def781,

title = "Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training",

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 Na{\"i}ve-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.",

keywords = "Autocorrelation, Brain-Computer Interface, Na{\"i}ve-Bayes Classifier, Steady-State Visual Evoked Potentials, Tri-training",

author = "Thomas Bender and Kjaer, {Troels W.} and Thomsen, {Carsten E.} and Sorensen, {Helge B D} and S. Puthusserypady",

year = "2013",

month = oct,

day = "31",

doi = "10.1109/embc.2013.6610491",

language = "English",

isbn = "9781457702167",

pages = "4279--4282",

booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training

AU - Bender, Thomas

AU - Kjaer, Troels W.

AU - Thomsen, Carsten E.

AU - Sorensen, Helge B D

AU - Puthusserypady, S.

PY - 2013/10/31

Y1 - 2013/10/31

N2 - 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.

AB - 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.

KW - Autocorrelation

KW - Brain-Computer Interface

KW - Naïve-Bayes Classifier

KW - Steady-State Visual Evoked Potentials

KW - Tri-training

U2 - 10.1109/embc.2013.6610491

DO - 10.1109/embc.2013.6610491

M3 - Article in proceedings

C2 - 24110678

AN - SCOPUS:84886483574

SN - 9781457702167

SP - 4279

EP - 4282

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -

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

Abstract

Keywords

Access to Document

Fingerprint

Cite this