UM  > 科技學院  > 電機及電腦工程系
Alpha neurofeedback training improves SSVEP-based BCI performance
Wan F.1; Da Cruz J.N.1; Nan W.1; Wong C.M.1; Vai M.I.1; Rosa A.2
Source PublicationJournal of Neural Engineering
ISSN17412552 17412560

Objective. Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) can provide relatively easy, reliable and high speed communication. However, the performance is still not satisfactory, especially in some users who are not able to generate strong enough SSVEP signals. This work aims to strengthen a user's SSVEP by alpha down-regulating neurofeedback training (NFT) and consequently improve the performance of the user in using SSVEP-based BCIs. Approach. An experiment with two steps was designed and conducted. The first step was to investigate the relationship between the resting alpha activity and the SSVEP-based BCI performance, in order to determine the training parameter for the NFT. Then in the second step, half of the subjects with 'low' performance (i.e. BCI classification accuracy <80%) were randomly assigned to a NFT group to perform a real-time NFT, and the rest half to a non-NFT control group for comparison. Main results. The first step revealed a significant negative correlation between the BCI performance and the individual alpha band (IAB) amplitudes in the eyes-open resting condition in a total of 33 subjects. In the second step, it was found that during the IAB down-regulating NFT, on average the subjects were able to successfully decrease their IAB amplitude over training sessions. More importantly, the NFT group showed an average increase of 16.5% in the SSVEP signal SNR (signal-to-noise ratio) and an average increase of 20.3% in the BCI classification accuracy, which was significant compared to the non-NFT control group. Significance. These findings indicate that the alpha down-regulating NFT can be used to improve the SSVEP signal quality and the subjects' performance in using SSVEP-based BCIs. It could be helpful to the SSVEP related studies and would contribute to more effective SSVEP-based BCI applications.

KeywordBci Performance Brain-computer Interface (Bci) Individual Alpha Band (Iab) Neurofeedback Training (Nft) Steady-state Visual Evoked Potential (Ssvep)
URLView the original
Indexed BySCI
WOS Research AreaEngineering ; Neurosciences & Neurology
WOS SubjectEngineering, Biomedical ; Neurosciences
WOS IDWOS:000375701200023
Fulltext Access
Citation statistics
Cited Times [WOS]:13   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
Affiliation1.Universidade de Macau
2.Instituto Superior Técnico
3.Swiss Federal Institute of Technology, Lausanne
Recommended Citation
GB/T 7714
Wan F.,Da Cruz J.N.,Nan W.,et al. Alpha neurofeedback training improves SSVEP-based BCI performance[J]. Journal of Neural Engineering,2016,13(3).
APA Wan F.,Da Cruz J.N.,Nan W.,Wong C.M.,Vai M.I.,&Rosa A..(2016).Alpha neurofeedback training improves SSVEP-based BCI performance.Journal of Neural Engineering,13(3).
MLA Wan F.,et al."Alpha neurofeedback training improves SSVEP-based BCI performance".Journal of Neural Engineering 13.3(2016).
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wan F.]'s Articles
[Da Cruz J.N.]'s Articles
[Nan W.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wan F.]'s Articles
[Da Cruz J.N.]'s Articles
[Nan W.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wan F.]'s Articles
[Da Cruz J.N.]'s Articles
[Nan W.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.