JIITA, vol. 2, no. 2, pp.62-64, Jun, 2018
DOI: DOI: 10.22664/ISITA.2018.2.2.62
BCI P300 Speller Combining User Feedback and Ensemble of Classifiers
Jae-Hwan Yu, Deok-Hwan Kim
Department of Electronic Engineering, Inha university, Inharo 100, Nam-Gu,Incheon, Korea
Abstract: P300 is one of the common methods for detecting brain activity. A brain response is relatively easy to generate. This paper proposes a method for detecting the p300 signal adaptively using the user feedback command. The user feedback of selecting or canceling the command enables the system to adjust the weight of the classifier and reflect the accuracy of the classifiers in the next phase. The experimental results show that the proposed method adaptively complements the weakness of a single classifier
Keyword: DNA; BCI; P300; ensemble of classifiers; user feedback
Full Paper: