P300 detection based on extraction and classification in online BCI

Author

Hutagalung, Sutrisno Salomo ; Turnip, Arjon ; Munandar, Aris

Author_Institution

Center for R&D of Calibration, Instrum., & Metrol., Indonesian Inst. of Sci., Serpong, Indonesia

fYear

2013

fDate

28-30 Aug. 2013

Firstpage

35

Lastpage

38

Abstract

In this paper, an application of nonlinear principal component analysis for online P300 extraction and classification is proposed. In order to cover the nonlinearity between the variables, a five-layer neural network is applied for feature extraction. The experimental results in this work show that the implementation of the proposed method achieves a very significant statistical improvement in extracting and classifying P300 components. After a short time of practice, most participants could learn to extract and classify the P300 wave with greater than 80% accuracy.

Keywords

brain-computer interfaces; electroencephalography; feature extraction; medical signal detection; medical signal processing; neural nets; principal component analysis; signal classification; P300 detection; feature extraction; five-layer neural network; measured EEG signals; nonlinear principal component analysis; online BCI classification; online BCI extraction; Accuracy; Biological neural networks; Electroencephalography; Feature extraction; Instruments; Principal component analysis; Vectors; BCI; Classification; Feature Extraction; Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation Control and Automation (ICA), 2013 3rd International Conference on

Conference_Location

Ungasan

Print_ISBN

978-1-4673-5795-1

Type

conf

DOI

10.1109/ICA.2013.6734042

Filename

6734042