Neural network in the application of EEG signal classification method

Author

Jia, Huaping

Author_Institution

Center of Network Eng. Technol., Weinan Teachers´´ Univ., Weinan, China

fYear

2011

fDate

3-4 Dec. 2011

Firstpage

1325

Lastpage

1327

Abstract

Electroencephalogram (EEG) signal is an important information source of underlying brain processes. The communication based on EEG between human brain and computer is a new modality of human-computer interaction. Through time-domain regression method for EEG denoising pretreatment, AR model coefficient is extracted as feature vector, and classifies the EEG signals based on BP network and PNN network. Finally, use Matlab 7.0 simulations, get classification accuracy rate was 90%. Experiments show that this method can get high correct rate of Classification.

Keywords

backpropagation; brain-computer interfaces; electroencephalography; feature extraction; human computer interaction; medical image processing; neural nets; regression analysis; signal classification; signal denoising; time-domain analysis; AR model coefficient; BP network; EEG denoising pretreatment; EEG signal classification method; Matlab 7.0 simulations; PNN network; electroencephalogram; feature vector extraction; human-computer interaction; neural network; time-domain regression method; Accuracy; Biological neural networks; Brain modeling; Electroencephalography; Neurons; Support vector machine classification; Training; AR parameters; BP network; EEG signal; PNN network; feature extraction;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Security (CIS), 2011 Seventh International Conference on

Conference_Location

Hainan

Print_ISBN

978-1-4577-2008-6

Type

conf

DOI

10.1109/CIS.2011.294

Filename

6128335