Title :
Neural network in the application of EEG signal classification method
Author_Institution :
Center of Network Eng. Technol., Weinan Teachers´´ Univ., Weinan, China
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;
Conference_Titel :
Computational Intelligence and Security (CIS), 2011 Seventh International Conference on
Conference_Location :
Hainan
Print_ISBN :
978-1-4577-2008-6
DOI :
10.1109/CIS.2011.294
