Application of Neural Network Based on the Unscented Kalman Filter

Author

Li, HongLi ; Ma, Xin

Author_Institution

Sch. of Electr. Eng. & Autom., Tianjin Polytechic Univ., Tianjin, China

fYear

2011

fDate

30-31 July 2011

Firstpage

1

Lastpage

5

Abstract

Neural network has been widely used for nonlinear mapping, time-series estimation and classification. The unscented Kalman filter is a nonlinear parameter estimation algorithm. By means of it, weights update can be realized. In this paper a three layers neural network is used as a classification of the acupuncture EEG signals. The classifier directly classed the EEG instead of the feature values of the EEG. For almost all the subjects the classification accuracies of 100% are obtained. The numerical simulation results show the effectiveness of the algorithm.

Keywords

Kalman filters; electroencephalography; medical signal processing; neural nets; numerical analysis; signal classification; acupuncture EEG signal classification; neural network; nonlinear mapping; nonlinear parameter estimation algorithm; numerical simulation; time series estimation; unscented Kalman filter; Accuracy; Artificial neural networks; Classification algorithms; Electroencephalography; Estimation; Kalman filters; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation and Systems Engineering (CASE), 2011 International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4577-0859-6

Type

conf

DOI

10.1109/ICCASE.2011.5997791

Filename

5997791