The Finger Movement Identification Based on Fuzzy Clustering and BP Neural Network

Author

Yu, Lanlan ; Meng, Tianxing ; Hu, Jian

Author_Institution

Sch. of Electr. & Electron. Eng., Shandong Univ. of Technol., Zibo, China

fYear

2009

fDate

24-26 July 2009

Firstpage

29

Lastpage

33

Abstract

The classification and identification technology plays an important role in the research of brain-computer interface (BCI) systems. In this paper, we do fuzzy clustering disposal for the multi-channel electroencephalogram (EEG) during finger movement at first according to event-related desynchronization phenomena (ERD) in the event-related EEG. Then we classify signal-trial EEG with the feature extracted from EEG based on common spatial subspace decomposition (CSSD) algorithm. The averaged classification accuracy achieves 94.58% in the course of testing on the data from four subjects. Experiment results show that the combination of fuzzy clustering and neural network can greatly improve the rate of identification for finger movement.

Keywords

backpropagation; brain-computer interfaces; electroencephalography; feature extraction; fuzzy set theory; identification technology; medical signal processing; neural nets; pattern classification; pattern clustering; BP neural network; brain-computer interface system; event-related desynchronization phenomena; feature extraction; finger movement identification; fuzzy clustering; identification technology; multichannel electroencephalogram; spatial subspace decomposition algorithm; Brain computer interfaces; Clustering algorithms; Data mining; Electroencephalography; Feature extraction; Fingers; Fuzzy neural networks; Fuzzy set theory; Intelligent networks; Neural networks; BP network; finger movement identification; fuzzy clustering;

fLanguage

English

Publisher

ieee

Conference_Titel

Business Intelligence and Financial Engineering, 2009. BIFE '09. International Conference on

Conference_Location

Beijing

Print_ISBN

978-0-7695-3705-4

Type

conf

DOI

10.1109/BIFE.2009.16

Filename

5208942