Identification and Classification for finger movement based on EEG

Author

Liu, Boqiang ; Mingshi Wang ; Wang, Mingshi ; Li, Tonglei

Author_Institution

Coll. of Precision Instrum. & Optoelectron. Eng., Tianjin Univ.

fYear

2006

Firstpage

5408

Lastpage

5411

Abstract

Identification and classification technology plays an important part in study of the BCI system. There are many algorithms to classify the event of different task related. Here, finger movement was used as the basic and typical tasks to be identified in the BCI experiments. The ideas of BP and ERD were introduced and discussed. The CSSD (common spatial subspace decomposition) algorithm was used for classifying single-trial EEG during the preparation of left-right finger movements after the two kinds of phenomena were expounded in detail in this paper. Experiment and simulating results show that the averaged classification accuracy can be up to the 75.6%

Keywords

biomechanics; electroencephalography; medical signal detection; medical signal processing; neurophysiology; user interfaces; Bereitschaftspotential; brain-computer interface; common spatial subspace decomposition; electroencephalography; event-related desynchronization; event-relative potential; finger movement; signal classification; signal identification; Band pass filters; Data preprocessing; Electrodes; Electroencephalography; Feature extraction; Fingers; Flowcharts; Frequency; Low pass filters; Rhythm; BCI; Classification; Data Processing; EEG; Event-relative Potential;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the

Conference_Location

Shanghai

Print_ISBN

0-7803-8741-4

Type

conf

DOI

10.1109/IEMBS.2005.1615705

Filename

1615705