Classifying ECoG/EEG-Based Motor Imagery Tasks

Author

An, Bin ; Ning, Yan ; Jiang, Zhaohui ; Feng, Huanqing ; Zhou, Heqin

Author_Institution

Dept. of Electron. Sci. & Technol., USTC, Hefei

fYear

2006

fDate

Aug. 30 2006-Sept. 3 2006

Firstpage

6339

Lastpage

6342

Abstract

The multichannel electrocorticogram (ECoG)/electroencephalogram (EEG) signals are commonly used to classify two kinds of motor imagery (MI) tasks. In this paper, the ECoG and EEG data sets are composed of training and test data, which are recorded during different time/days. Power spectral density (PSD) is selected as features; Fisher discriminant analysis (FDA) and common spatial patterns (CSP) are used to filter redundancy; K-Nearest-Neighbor (KNN) classifier is applied to classify MI tasks; and a new function R (k) is presented to estimate the value of k. Using these methods, we obtain the predictive accuracy of MI tasks based on ECoG data (which is 92%) and EEG data (which is 81%). The results show that we can effectively classify two kinds of MI tasks based on EEG as well as ECoG

Keywords

electroencephalography; filtering theory; neurophysiology; pattern classification; signal classification; ECoG-EEG-based motor imagery task; Fisher discriminant analysis; common spatial patterns; electroencephalogram; filter redundancy; k-nearest-neighbor classifier; multichannel electrocorticogram; power spectral density; signal classification; training; Cities and towns; Data mining; Electrodes; Electroencephalography; Feature extraction; Filtering; Filters; Frequency; Spatial resolution; Testing; ECoG; EEG; KNN; MI;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2006. EMBS '06. 28th Annual International Conference of the IEEE

Conference_Location

New York, NY

ISSN

1557-170X

Print_ISBN

1-4244-0032-5

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2006.259567

Filename

4463260