Title :
Classifying motor imagery EEG by Empirical Mode Decomposition based on spatial-time-frequency joint analysis approach
Author :
Wei, Pengfei ; Li, Qiuhua ; Li, Guanglin
Author_Institution :
Res. Centre for Neural Eng., Shenzhen Institutes of Adv. Technol., Shenzhen, China
Abstract :
A novel spatial-time-frequency approach to classify the different mental task in brain computer interface was presented. A high resolution time-frequency spectral was achieved by using empirical mode decomposition and Hilbert-Huang transform, and the subject specific spatial-time-frequency joint features were extracted from the restricted spectral of multi-channel EEG recordings. A weighting synthetic classifier was built and used to identify the classes of the imaged motions The test results in four subjects showed that the classification accuracy varied between 77.0% and 95.0%, with an average of 85.9%, which suggested that the present method can achieve a reasonable performance in identifying imaged motions compared with previous methods.
Keywords :
Hilbert transforms; brain-computer interfaces; electroencephalography; feature extraction; medical signal processing; signal classification; spectral analysis; Hilbert-Huang transform; brain computer interface; classification accuracy; empirical mode decomposition; feature extraction; high resolution time-frequency spectral; imaged motions; mental task; motor imagery EEG; multichannel EEG recordings; spatial-time-frequency approach; spatial-time-frequency joint analysis approach; weighting synthetic classifier; Band pass filters; Biomedical engineering; Brain computer interfaces; Electrodes; Electroencephalography; Feature extraction; Image analysis; Information analysis; Neural engineering; Spatial resolution; Brain Computer Interface; EEG; Empirical Mode Decomposition; Hilbert-Huang Transform; Spatial-time-frequency joint analysis;
Conference_Titel :
BioMedical Information Engineering, 2009. FBIE 2009. International Conference on Future
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-4690-2
Electronic_ISBN :
978-1-4244-4692-6
DOI :
10.1109/FBIE.2009.5405811