Feature extraction for EEG-based brain–computer interfaces by wavelet packet best basis decomposition
Authors:
- Bang-Hua YangBYBang-Hua Yang
- Guo-Zheng YanGYGuo-Zheng Yan
- Rong-Guo YanRYRong-Guo Yan
- Ting WuTWTing Wu
- 5 September 2006
- journal article
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 3 (4) , 251-256
Abstract
A method based on wavelet packet best basis decomposition (WPBBD) is investigated for the purpose of extracting features of electroencephalogram signals produced during motor imagery tasks in brain-computer interfaces. The method includes the following three steps. (1) Original signals are decomposed by wavelet packet transform (WPT) and a wavelet packet library can be formed. (2) The best basis for classification is selected from the library. (3) Subband energies included in the best basis are used as effective features. Three different motor imagery tasks are discriminated using the features. The WPBBD produces a 70.3% classification accuracy, which is 4.2% higher than that of the existing wavelet packet method.Keywords
This publication has 17 references indexed in Scilit:
- A parametric feature extraction and classification strategy for brain-computer interfacingIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2005
- BCI Competition 2003—Data Set Ia: Combining Gamma-Band Power With Slow Cortical Potentials to Improve Single-Trial Classification of Electroencephalographic SignalsIEEE Transactions on Biomedical Engineering, 2004
- Adaptive brain interfacesCommunications of the ACM, 2003
- Evaluating the performance of three feature sets for brain-computer interfaces with an early stopping MLP committee2002
- Brain–computer interfaces for communication and controlClinical Neurophysiology, 2002
- Mu and Beta Rhythm Topographies During Motor Imagery and Actual MovementsBrain Topography, 2000
- Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasksIEEE Transactions on Biomedical Engineering, 1998
- Spatial filter selection for EEG-based communicationElectroencephalography and Clinical Neurophysiology, 1997
- Design and operation of an EEG-based brain-computer interface with digital signal processing technologyBehavior Research Methods, Instruments, & Computers, 1997
- A new mode of communication between man and his surroundingsIEEE Transactions on Biomedical Engineering, 1990