Title :
A Novel Criterion of Wavelet Packet Best Basis Selection for Signal Classification With Application to Brain–Computer Interfaces
Author :
Vautrin, Denis ; Artusi, Xavier ; Lucas, Marie-Francoise ; Farina, Dario
Author_Institution :
Inst. de Rech. en Commun. et Cybernetique de Nantes (IRCCyN), Nantes, France
Abstract :
This study proposes a method to select a wavelet basis for classification. It uses a strategy defined by Wickerhauser and Coifman and proposes a new additive criterion describing the contrast between classes. Its performance is compared with other approaches on simulated signals and on experimental EEG signals for brain-computer interface applications.
Keywords :
brain-computer interfaces; electroencephalography; handicapped aids; medical signal processing; signal classification; EEG signals; brain-computer interfaces; signal classification; wavelet basis selection; wavelet packet; Brain computer interfaces; Discrete wavelet transforms; Electroencephalography; Feature extraction; Frequency; Optimization methods; Pattern classification; Permission; Support vector machine classification; Support vector machines; Wavelet analysis; Wavelet packets; Brain-computer interfaces (BCIs); pattern recognition; wavelets; Adult; Algorithms; Brain; Brain Mapping; Electroencephalography; Evoked Potentials; Humans; Male; Pattern Recognition, Automated; Signal Processing, Computer-Assisted; User-Computer Interface;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2009.2028014
