Title :
A Method Based on Chirplet Transform for Visual Evoked Potentials Extraction
Author :
Qiu, Fei-Yue ; Gao, Xin ; Wang, Li-ping ; Li, Hao-Jun
Author_Institution :
Collage of Educ. Sci. & Technol., Zhejiang Univ. of Technol., Hangzhou
Abstract :
Fast and accurate to extract the visual evoked potential form large background noise has very high medical value in ophthalmology and neurological dysfunction, and other aspects of the clinical diagnosis. In this paper, a method based on chirplet transform for extract VEP signal has been adopted in which use maximum likelihood estimation to estimate chirplet parameters, and parameters are refined at each iteration by expectation-maximization algorithm. The scheme of the algorithm is shown in this paper, and the result of the synthetic signal and the actual acquisition VEP signal demonstrate the validity of the method proposed.
Keywords :
expectation-maximisation algorithm; feature extraction; medical signal processing; neurophysiology; signal denoising; visual evoked potentials; VEP signal; background noise; chirplet transform; clinical diagnosis; expectation-maximization algorithm; maximum likelihood estimation; neurological dysfunction; ophthalmology; signal acquisition; synthetic signal; visual evoked potentials extraction; Background noise; Chirp; Data mining; Educational technology; Frequency; Maximum likelihood estimation; Signal analysis; Signal to noise ratio; Wavelet analysis; Wavelet transforms;
Conference_Titel :
Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-1747-6
Electronic_ISBN :
978-1-4244-1748-3
DOI :
10.1109/ICBBE.2008.875
