DocumentCode :
3410826
Title :
LS-SVR with variant parameters and its practical applications for seismic prospecting data denoising
Author :
Xiaoying Deng ; Dinghui Yang ; Baojun Yang
Author_Institution :
Dept. of Math., Tsinghua Univ., Beijing
fYear :
2008
fDate :
June 30 2008-July 2 2008
Firstpage :
1060
Lastpage :
1063
Abstract :
Signal denoising can be considered as a function regression problem. LS-SVR (least squares-support vector regression) based on Ricker wavelet kernel function is applied to the practical seismic prospecting data denoising in this paper. To adapt LS-SVR well to the practical seismic data, the parameters including Ricker wavelet kernel parameter f and regularization parameter ? are selected automatically according to the features of data in the fixed window. The denoising experimental results for the theoretical and practical seismic data show that the performance of Ricker wavelet LS-SVR with variant parameters outperforms the one with invariant parameters in terms of the retrieved waveform in time domain and spectrum range in frequency domain.
Keywords :
geophysical prospecting; geophysical signal processing; least squares approximations; regression analysis; signal denoising; support vector machines; wavelet transforms; LS-SVR; Ricker wavelet kernel function; function regression problem; least squares-support vector regression; seismic prospecting data denoising; signal denoising; variant parameters; Face recognition; Frequency domain analysis; Information retrieval; Kernel; Noise reduction; Signal denoising; Signal to noise ratio; Support vector machine classification; Support vector machines; Wavelet domain; LS-SVR; Ricker wavelet kernel function; seismic prospecting event; variant parameters;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics, 2008. ISIE 2008. IEEE International Symposium on
Conference_Location :
Cambridge
Print_ISBN :
978-1-4244-1665-3
Electronic_ISBN :
978-1-4244-1666-0
Type :
conf
DOI :
10.1109/ISIE.2008.4677053
Filename :
4677053
Link To Document :
بازگشت