Seismic buffer recognition using mutual information for selecting wavelet based features

Author

Hoffman, A.J. ; Hoogenboezem, C. ; van der Merwe, N.T. ; Tollig, C.J.A.

Author_Institution

Sch. for Electr. & Electron. Eng., Potchefstroom Univ. for CHE, South Africa

Volume

2

fYear

1998

fDate

7-10 Jul 1998

Firstpage

663

Abstract

One of the first operations in seismic signal processing system is to distinguish between valid and invalid records. Since valid signals are characterized by a combination of their time and frequency properties, wavelets are natural candidates for describing seismic features in a compact way. This paper investigates an approach to seismic pattern recognition comprising wavelet-based feature extraction, feature selection based on the mutual information criterion and neural classification based on feedforward networks. The ability of the wavelet transform to capture discriminating information from seismic data in a small number of features is compared against alternative feature reduction techniques, including statistical moments

Keywords

classification; feature extraction; feedforward neural nets; geophysical signal processing; geophysical techniques; seismology; wavelet transforms; feature extraction; feedforward networks; frequency properties; invalid records; mutual information; neural classification; seismic buffer recognition; seismic pattern recognition; seismic signal processing system; time properties; valid records; wavelet-based features selection; Africa; Channel hot electron injection; Continuous wavelet transforms; Discrete wavelet transforms; Feature extraction; Frequency; Mutual information; Neural networks; Pattern recognition; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 1998. Proceedings. ISIE '98. IEEE International Symposium on

Conference_Location

Pretoria

Print_ISBN

0-7803-4756-0

Type

conf

DOI

10.1109/ISIE.1998.711699

Filename

711699