Neural network and tree automaton for seismic pattern recognition

Kou-Yuan Huang*, Yi Hsian Chao

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

We combine neural network and syntactic pattern recognition, and propose a tree automaton system for the recognition of structural seismic patterns in a seismogram. Multilayer perceptron of the neural network is used for the identification of subpatterns, then a tree representation of the structural seismic pattern is constructed. We use three kinds of modified bottom-up structure preserved error correcting tree automata to recognize the tree representation of syntactic pattern, and propose a new top-down error correcting tree automaton to recognize non-structural preserved seismic pattern. In the experiments, the system is applied to the simulated and the real seismic bright spot patterns. The recognition result can improve seismic interpretation.

Original languageEnglish
Pages (from-to)663-668
Number of pages6
JournalIEEE International Conference on Neural Networks - Conference Proceedings
Volume1
DOIs
StatePublished - 1 Dec 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary
Duration: 25 Jul 200429 Jul 2004

Fingerprint Dive into the research topics of 'Neural network and tree automaton for seismic pattern recognition'. Together they form a unique fingerprint.

Cite this