Neural network of fuzzy K-nearest neighbor - Classification rule for seismic first-arrival picking

Kou-Yuan Huang*, Yune Wei Yuan

*Corresponding author for this work

Research output: Contribution to conferencePaper

1 Scopus citations

Abstract

Fuzzy IS-nearest neighbor classification rule is implemented by neural network of the Hamming net and is applied to seismic first arrival picking. Two kinds of feature set are used in two experiments. The first experiment uses amplitude, mean power level, power ratio, and envelope slope as the features. The second experiment uses average amplitude and envelope at the local maximum amplitude as the features. In the training stage, the training wavelets of the first arrival are selected from the training traces, and features are generated. Then assign fuzzy membership to each training wavelet. In the testing stage, features of each seismic trace is generated, and each candidate local picks is selected. Then the features of each candidate local pick are through the neural network to determine the candidate is the first arrival or not. The experimental results are quite encouraging.

Original languageEnglish
Pages145-148
Number of pages4
StatePublished - 1 Jan 1995
Event1995 Society of Exploration Geophysicists Annual Meeting, SEG 1995 - Houston, United States
Duration: 8 Oct 199513 Oct 1995

Conference

Conference1995 Society of Exploration Geophysicists Annual Meeting, SEG 1995
CountryUnited States
CityHouston
Period8/10/9513/10/95

Fingerprint Dive into the research topics of 'Neural network of fuzzy K-nearest neighbor - Classification rule for seismic first-arrival picking'. Together they form a unique fingerprint.

  • Cite this

    Huang, K-Y., & Yuan, Y. W. (1995). Neural network of fuzzy K-nearest neighbor - Classification rule for seismic first-arrival picking. 145-148. Paper presented at 1995 Society of Exploration Geophysicists Annual Meeting, SEG 1995, Houston, United States.