Preprocessing GPR signatures for cascading neural network classification

Mary M Poulton, Adel EI-Fouly

Research output: Contribution to conferencePaper

6 Scopus citations

Abstract

A solution to the problem of long training times is found by seg?menting classification and param?eter estimation problems into several smaller problems. Information cascades from one neural network to another with each level increasing the specificity of the problem. To be used most effectively, the networks require small input pattern vectors. Therefore much pre-processing is done to extract information from the GPR records that is germane to the classification. A novel method of extracting and enhancing the target reflection through the use of logical filters is developed. A cascading network is constructed that classifies the type of target as point or plane and then iden?tifies the composition. Finally, the size and location of the target are estimated. The modular nature of the network allows it to train faster, give more accurate results and be easily modified.

Original languageEnglish (US)
Pages507-509
Number of pages3
StatePublished - Jan 1 1991
Event1991 Society of Exploration Geophysicists Annual Meeting - Houston, United States
Duration: Nov 10 1991Nov 14 1991

Other

Other1991 Society of Exploration Geophysicists Annual Meeting
CountryUnited States
CityHouston
Period11/10/9111/14/91

ASJC Scopus subject areas

  • Geophysics

Fingerprint Dive into the research topics of 'Preprocessing GPR signatures for cascading neural network classification'. Together they form a unique fingerprint.

  • Cite this

    Poulton, M. M., & EI-Fouly, A. (1991). Preprocessing GPR signatures for cascading neural network classification. 507-509. Paper presented at 1991 Society of Exploration Geophysicists Annual Meeting, Houston, United States.