IDENTIFICATION OF STRUCTURALLY ALTERED COAL FROM NEAR-FAULT ZONES AS PERFORMED WITH NEURAL CLASSIFIERS
M. Skiba, K. GodyЕ„, M. MЕ‚ynarczuk
Strata Mechanics Research Institute, Polish Academy of Sciences, Krakow, Poland
Keywords: Structurally altered coal, artificial neural networks (ANN), quantitative analysis of coal, near-fault zone
Abstract
The aim of the research is to propose that artificial neural networks be applied in the process of identification of structurally altered coal. The results suggest that the proposed methodology of classification, due to its high effectiveness exceeding 90% of correct identifications, may be successfully used as a tool supporting the observer's decisions concerning the description of coal from near-fault zones.
|
