Three nonparametric techniques for the optimum discretization of quantitative geological variables

Pan, Guocheng; Harris, DeVerle P.

doi:10.1007/bf00890516

Cited by 15 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can propose logarithm state variable weight formula: State variable weight formula has the penalty from 1 to 3. When the 0 α > , ( ) j S X has the reward [7] ; When 0 α < , ( ) j S X has the penalty. ( ) j S X from model 5 has the penalty and reward.…”

Section: Geological Variable Weight Function Constructionmentioning

confidence: 99%

A Variable Weight Function Model in Geological Variables Function Research

Liu

2013

AMR

View full text Add to dashboard Cite

In mineral resources prediction and other research of geological variables, stability exactness of quantitative models concern modeling conditions, geological variables from model and the status of the variable. In traditional geological modeling process, variable support is measured under some contrains weight and this kind of weight is characterized by constant coefficients. Constant weight[1] has some limitations due to structuredness and dependency of variable. For overcoming the inflexibility of constant weight, this paper proposes geological variable mathematics model basedd state variable vector. We revise existing form of state variable weight and provide logarithm state variable vector as measurement level of geological variable weight coefficients. According to 1:200000 scale geochemistry measured data from Baishan area, we calculate the samples unit connection degree based on exponent and logarithm state variable vector and compare the connection degree based on constant weight. The connection degree sorting has the similarity as a whole among them, but there is the obvious difference locally. We can conclude that geological variable weight function based on state variable vector is more flexible and fine.

show abstract

Section: Geological Variable Weight Function Constructionmentioning

confidence: 99%