java - how to create hyperbox for fuzzy set? and how to calculate hyperbox membership degree? -
i want know while creating hyperbox (fuzzy min max neural network) parameters of input dataset (wbc or pid ) should used or work can done single parameter , want know weather size of hyperbox depend on input pattern ?and how calculate membership degree of hyperbox?
or
is there easier way generate hyperbox fuzzy set know.
check out link videos regarding hyperbox in detail
consider "iris" dataset uci repository contains n-features. link dataset
for example: 5.1,3.5,1.4,0.2,iris-setosa
this sample single point in n-dimensional plane. first 4 values n-dimensions of point. here n 4. , last term notifies class name belongs.
initially, there no hyperbox present. create hyperbox, consider 4 values min , max values of hyperbox. because there 1 point @ moment, min , max points same. hyperbox called point hyperbox. if second point next feature sample belongs same class, necessary check whether existing hyperbox can expanded or not using expand function. if can expanded update min-max point if necessary else there no need of hyperbox expansion. if hyperbox can not expanded or second point not belongs same class of existing hyperbox, create new hyperbox.
Comments
Post a Comment