build_PCC_nonlinear_models = function(X, y, seed_value=456, build_mda_model=TRUE){
    #
    # Builds (using caret's train function) several of the nonlinear models discussed in
    # this chapter of the book optimizing the probability of correct classification PCC (i.e. accuracy).
    #
    # X [n samples, n features] needs to have zero variance columns removed (use nearZeroVar to remove them) and
    # linear dependent columns removed (use findLinearCombos to remove them)
    #
    # y [n samples, 1] is a two factor vector of predictions with the FIRST factor corresponding to the event of interest
    #
    # Written by:
    # -- 
    # John L. Weatherwax                2009-04-21
    # 
    # email: wax@alum.mit.edu
    # 
    # Please send comments and especially bug reports to the
    # above email address.
    #
    #-----

    # Mixture Discriminant Analysis (MDA):
    #
    if( build_mda_model ){
        set.seed(seed_value)
        mda.classifier = train( X, y, method="mda", tuneGrid=expand.grid(.subclasses=1:2) )
        mda.predictions = predict( mda.classifier, X )
        cm = confusionMatrix( data=mda.predictions, reference=y )
        mda=list( classifier=mda.classifier, predictions=mda.predictions, confusionMatrix=cm )
    }

    # Neural Networks:
    #
    set.seed(seed_value)
    nnetGrid = expand.grid( .size=1:5, .decay=c(0,0.1,1,2) )
    nnet.classifier = train( X, y, method="nnet", preProc=c("center","scale","spatialSign"), tuneGrid=nnetGrid, trace=FALSE, maxit=2000 )
    nnet.predictions = predict( nnet.classifier, X )
    cm = confusionMatrix( data=nnet.predictions, reference=y )
    nnet=list( classifier=nnet.classifier, predictions=nnet.predictions, confusionMatrix=cm )

    # Support Vector Machines:
    #
    library(kernlab)
    sigmaEst = kernlab::sigest( as.matrix(X) )
    svarid = expand.grid(.sigma=sigmaEst[1], .C=2^seq(-4,+4))
    set.seed(seed_value)
    svm.classifier = train( X, y, method="svmRadial", tuneGrid=svarid, preProc=c("center","scale"), fit=FALSE )
    svm.predictions = predict( svm.classifier, X )
    cm = confusionMatrix( data=svm.predictions, reference=y )
    svm=list( classifier=svm.classifier, predictions=svm.predictions, confusionMatrix=cm )

    # K-Nearest Neighbors:
    #
    set.seed(seed_value)
    knn.classifier = train( X, y, method="knn", tuneLength=20, preProc=c("center","scale") )
    knn.predictions = predict( knn.classifier, X )
    cm = confusionMatrix( data=knn.predictions, reference=y )
    knn=list( classifier=knn.classifier, predictions=knn.predictions, confusionMatrix=cm )

    # Naive Bayes:
    #
    nbGrid = expand.grid(.fL=c(1,2), .usekernel=c(T,F))
    set.seed(seed_value)
    nb.classifier = train( X, y, method="nb", tuneGrid=nbGrid )
    nb.predictions = predict( nb.classifier, X )
    cm = confusionMatrix( data=nb.predictions, reference=y )
    nb=list( classifier=nb.classifier, predictions=nb.predictions, confusionMatrix=cm )

    result = list( nnet=nnet, svm=svm, knn=knn, nb=nb )
    if( build_mda_model ){ result = c(result, list(mda=mda)) }
    return( result )
}