GMDH: Feature Selection and Classification via GMDH-Type Neural...

In GMDH2: Binary Classification via GMDH-Type Neural Network Algorithms

Feature Selection and Classification via GMDH-Type Neural Network Algorithm for a Binary Response

Description

GMDH makes feature selection and classification via GMDH-type neural network algorithm.

Usage

GMDH(x.train, y.train, x.valid, y.valid, alpha = 0.6, maxlayers = 10, maxneurons = 15, 
  exCriterion = "MSE", verbose = TRUE, ...)

Arguments

x.train	a n1xp matrix to be included in model construction, n1 is the number of observations and p is the number of variables.
y.train	a factor of binary response variable to be included in model construction.
x.valid	a n2xp matrix to be used for neuron selection, n2 is the number of observations and p is the number of variables.
y.valid	a factor of binary response variable to be used for neuron selection.
alpha	the selection pressure in a layer. Defaults alpha = 0.6.
maxlayers	the number of maximum layers. Defaults maxlayers = 10.
maxneurons	the number of maximum neurons selected in each layer. Defaults maxneurons = 15.
exCriterion	a character string to select an external criteria. "MSE": Mean Square Error, "MAE": Mean Absolute Error. Default is set to "MSE".
verbose	a logical for printing summary output to R console.
...	not used currently.

Value

A list with class "GMDH" and "GMDHplot" containing the following components:

architecture	all objects stored in construction process of network
nlayer	the number of layers
neurons	the number of neurons in layers
sneurons	the number of selected neurons in layers
structure	the summary structure of the process
levels	the levels of binary response
features	the names of variables used in GMDH algorithm
pfeatures	the column number of variables used in GMDH algorithm
nvar	the number of variables in the data set
plot_list	the list of objects to be used in plot.GMDHplot

Author(s)

Osman Dag, Erdem Karabulut, Reha Alpar

References

Dag, O., Karabulut, E., Alpar, R. (2019). GMDH2: Binary Classification via GMDH-Type Neural Network Algorithms - R Package and Web-Based Tool. International Journal of Computational Intelligence Systems, 12:2, 649-660.

Examples

library(GMDH2)

library(mlbench)
data(BreastCancer)

data <- BreastCancer

# to obtain complete observations
completeObs <- complete.cases(data)
data <- data[completeObs,]

x <- data.matrix(data[,2:10])
y <- data[,11]

seed <- 12345
set.seed(seed)
nobs <- length(y)

# to split train, validation and test sets

indices <- sample(1:nobs)

ntrain <- round(nobs*0.6,0)
nvalid <- round(nobs*0.2,0)
ntest <- nobs-(ntrain+nvalid)

train.indices <- sort(indices[1:ntrain])
valid.indices <- sort(indices[(ntrain+1):(ntrain+nvalid)])
test.indices <- sort(indices[(ntrain+nvalid+1):nobs])


x.train <- x[train.indices,]
y.train <- y[train.indices]

x.valid <- x[valid.indices,]
y.valid <- y[valid.indices]

x.test <- x[test.indices,]
y.test <- y[test.indices]

set.seed(seed)
# to construct model via GMDH algorithm
model <- GMDH(x.train, y.train, x.valid, y.valid)
predict(model, x.test)

GMDH2 documentation built on Oct. 26, 2022, 5:06 p.m.