SKNN {SKNN} | R Documentation |
It's a Super K-Nearest Neighbor classification method with using kernel density to describe weight of the distance between a training observation and the testing sample.
SKNN(data, Class, k, test)
data |
Numeric. The training data set, matrix. |
Class |
Character. Class of the training observations, vector. |
k |
Integer. The number of K to be used. |
test |
Numeric. The sample to be classified. |
A character.
Yarong Yang, Nader Ebrahimi, and Yoram Rubin
Yarong Yang, Nader Ebrahimi, and Yoram Rubin.(2024) SKNN: A Super K-Nearest Neighbor Classification Algorithm.
Yarong Yang, Matt Over, and Yoram Rubin.(2012) Strategic Placement of Localization Devices (such as Pilot Points and Anchors) in Inverse Modeling Schemes. Water Resources Research, 48, W08519, doi:10.1029/2012WR011864.
B.B.W. Silverman. Density Estimation for Statistics and Data Analysis. London: Chapman and Hall, 1986.
Sepal.Length<-c(4.8, 5.1, 4.6, 5.3, 5.0, 5.7, 5.7, 6.2, 5.1, 5.7, 6.7, 6.3, 6.5, 6.2, 5.9)
Sepal.Width<-c(3.0, 3.8, 3.2, 3.7, 3.3, 3.0, 2.9, 2.9, 2.5, 2.8, 3.0, 2.5, 3.0, 3.4, 3.0)
Petal.Length<-c(1.4, 1.6, 1.4, 1.5, 1.4, 4.2, 4.2, 4.3, 3.0, 4.1, 5.2, 5.0, 5.2, 5.4, 5.1)
Petal.Width<-c(0.3, 0.2, 0.2, 0.2, 0.2, 1.2, 1.3, 1.3, 1.1, 1.3, 2.3, 1.9, 2.0, 2.3, 1.8)
Species<-as.factor(c(rep("red",5),rep("blue",5),rep("green",5)))
iris<-cbind(Sepal.Length,Sepal.Width,Petal.Length,Petal.Width)
Res<-length(nrow(iris))
k<-10
for(i in 1:nrow(iris))
Res[i]<-SKNN(data=iris,Class=as.vector(Species),k=k,test=iris[i,])
accuracy<-length(which(Res==Species))/length(Species)
plot(x=1:15,y=rep(1,15),col=as.vector(Species),lwd=4,ylim=c(0,3),xlab="",ylab="",
yaxt = "n",xaxt="n")
par(new=TRUE)
plot(x=1:15,y=rep(2,15),col=Res,lwd=4,ylim=c(0,3),xlab="",ylab="",yaxt = "n",xaxt="n")
ind<-which(Res!=Species)
if(length(ind)>0) {
for(j in 1:length(ind))
lines(x=c(ind[j],ind[j]),y=c(1+0.05,2-0.05))
}
text(5,0.3,paste("SKNN Misclassified:",length(ind)))
axis(2,at=2,labels="SKNN",las=1)
text(10,2.5,paste("k: ",k))