Distance Based Classification Methods:

One of the simplest algorithms
that is based on distance based classification method is the k-Nearest
Neighbor algorithm . It classifies an object based on the class of its
nearest neighbor in the training set. A straightforward generalization of
this approach is to classify an object as belonging to the class which is most
frequently represented among its k nearest neighbors. The choice of k is
data dependent. Usually, k depends on the size of the training set.