KNNM

K-Nearest Neighbour based density estimate

    W = KNNM(A,KNN)

    D = B*W

Input
A	Dataset
KNN	Number of nearest neighbours

Output
W	Density estimate

Description

A density estimator is constructed based on the k-Nearest Neighbour rule  using the labeled objects in A. All objects, however, are used if the  entire dataset is unlabeled or if A is not a dataset, but a double.  In all cases, just single density estimator W is computed.  Class priors in A are neglected.

The mapping W may be applied to a new dataset B using DENSITY = B*W.

See also

datasets, mappings, knnc, qdc, parzenm, gaussm,