next up previous
Next: Decision Trees Up: Non-Linear reconstruction Previous: Non-Linear reconstruction

Distanced-Weighted k-Nearest Neighbor Algorithm

The first algorithm applied is the Nearest Neighbor. To classify a new instance we consider the k nearest points in terms of Euclidean distance. The refinement considered is to weight the contribution of each of the k nearest neighbors according to the query point, giving greater weight to closer neighbors. This weight is tex2html_wrap_inline677, where x is the new instance to classify.

Eddy Mayoraz
Tue Mar 31 18:35:24 MET DST 1998