Dissimilarity representations allow for building good classifiers

In this paper, a classification task on dissimilarity representations is considered. A traditional way to discriminate between objects represented by dissimilarities is the nearest neighbor method. It suffers, however, from a number of limitations, i.e., high computational complexity, a potential loss of accuracy when a small set of prototypes is used and sensitivity to noise. To overcome these shortcomings, we propose to use a normal density-based classifier constructed on the same representation. We show that such a classifier, based on a weighted combination of dissimilarities, can significantly improve the nearest neighbor rule with respect to the recognition accuracy and computational effort.

• Type: Journal
• Year: 2002
• Where: PRL
• Authors: Elzbieta Pekalska, Robert P. W. Duin
• Keywords: Nearest Neighbor, Nearest Neighbor Method, Normal Density-based Classifier, PRL 2002