Prototype Selection Algorithms for KNN Classifier a Survey

Abstract: The k-Nearest Neighbor classifier is one of the most used and well-known techniques for performing recognition tasks but, it suffers from several drawbacks such as high storage requirements, low efficiency in classification response, and low noise tolerance. The most promising solution to overcome these drawbacks consists of reducing the data used for establishing a classification rule (training data) by means of selecting relevant prototypes. Prototype selection is a research field which has been active for more than four decades. As a result, a great number of methods tackling the prototype selection problem have been proposed yet. Different properties could be observed in the definition of these methods, but no formal categorization has been established yet. This paper provides a survey of the prototype selection method’s categorization/taxonomy that could be considered relevant.

Keywords: k-NN classifier, prototype selection, data reduction, taxonomy.