An efficient prototype merging strategy for the condensed 1-NN rule through class-conditional hierarchical clustering

Abstract A generalized prototype-based classification scheme founded on hierarchical clustering is proposed. The basic idea is to obtain a condensed 1-NN classification rule by merging the two same-class nearest clusters, provided that the set of cluster representatives correctly classifies all the original points. Apart from the quality of the obtained sets and its flexibility which comes from the fact that different intercluster measures and criteria can be used, the proposed scheme includes a very efficient four-stage procedure which conveniently exploits geometric cluster properties to decide about each possible merge. Empirical results demonstrate the merits of the proposed algorithm taking into account the size of the condensed sets of prototypes, the accuracy of the corresponding condensed 1-NN classification rule and the computing time.

[1]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[2]  Shlomo Geva,et al.  Adaptive nearest neighbor pattern classification , 1991, IEEE Trans. Neural Networks.

[3]  Francesc J. Ferri,et al.  A cluster-based merging strategy for nearest prototype classifiers , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[4]  Enrique Vidal,et al.  New formulation and improvements of the nearest-neighbour approximating and eliminating search algorithm (AESA) , 1994, Pattern Recognit. Lett..

[5]  Belur V. Dasarathy,et al.  Minimal consistent set (MCS) identification for optimal nearest neighbor decision systems design , 1994, IEEE Trans. Syst. Man Cybern..

[6]  Kuldip K. Paliwal,et al.  Fast nearest-neighbor search algorithms based on approximation-elimination search , 2000, Pattern Recognit..

[7]  C. G. Hilborn,et al.  The Condensed Nearest Neighbor Rule , 1967 .

[8]  Tony R. Martinez,et al.  Reduction Techniques for Instance-Based Learning Algorithms , 2000, Machine Learning.

[9]  Dennis L. Wilson,et al.  Asymptotic Properties of Nearest Neighbor Rules Using Edited Data , 1972, IEEE Trans. Syst. Man Cybern..

[10]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[11]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[12]  James C. Bezdek,et al.  Multiple-prototype classifier design , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[13]  Luisa Micó,et al.  A new version of the nearest-neighbour approximating and eliminating search algorithm (AESA) with linear preprocessing time and memory requirements , 1994, Pattern Recognit. Lett..

[14]  Francesc J. Ferri,et al.  Another move toward the minimum consistent subset: a tabu search approach to the condensed nearest neighbor rule , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Fionn Murtagh,et al.  A Survey of Recent Advances in Hierarchical Clustering Algorithms , 1983, Comput. J..

[16]  David B. Skalak,et al.  Prototype and Feature Selection by Sampling and Random Mutation Hill Climbing Algorithms , 1994, ICML.

[17]  Peter E. Hart,et al.  The condensed nearest neighbor rule (Corresp.) , 1968, IEEE Trans. Inf. Theory.

[18]  Chin-Liang Chang,et al.  Finding Prototypes For Nearest Neighbor Classifiers , 1974, IEEE Transactions on Computers.

[19]  James C. Bezdek,et al.  Nearest prototype classification: clustering, genetic algorithms, or random search? , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[20]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .