Clustering-and-selection model for classifier combination

Author

Kuncheva, Ludmila I.

Author_Institution

Sch. of Inf., Univ. Coll. of North Wales, Bangor, UK

Volume

1

fYear

2000

fDate

2000

Firstpage

185

Abstract

We devise a simple clustering-and-selection algorithm based on a probabilistic interpretation of classifier selection. First, the data set is clustered into K clusters, and then the most successful classifier for a given cluster is nominated to label the inputs in the Voronoi cell of the cluster centroid. The proposed method is compared experimentally with the minimum, maximum, product and average. Also given are the results from the naive Bayes method, the behaviour-knowledge space (BKS) method, the best individual and the oracle

Keywords

Bayes methods; computational geometry; pattern classification; pattern clustering; Voronoi cell input labelling; average; behaviour-knowledge space method; best individual; classifier combination; classifier selection; cluster centroid; clustering-and-selection algorithm; data set clustering; maximum; minimum; multiple-classifier systems; naive Bayes method; oracle; probabilistic interpretation; product; Clustering algorithms; Decision making; Informatics; Medical diagnosis; Nearest neighbor searches; Shape; Switches; Table lookup;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on

Conference_Location

Brighton

Print_ISBN

0-7803-6400-7

Type

conf

DOI

10.1109/KES.2000.885788

Filename

885788