Use of the mini-model method in classification task on example of iris flower dataset

Marcin Pietrzykowski

Download PDF

Citation:

M. Pietrzykowski, "Use of the mini-model method in classification task on example of iris flower dataset", Journal of Theoretical and Applied Computer Science, vol. 8, no. 2, pp. 27-36, 2014.

Export to BibTex

Keywords:

mini-model, local classification, k-nearest neighbors method, mathematical modeling

Abstract:

The paper presents use of the mini-models method in a classification task. The article brief-ly describes the method and compares it to the k-nearest neighbor algorithm. The algorithm concentrates only on local query data and uses a data samples only from local neighbor-hood of the query. The paper presents the results of experiment that compare the effective-ness of mini-models with selected methods of classification. The experiments were performed on well-known Iris Flower dataset and on other popular classification datasets.