Horse breed discrimination using machine learning methods

0340630 - ÚŽFG 2010 RIV CZ eng J - Journal Article
Burócziová, Monika - Riha, J.
Horse breed discrimination using machine learning methods.
Journal of Applied Genetics. Roč. 50, č. 4 (2009), s. 375-377. ISSN 1234-1983. E-ISSN 2190-3883
Institutional research plan: CEZ:AV0Z50450515
Keywords : Breed discrimination * Genetics diversity * Horse breeds
Subject RIV: EG - Zoology
Impact factor: 1.324, year: 2009

Genetic relationships and population structure of 8 horse breeds in the Czech and Slovak Republics were investigated using classification methods for breed discrimination. To demonstrate genetic differences among these breeds, we used genotype data of microsatellite markers and classification algorithms-to perform a probabilistic prediction of an individual's breed. In total, 932 unrelated animals were genotyped for 17 microsatellite markers recommended by the ISAG for parentage testing . Algorithms of classification methods - J48 (decision trees); Naive Bayes, Bayes Net (probability predictors); IB1, IB5 (instance-based machine learning methods); and JRip (decision rules)- were used for analysis of their classification performance and of results of classification on this genotype dataset. Selected classification methods based on machine learning and principles of artificial intelligence, appear usable for these tasks.
Permanent Link: http://hdl.handle.net/11104/0183838