Please use this identifier to cite or link to this item:
Type: Artigo de evento
Title: Data Mining As A Tool To Evaluate Thermal Comfort Of Horses
Author: Maia A.P.A.
Medeiros B.B.L.
Vercellino R.A.
Sarubbi J.
Oliveira S.R.M.
Griska P.R.
Moura D.J.
Abstract: Thermal comfort is of great importance to preserve body temperature homeostasis during thermal stress conditions. Although thermal comfort of horses has been widely studied, research has not reported its relationship to surface temperature (TS). The aim of this study was to investigate the potential of data mining techniques as a tool to associate surface temperature with thermal comfort of horses. TS was measured using infrared thermographic image processing. Physiological and environmental variables were used to define the predicted class, which classified thermal comfort as "comfort" and "discomfort". The TS variables for the armpit, croup, breast and groin of horses and the predicted class were then submitted to a machine learning process. All dataset variables were considered relevant to the classification problem and the decision-tree model yielded an accuracy rate of 74.0%. The feature selection methods used to reduce computational cost and simplify predictive learning reduced the model accuracy to 70.1%; however the model became simpler with representative rules. For these selection methods and for the classification using all attributes, TS of armpit and breast had a higher rating power for predicting thermal comfort. The data mining techniques had discovered new variables relating to the thermal comfort of horses.
Editor: Katholieke Universiteit Leuven
Rights: fechado
Identifier DOI: 
Date Issue: 2013
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.