A decision-tree-based model for evaluating the thermal comfort of horses

Abstract

Thermal comfort is of great importance in preserving body temperature homeostasis during thermal stress conditions. Although the thermal comfort of horses has been widely studied, there is no report of its relationship with surface temperature (T S ). This study aimed to assess the potential of data mining techniques as a tool to associate surface temperature with thermal comfort of horses. T S was obtained using infrared thermography image processing.Physiological and environmental variables were used to defi ne the predicted class, which classifi ed thermal comfort as "comfort" and "discomfort". The variables of armpit, croup, breast and groin T S of horses and the predicted classes were then subjected to a machine learning process. All variables in the dataset were considered relevant for the classifi cation problem and the decision-tree model yielded an accuracy rate of 74 %. The feature selection methods used to reduce computational cost and simplify predictive learning decreased model accuracy to 70 %; however, the model became simpler with easily interpretable rules. For both these selection methods and for the classifi cation using all attributes, armpit and breast T S had a higher power rating for predicting thermal comfort. Data mining techniques show promise in the discovery of new variables associated with the thermal comfort of horses.

Subjective and Objective Thermal Comfort Estimation Using Wearable Sensors and Environmental Sensors

“…Burzo et al extracted the features from thermography by k-means and examined the estimation result for a 3-level scale of hot, neutral, and cold in three models of Decision Tree, k-NN, and Naive Bayes [16]. In recent research, Maia et al built a model of two classifications of comfort and discomfort for estimating horse thermal comfort by image processing [17]. All of the above is based on the estimation of image data.…”

A Human Thermal Comfort Level Estimating Method Using Thermal Image and Sensor Data

“…Burzo et al extracted the features from thermography by k-means and estimated human thermal comfort of a three-level scale of "hot, " "neutral, " and "cold" in three models of Decision Tree, k-NN, and Simple Bayes [9]. And in recent research, Maia et al predicted horse thermal comfort to two class of "comfort" and "discomfort" by machine learning [10].…”

A Pilot Study for Estimating the Cardiopulmonary Signals of Diverse Exotic Animals Using a Digital Camera

“…Thermal cameras have also been intensively used in animal research [18][19][20][21][22][23][24][25][26] because they are suitable for long-term monitoring and dark environments. However, limitations for such measurements include difficulty in extracting the signal with a partially occluded region of interest (ROI), ambient environmental thermal noise, high cost, and they are limited to comparatively short distances due to limitations of resolution and optics, size, cost which are all connected to thermal imaging physics and lack of a consumer market for the devices [16,17].…”