Machine learning algorithms to predict core, skin, and hair-coat temperatures of piglets

Abstract

A B S T R A C TInternal-body (core) and surface temperatures of livestock are important information that indicate heat stress status and comfort of animals. Previous studies focused on developing mechanistic and empirical models to predict these temperatures. Mechanistic models based on bioenergetics of animals often require parameters that may be difficult to obtain (e.g., thickness of internal tissues). Empirical models, on the other hand, are databased and often assume linear relationships between predictor (e.g., air temperature) and response (e.g., internal-body temperature) variables although, from the theory of bioenergetics, the relationship between the predictor and the response variables is non-linear. One alternative to consider non-linearity is to use machine learning algorithms to predict physiological temperatures. Unlike mechanistic models, machine learning algorithms do not depend on biophysical parameters, and, unlike linear empirical models, machine learning algorithms automatically select the predictor variables and find non-linear functions between predictor and response variables. In this paper, we tested four different machine learning algorithms to predict rectal (T r ), skin-surface (T s ), and hair-coat surface (T h ) temperatures of piglets based on environmental data. From the four algorithms considered, deep neural networks provided the best prediction for T r with an error of 0.36%, gradient boosted machines provided the best prediction for T s with an error of 0.62%, and random forests provided the best predictions for T h with an error of 1.35%. These three algorithms were robust for a wide range of inputs. The fourth algorithm, generalized linear regression, predicted at higher errors and was not robust for a wide range of inputs. This study supports the use of machine learning algorithms (specifically deep neural networks, gradient boosted machines, and random forests) to predict physiological temperature responses of piglets.

PigLeg: prediction of swine phenotype using machine learning

“…Rapidly developing data mining approaches are of increasing interest because they provide for acquisition and analysis of information that results in predictive productivity indicators for animals (Morota et al, 2018;Putz et al, 2018;Howard, 2019). Machine learning (ML) approaches have been successfully used in animal husbandry for early prediction of the growth and quality of adult wool in Australian merino sheep (Shahinfar & Kahn, 2018), sheep carcass traits from early-life records (Shahinfar, Kelman & Kahn, 2019), and skin temperature of piglets (Gorczyca et al, 2018). Compared to other statistical approaches, ML is suitable for use even when there are many predictors, missing values, and abnormally distributed data, which is often the case with data obtained from commercial pig production.…”

Smart Farming Becomes Even Smarter With Deep Learning—A Bibliographical Analysis

“…These techniques include monitoring of animal health indicators, such as the comfort of animal, pose estimation, and behavior detection, as well as other production indicators. Gorczyca et al [48] used machinelearning algorithms for predicting skin, core, and hair-coat temperatures of piglets. Kvam and Kongsro [49] proposed a method for estimating the IMF on ultrasound images.…”

“…The best prediction for Tr was performed by DNN, with an error of 0.36%, for Ts was performed by a gradient boosted machines with an error of 0.62%, for Th was performed by random forests with an error of 1.35%. [48] "Automatic prediction of villagewise soil fertility for several nutrients in India using a wide range of regression methods" The method is based on CNN, which is claimed to be the first application of CNNs in the area of dendrochronological analysis. The proposed approach detection rate was at the level of 96%.…”

Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens

“…A model-free approach is also explored, as in [11] for instance. Machine Learning tool based on Neural Networks were developed to simulate and predict the evolution of biological factors in [10]. This approach, which are only based on data does not need knowledge about the link existing between the used inputs and outputs and permits to develop easier to handle models.…”