Applicability of ANN and MLR Models in Measuring the Impact of Environmental Parameters on the Body Temperature of Swine

DOI

10.2991/978-94-6463-086-2_86How to use a DOI?

Keywords

Relative temperature-humidity index; Swine body temperature; ANNs model; MLR model

Abstract

This study was conducted to identify key parameters such as temperature, humidity, carbon dioxide (CO2), and relative temperature-humidity index (RTHI) that affect the inside and outside environment of the Swine barn. Moreover, the climate of the Swine barn is always related to the Swine’s body temperature (SBT). This study used three growth-related factors and eight environmental components as variables. Hidden layer neurons were performed in this experiment to determine the link between input and output parameters using an artificial neural network (ANNs) model. The model’s accuracy was measured using three statistical performance metrics: regression coefficient (R²), root mean square error (RMSE) and mean absolute error (MAE). The multiple linear regression (MLR) and ANN models were subjected to sensitivity tests to ascertain the input parameter’s specific effects on the SBT. The predicted results were the same as the measured results in the ANNs model, while the predicted and measured results were different in the MLR model. Compared to different traits, trait F showed the best results such as an increase in RMSE (2.0 and 0.70%, respectively) and a decline in R² (2.10 and 1.40%, respectively). The ANNs model had higher efficiency compared to the MLR models. Furthermore, the RTHI, indoor temperature-humidity index (ITHI), relative temperature (RT), outdoor temperature-humidity index (OTHI), and outdoor temperature (OT) were positively associated and accounted for 81.2% and 70.8% of the SBT change, in the ANNs and MLR models, respectively. Overall, this study concludes that RTHI is an important indirect indicator for determining the body temperature of Swine (BTS).

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nibas Chandra Deb
AU  - Jayanta Kumar Basak
AU  - Na Eun Kim
AU  - Bolappa Gamage Kaushalya Madhavi
AU  - Hyeon Tae Kim
PY  - 2022
DA  - 2022/12/28
TI  - Applicability of ANN and MLR Models in Measuring the Impact of Environmental Parameters on the Body Temperature of Swine
BT  - Proceedings of the International Conference on Sustainable Environment, Agriculture and Tourism (ICOSEAT 2022)
PB  - Atlantis Press
SP  - 651
EP  - 657
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-086-2_86
DO  - 10.2991/978-94-6463-086-2_86
ID  - Deb2022
ER  -