Predicting slaughter weight in pigs with regression tree ensembles

A. Alsahaf, G. Azzopardi, B. Ducro, R.F. Veerkamp, N. Petkov

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

Abstract

Domestic pigs vary in the age at which they reach slaughter weight even under the controlled conditions of modern pig farming. Early and accurate estimates of when a pig will reach slaughter weight can lead to logistic efficiency in farms. In this study, we compare four methods in predicting the age at which a pig reaches slaughter weight (120 kg). Namely, we compare the following regression tree-based ensemble methods: random forest (RF), extremely randomized trees (ET), gradient boosted machines (GBM), and XGBoost. Data from 32979 pigs is used, comprising a combination of phenotypic features and estimated breeding values (EBV). We found that the boosting ensemble methods, GBM and XGBoost, achieve lower prediction errors than the parallel ensembles methods, RF and ET. On the other hand, RF and ET have fewer parameters to tune, and perform adequately well with default parameter settings.

Original languageEnglish
Title of host publicationApplications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018
EditorsNicolai Petkov, Nicola Strisciuglio, Carlos M. Travieso-Gonzalez
PublisherIOS Press
Pages1-9
ISBN (Electronic)9781614999287
DOIs
Publication statusPublished - Jan 2018
Event1st International Conference on Applications of Intelligent Systems, APPIS 2018 - Las Palmas de Gran Canaria, Spain
Duration: 10 Jan 201812 Jan 2018

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume310
ISSN (Print)0922-6389

Conference

Conference1st International Conference on Applications of Intelligent Systems, APPIS 2018
CountrySpain
CityLas Palmas de Gran Canaria
Period10/01/1812/01/18

Fingerprint

Gradient methods
Farms
Logistics

Keywords

  • Animal production
  • Ensemble learning
  • Gradient boosting
  • Pigs
  • Random forest
  • XGBoost

Cite this

Alsahaf, A., Azzopardi, G., Ducro, B., Veerkamp, R. F., & Petkov, N. (2018). Predicting slaughter weight in pigs with regression tree ensembles. In N. Petkov, N. Strisciuglio, & C. M. Travieso-Gonzalez (Eds.), Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018 (pp. 1-9). (Frontiers in Artificial Intelligence and Applications; Vol. 310). IOS Press. https://doi.org/10.3233/978-1-61499-929-4-1
Alsahaf, A. ; Azzopardi, G. ; Ducro, B. ; Veerkamp, R.F. ; Petkov, N. / Predicting slaughter weight in pigs with regression tree ensembles. Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018. editor / Nicolai Petkov ; Nicola Strisciuglio ; Carlos M. Travieso-Gonzalez. IOS Press, 2018. pp. 1-9 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{659e4412e9304bae99bcd488de62a7a4,
title = "Predicting slaughter weight in pigs with regression tree ensembles",
abstract = "Domestic pigs vary in the age at which they reach slaughter weight even under the controlled conditions of modern pig farming. Early and accurate estimates of when a pig will reach slaughter weight can lead to logistic efficiency in farms. In this study, we compare four methods in predicting the age at which a pig reaches slaughter weight (120 kg). Namely, we compare the following regression tree-based ensemble methods: random forest (RF), extremely randomized trees (ET), gradient boosted machines (GBM), and XGBoost. Data from 32979 pigs is used, comprising a combination of phenotypic features and estimated breeding values (EBV). We found that the boosting ensemble methods, GBM and XGBoost, achieve lower prediction errors than the parallel ensembles methods, RF and ET. On the other hand, RF and ET have fewer parameters to tune, and perform adequately well with default parameter settings.",
keywords = "Animal production, Ensemble learning, Gradient boosting, Pigs, Random forest, XGBoost",
author = "A. Alsahaf and G. Azzopardi and B. Ducro and R.F. Veerkamp and N. Petkov",
year = "2018",
month = "1",
doi = "10.3233/978-1-61499-929-4-1",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "1--9",
editor = "Nicolai Petkov and Nicola Strisciuglio and Travieso-Gonzalez, {Carlos M.}",
booktitle = "Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018",

}

Alsahaf, A, Azzopardi, G, Ducro, B, Veerkamp, RF & Petkov, N 2018, Predicting slaughter weight in pigs with regression tree ensembles. in N Petkov, N Strisciuglio & CM Travieso-Gonzalez (eds), Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018. Frontiers in Artificial Intelligence and Applications, vol. 310, IOS Press, pp. 1-9, 1st International Conference on Applications of Intelligent Systems, APPIS 2018, Las Palmas de Gran Canaria, Spain, 10/01/18. https://doi.org/10.3233/978-1-61499-929-4-1

Predicting slaughter weight in pigs with regression tree ensembles. / Alsahaf, A.; Azzopardi, G.; Ducro, B.; Veerkamp, R.F.; Petkov, N.

Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018. ed. / Nicolai Petkov; Nicola Strisciuglio; Carlos M. Travieso-Gonzalez. IOS Press, 2018. p. 1-9 (Frontiers in Artificial Intelligence and Applications; Vol. 310).

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

TY - GEN

T1 - Predicting slaughter weight in pigs with regression tree ensembles

AU - Alsahaf, A.

AU - Azzopardi, G.

AU - Ducro, B.

AU - Veerkamp, R.F.

AU - Petkov, N.

PY - 2018/1

Y1 - 2018/1

N2 - Domestic pigs vary in the age at which they reach slaughter weight even under the controlled conditions of modern pig farming. Early and accurate estimates of when a pig will reach slaughter weight can lead to logistic efficiency in farms. In this study, we compare four methods in predicting the age at which a pig reaches slaughter weight (120 kg). Namely, we compare the following regression tree-based ensemble methods: random forest (RF), extremely randomized trees (ET), gradient boosted machines (GBM), and XGBoost. Data from 32979 pigs is used, comprising a combination of phenotypic features and estimated breeding values (EBV). We found that the boosting ensemble methods, GBM and XGBoost, achieve lower prediction errors than the parallel ensembles methods, RF and ET. On the other hand, RF and ET have fewer parameters to tune, and perform adequately well with default parameter settings.

AB - Domestic pigs vary in the age at which they reach slaughter weight even under the controlled conditions of modern pig farming. Early and accurate estimates of when a pig will reach slaughter weight can lead to logistic efficiency in farms. In this study, we compare four methods in predicting the age at which a pig reaches slaughter weight (120 kg). Namely, we compare the following regression tree-based ensemble methods: random forest (RF), extremely randomized trees (ET), gradient boosted machines (GBM), and XGBoost. Data from 32979 pigs is used, comprising a combination of phenotypic features and estimated breeding values (EBV). We found that the boosting ensemble methods, GBM and XGBoost, achieve lower prediction errors than the parallel ensembles methods, RF and ET. On the other hand, RF and ET have fewer parameters to tune, and perform adequately well with default parameter settings.

KW - Animal production

KW - Ensemble learning

KW - Gradient boosting

KW - Pigs

KW - Random forest

KW - XGBoost

U2 - 10.3233/978-1-61499-929-4-1

DO - 10.3233/978-1-61499-929-4-1

M3 - Conference paper

T3 - Frontiers in Artificial Intelligence and Applications

SP - 1

EP - 9

BT - Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018

A2 - Petkov, Nicolai

A2 - Strisciuglio, Nicola

A2 - Travieso-Gonzalez, Carlos M.

PB - IOS Press

ER -

Alsahaf A, Azzopardi G, Ducro B, Veerkamp RF, Petkov N. Predicting slaughter weight in pigs with regression tree ensembles. In Petkov N, Strisciuglio N, Travieso-Gonzalez CM, editors, Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018. IOS Press. 2018. p. 1-9. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-929-4-1