Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data
Tail biting in pigs is an animal welfare problem, and tail biting should be prevented from developing into tail damage. One strategy could be to predict events of tail biting so that the farmer can make timely interventions in specific pens. In the current investigation, sensor data on water usage (...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/9/7/458 |
| _version_ | 1818543514741374976 |
|---|---|
| author | Mona Lilian Vestbjerg Larsen Lene Juul Pedersen Dan Børge Jensen |
| author_facet | Mona Lilian Vestbjerg Larsen Lene Juul Pedersen Dan Børge Jensen |
| author_sort | Mona Lilian Vestbjerg Larsen |
| collection | DOAJ |
| description | Tail biting in pigs is an animal welfare problem, and tail biting should be prevented from developing into tail damage. One strategy could be to predict events of tail biting so that the farmer can make timely interventions in specific pens. In the current investigation, sensor data on water usage (water flow and activation frequency) and pen temperature (above solid and slatted floor) were included in the development of a prediction algorithm for tail biting. Steps in the development included modelling of data sources with dynamic linear models, optimisation and training of artificial neural networks and combining predictions of the single data sources with a Bayesian ensemble strategy. Lastly, the Bayesian ensemble combination was tested on a separate batch of finisher pigs in a real-life setting. The final prediction algorithm had an AUC > 0.80, and thus it does seem possible to predict events of tail biting from already available sensor data. However, around 30% of the no-event days were false alarms, and more event-specific predictors are needed. Thus, it was suggested that farmers could use the alarms to point out pens that need greater attention. |
| first_indexed | 2024-12-11T22:36:24Z |
| format | Article |
| id | doaj.art-bb344cc517bf42f4a549e3ad3605f36f |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-12-11T22:36:24Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-bb344cc517bf42f4a549e3ad3605f36f2022-12-22T00:47:58ZengMDPI AGAnimals2076-26152019-07-019745810.3390/ani9070458ani9070458Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor DataMona Lilian Vestbjerg Larsen0Lene Juul Pedersen1Dan Børge Jensen2Department of Animal Science, Aarhus University, Blichers Allé 20, DK-8830 Tjele, DenmarkDepartment of Animal Science, Aarhus University, Blichers Allé 20, DK-8830 Tjele, DenmarkDepartment of Veterinary and Animal Sciences, University of Copenhagen, Grønnegårdsvej 2, DK-1870 Frederiksberg C, DenmarkTail biting in pigs is an animal welfare problem, and tail biting should be prevented from developing into tail damage. One strategy could be to predict events of tail biting so that the farmer can make timely interventions in specific pens. In the current investigation, sensor data on water usage (water flow and activation frequency) and pen temperature (above solid and slatted floor) were included in the development of a prediction algorithm for tail biting. Steps in the development included modelling of data sources with dynamic linear models, optimisation and training of artificial neural networks and combining predictions of the single data sources with a Bayesian ensemble strategy. Lastly, the Bayesian ensemble combination was tested on a separate batch of finisher pigs in a real-life setting. The final prediction algorithm had an AUC > 0.80, and thus it does seem possible to predict events of tail biting from already available sensor data. However, around 30% of the no-event days were false alarms, and more event-specific predictors are needed. Thus, it was suggested that farmers could use the alarms to point out pens that need greater attention.https://www.mdpi.com/2076-2615/9/7/458Sus scrofa domesticusprecision livestock farmingcomputational ethologydrinking behaviourwater flowpen temperaturedynamic linear modelsartificial neural networkBayes’ TheoremBayesian ensemble |
| spellingShingle | Mona Lilian Vestbjerg Larsen Lene Juul Pedersen Dan Børge Jensen Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data Animals Sus scrofa domesticus precision livestock farming computational ethology drinking behaviour water flow pen temperature dynamic linear models artificial neural network Bayes’ Theorem Bayesian ensemble |
| title | Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data |
| title_full | Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data |
| title_fullStr | Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data |
| title_full_unstemmed | Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data |
| title_short | Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data |
| title_sort | prediction of tail biting events in finisher pigs from automatically recorded sensor data |
| topic | Sus scrofa domesticus precision livestock farming computational ethology drinking behaviour water flow pen temperature dynamic linear models artificial neural network Bayes’ Theorem Bayesian ensemble |
| url | https://www.mdpi.com/2076-2615/9/7/458 |
| work_keys_str_mv | AT monalilianvestbjerglarsen predictionoftailbitingeventsinfinisherpigsfromautomaticallyrecordedsensordata AT lenejuulpedersen predictionoftailbitingeventsinfinisherpigsfromautomaticallyrecordedsensordata AT danbørgejensen predictionoftailbitingeventsinfinisherpigsfromautomaticallyrecordedsensordata |