Dataset Information

Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data.

ABSTRACT: 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.

SUBMITTER: Larsen MLV

PROVIDER: S-EPMC6681100 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data.

Larsen Mona Lilian Vestbjerg MLV Pedersen Lene Juul LJ Jensen Dan Børge DB

Animals : an open access journal from MDPI 20190719 7

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 m ...[more]

PMID: 31330973

Similar Datasets

Project description:Tail-biting (TB) in pigs is a serious behavioral disorder. It is an important challenge in swine production as it impacts animal welfare and health and the economics and safety of the pork meat supply chain. To prevent TB, approaches including enrichment material and tail docking are proposed but none are optimal. Nutrition appears to be an important factor in TB behavior, perhaps by modulating the intestinal microbiota (IM). Our aim was to assess the association between TB behavior and IM in pigs through comparisons of IM in groups of biter, bitten and non-biter/non-bitten pigs. Each group composed of 12 pigs was formed at the beginning of the growing/finishing phase based on a target behavior analysis centered on TB behavior for the biter group and a score of damages caused to the tail for the bitten group. Blood and fecal samples were collected from each pig during a TB episode, at time 0, t0, and when the TB episode was considered finished, 4 weeks later, at time 1, t1. Serum cortisol level was determined by ELISA and used as an indicator of stress. The pig's fecal microbiota was analyzed from DNA extracted from freshly collected fecal matter using amplicon sequencing of the V4 hypervariable region of the 16S rRNA gene. Serum cortisol levels were significantly higher in either the biter or bitten pig groups compared to the negative control group (p = 0.02 and p = 0.01, respectively). The microbiota alpha-diversity was not significantly different between all groups, biter, bitten and negative control. Analyses of beta-diversity, however, revealed a significant difference between either the biter or the bitten group in comparison to the non-biter/non-bitten negative control group in terms of structure and composition of the microbiota. Lactobacillus were significantly more abundant in the negative control group compared to the two other groups (p = 0.001). No significant difference was revealed between the biter and bitten groups. Quantitative real-time PCR (qPCR) confirmed that lactobacilli were more abundant in the negative control group. Our study indicates that TB behavior is associated with the IM composition in pigs.

Dataset Information

Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data.

Publications

Prediction of Tail Biting Events in Finisher Pigs from Automatically Recorded Sensor Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets