A multivariate dynamic linear model for early warnings of diarrhea and pen fouling in slaughter pigs

Jensen, Dan Børge; Toft, Nils; Kristensen, Anders Ringgaard

doi:10.1016/j.compag.2016.12.018

Cited by 26 publications

(26 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this combination, 12 of the 14 tail biting events were predicted, and ‘only’ 31% of the no-event days were false alarms, lowering the number of false alarms with around 400. The fact that this combination performs well is in accordance with previous investigations, e.g., Jensen et al [18] who showed that data on drinking amount and drinking frequency contain mutually independent information value with respect to early detection of undesired events in finisher pigs. Also Dominiak et al [20] found AUCs > 0.80 when using similar data sources to predict tail biting events in both weaner and finisher pigs using both internal (as in the current study) and external evaluation.…”

Section: Discussionsupporting

confidence: 90%

“…Previously developed prediction algorithms for finisher pigs, focussing on prediction of tail biting, fouling and diarrhoea events, investigated time windows including the day of the event and sometimes the day after the event [18,20,21]. This means that the farmer can possibly receive an alarm after the event, probably while the event is still ongoing but at a later stage of development.…”

Section: Discussionmentioning

confidence: 99%

“…Previous investigations into the prediction of undesirable events in finisher pigs have also looked at water usage and pen temperature as predictors of pen fouling and diarrhoea [18,20,23]. Jensen et al [18] tried to indiscriminately predict pen fouling and diarrhoea events using a multivariate dynamic linear model including predictors on water usage, pen temperature, humidity and feed usage. They found that both water usage and pen temperature had predictive value of the two events with AUCs > 0.80 for water usage and AUCs > 0.75 for pen temperature, whereas the other predictors did not.…”

Section: Discussionmentioning

confidence: 99%

“…The AUC was calculated using the ‘auc’ function of the ‘MESS’ library in R [17]. Further, the 95% confidence interval (CI) for the AUC was calculated following the example of Jensen et al [18] as follows (Equations (10)–(13)):AUC±zα/2·SEAUC where SEAUC=AUC·(1−AUC)+(N1−1)·(Q1−AUC2)+(N2−1)·(Q2−AUC2)N1·N2 Q1=AUC2−AUC Q2=2·AUC21+AUC and N 1 and N 2 are the numbers of event and control pens, respectively. The performance of the prediction model is said to be better than random guessing if the 95% CI of the AUC does not contain the value 0.5.…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

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

Larsen

Pedersen

Jensen

2019

Animals

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

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

Larsen

Pedersen

Jensen

2019

Animals

Self Cite

View full text Add to dashboard Cite

show abstract

“…The study by was the first one to consider the dynamic modelling of water drinking patterns and demonstrated its power in detecting disease outbreaks . One way to measure water intake is to utilise water meters, and multiple studies have found predictive information in this measure when considering unwanted events within the pig production including tail biting, pen fouling and diarrhoea (Jensen et al, 2017;Dominiak et al, 2019;Larsen et al, 2019). Other approaches focus less on the precise water consumption of the animals and instead focus more on the frequency and duration of the visits to the drinker.…”

Section: Applications Of Monitoring Technologies In the Production Prmentioning

confidence: 99%

Review: Precision livestock farming: building ‘digital representations’ to bring the animals closer to the farmer

Norton

Chen

Larsen

et al. 2019

Animal

120

View full text Add to dashboard Cite

Economic pressures continue to mount on modern-day livestock farmers, forcing them to increase herds sizes in order to be commercially viable. The natural consequence of this is to drive the farmer and the animal further apart. However, closer attention to the animal not only positively impacts animal welfare and health but can also increase the capacity of the farmer to achieve a more sustainable production. State-of-the-art precision livestock farming (PLF) technology is one such means of bringing the animals closer to the farmer in the facing of expanding systems. Contrary to some current opinions, it can offer an alternative philosophy to 'farming by numbers'. This review addresses the key technology-oriented approaches to monitor animals and demonstrates how image and sound analyses can be used to build 'digital representations' of animals by giving an overview of some of the core concepts of PLF tool development and value discovery during PLF implementation. The key to developing such a representation is by measuring important behaviours and events in the livestock buildings. The application of image and sound can realise more advanced applications and has enormous potential in the industry. In the end, the importance lies in the accuracy of the developed PLF applications in the commercial farming system as this will also make the farmer embrace the technological development and ensure progress within the PLF field in favour of the livestock animals and their well-being. ImplicationsThis work address the main approaches utilised in developing precision livestock farming tools. Precision livestock farming is an approach that enables the farmer with more objective information about the animal to make better choices about the sustainability of their production system. This paper demonstrates some of the key solutions and the approaches taken to develop technologies with sound and image analyses. †

show abstract

On-farm and post-mortem health assessment

Temple,

Llonch,

Mainau

et al. 2024

Advances in Pig Welfare

View full text Add to dashboard Cite

A multivariate dynamic linear model for early warnings of diarrhea and pen fouling in slaughter pigs

Cited by 26 publications

References 14 publications

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

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

Review: Precision livestock farming: building ‘digital representations’ to bring the animals closer to the farmer

On-farm and post-mortem health assessment

Contact Info

Product

Resources

About