By: Anders L. Madsen (HUGIN)
27 February 2017
The ComBDK model demonstrated on this page is a slightly modified version of the ComBDK model developed in corporation with Anna Garcia, Technical University of Denmark, National Food Institute as part of the CamVac project running from 01/03/2010 until 31/12/2014.
The ComBDK model served as a starting point for the development of the Feed Additive decision model developed in CytoCam.
The model deployed here implements Reward system 2 [Garcia et al, 2016]].
The ComBDK model was developed for decision support on commercial broiler vaccination. The model was designed for the Danish market and production in Denmark. The decision considered by the farmer is whether or not to and how to vaccinate a broiler. We assume the farmer has two vaccines referred to as vaccination A and vaccination B both with oral delivery to choose from (in addition to not vaccinating). The decision must been taken at two weeks where the birds are grown for five weeks.
Below are some HUGIN widgets for interacting with the model. This interface has been developed using the HUGIN Web Service API ([Madsen et al, 2013]).
The model is used under the assumption that the farmer at the time of decision knows the value of a set of risk factors related to farm characteristics, system variables and observations. The three risk factors included in the model are shown on the far left where the user is expected to select the corresponding value for each risk factore. The middle column shows the decision alternatives under the heading Vaccination. Below the decision alternatives the cost, reward and combined cost and reward are shown. On the far right, the expected impact of the selected decision alternative is shown.
Observations at 2 weeks on risk factors and effectiveness factors related to the vaccination should be entered prior to making the decision on the method of vaccination. Select the appropriate values below.
Observations on risk, effectiveness factors and observed level of campylobacter at two weeks should be selected above deciding on the method of vaccination.
The expected selling price at five weeks is and the expect cost is for flyscreens and for vaccination. This means that the expected profit is .
The expected campylobacter level at slaughter is
[Garcia et al, 2016] define the best case scenario as follows:
Similarly, [Garcia et al, 2016] define the worst case scenario as follows:
[Madsen et al, 2013] Madsen, A. L., Karlsen, M., Barker, G. C., Garcia, A. B., Hoorfar, J., Jensen, F (2013). A Software Package for Web Deployment of Probabilistic Graphical Models. In Proceedings of the Twelfth Scandinavian Conference on Artificial Intelligence (SCAI), pages 175-184.
[Garcia et al, 2016] Garcia, A.B., Madsen, A.L., Vigre, H. (2016). A decision support system for the control of Campylobacter in chickens at farm level using data from Denmark, Journal of Agricultural Science, 154, pages 720-731.
Useful references for those interested in BBN include:
[Kjærulff and Madsen, 2013] Kjærulff, U. B. and Madsen, A. L. (2013) Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis. Springer, Second Edition.
For further details on the paper: Anna Garcia
For further details on the use of Bayesian networks and web deployment of models contact: Anders L Madsen (alm(at)hugin(dot)com)
HUGIN EXPERT A/S takes no responsibility whatsoever for examples and information in examples published on this web site. ALL EXAMPLES ARE FOR DEMONSTRATION PURPOSES ONLY.