Enhanced pregnancy testing (DRGTTST1.NET)
A more realistic example includes the heat detection at three weeks of age, and allows for the possibility of different herd levels for the pregnancy rate. Very often the sow will return regularly to heat three weeks after mating. If this heat is detected, the pig producer knows that the sow is not pregnant and therefore, she will not make any pregnancy test. A simple expansion of the net in figure 1 captures this. This example can be handled by the demo-version of Hugin.
The graph in figure has three additional nodes compared to Simple pregnancy testing.
- Herdlevel Gives the possibility of specifying different level for
pregnancy probability in the herd. The node has 7 states (0.70, 0.75,0.80, 0.85, 0.90, 0.95, 0.975) with uniform apriori probabilities (1/7).
- Heat_DetectionIndicates the quality of the heat detection
(corresponds to Preg_test). The node has two states (Good, Bad) with prior probabilities (0.50,0.50)
- Heat_DiagnoseIndicates the outcome of the pregnancy test
(corresponds to Preg_diagnose). The node has two states ( Neg, Pos).
By combination of the networks such as these we obtain the foundation for herd monitoring networks