Designing optimal food safety monitoring schemes using Bayesian network and integer programming: The case of monitoring dioxins and DL‐PCBs.
An object of class bn.fit. Refer to the documentation of bnlearn for details.
A discrete Bayesian network to optimize the use of resources for food safety monitoring. The Bayesian network is learned as in the referenced paper. The vertices are:
The results from the screening DR CALUX method (negative, suspect);
The monitoring year (2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017);
The quarter of the year (1, 2, 3, 4);
The animal species monitored (bovine animal, bovine animal for fattening, broiler, calf for fattening, cow, deer, duck, eel, fishm goat, goose, hen, horse, pig, poultry, rabbit, sheep, trout);
The food product type (egg, liver, meat, milk);
The control points (aquaculture, farm, slaughterhouse);
The number of samples analyzed for EU monitoring to estimate background contamination in different products (0, 1, ..., 31);
The results from the GC/MS method (0, n, p);
The number of samples collected during the monitoring period (196, 226, 254, 340, 352, 358, 365, 366, 379, 425).
Wang, Z., van der Fels-Klerx, H. J., & Oude Lansink, A. G. J. M. (2023). Designing optimal food safety monitoring schemes using Bayesian network and integer programming: The case of monitoring dioxins and DL-PCBs. Risk Analysis, 43(7), 1400-1413.