In the area of food safety, there is an increasing awareness for the need to recognise potential risks in the food chain before these risks are actually having an effect [1,2]. To identify these emerging risks is a difficult and labour-intensive task. This problem is exacerbated by the fact that at this early stage the causes of these risks may not yet be related to food at all . Small changes in areas unrelated to food production, such as policy, environment, or technology can start a cascade of causes and effects that in the end have an impact on food safety. It is clear that to be able to reliably predict these emerging risks, many different fields of expertise need to be taken into account. Decision support systems are now being created that will incorporate knowledge from many different domains and are thereby able to deduce the emergence of new risks to the food chain. To this end, we created a prototype Emerging Risk Detection Support System (ERDSS) for the Dutch food safety authority (NVWA) . This computer system uses automatic reasoning to detect emerging risks. It presents the reasoning steps followed to experts, who are then able to evaluate the potential risk and decide on possible countermeasures at a very early stage. The information needed for reasoning consists of (i) events detected on the web and (ii) heuristic rules describing expert knowledge about food safety. This information can be extracted from databases, web services, computer models, experts or from text mining of scientific journals or media on the internet. This method for detecting emerging risks is now also being applied in other areas such as the discovery of new innovations  and may be extended to the detection of risks and opportunities in supply chains. Acknowledgements: The research presented here was supported by the Dutch Ministry of Economic Affairs and the Dutch national program COMMIT. Keywords: Emerging risk, Food safety, Decision support, Information management.
There are no comments yet. You can post the first one!
Post a comment
Please log in to use this service. Login as Wageningen University & Research user or guest user in upper right hand corner of this page.