Decision Support Tool for the Agri-Food Sector Using Data Annotated by Ontology and Bayesian Network

Abstract

The scientific literature is a valuable source of information for developing predictive models to design decision support systems. However, scientific data are heterogeneously structured expressed using different vocabularies. This study developed a generic workflow that combines ontology, databases and computer calculation tools based on the theory of belief functions and Bayesian networks. The ontology paradigm is used to help integrate data from heterogeneous sources. Bayesian network is estimated using the integrated data taking into account their reliability. The proposed method is unique in the sense that it proposes an annotation and reasoning tool dedicated to systematic analysis of the literature, which takes into account expert knowledge of the domain at several levels: ontology definition, reliability criteria and dependence relations between variables in the BN. The workflow is assessed successfully by applying it to a complex food engineering process: skimmed milk microfiltration. It represents an original contribution to the state of the art in this application domain.

PO2/TransformON, an ontology for data integration on food, feed, bioproducts and biowaste engineering

“…However, this process remains difficult to understand as a whole, in particular, because the existing models 25 only evaluate a precise range of operating conditions and do not take into account the different types of membrane technologies that can be used 26 . To meet this challenge, Baudrit et al 27 designed a method combining the use of the PO2/TransformON vocabulary and a Bayesian network, to structure heterogeneous data sources, assess the reliability of data sources, and provide relevant recommendations based on deductive and quantitative reasoning. This innovative method allows answering specific questions from experts in the field, namely to predict the performance of the milk microfiltration process under a wide range of operating conditions and membrane technologies.…”

Integrating collective know-how for multicriteria decision support in agrifood chains—application to cheesemaking

“…Belna et al (2022) optimized microfiltration unit operation to integrate conflicting stakeholder objectives, such as maximizing product output quality while minimizing cost inputs and addressing environmental impacts. Baudrit et al (2022) used data from scientific articles describing the entire milk microfiltration process including several unit operations in addition to the milk microfiltration step as skimming, heat treatment or storage. Those data are available in Buche et al (2021).…”

“…Those data are available in Buche et al (2021). But the method presented in Baudrit et al (2022) only proposes to learn a predictive model of the milk microfiltration unit operation in large-scale operational conditions including different membranes.…”

“…The emergence of methods based on knowledge engineering in the field of food and bio-based product processing facilitates the development of decision-support tools that model complex reasoning based on processing operators' expertise (Buche et al, 2019;Baudrit et al, 2022;Belaud et al, 2022;Munch et al, 2022). Here we present a new multicriteria decision-support system (MCDSS) based on collective know-how which enables the formulation of recommendations on technological actions that may help maintain product quality or correct a product quality defect at the scale of a given food processing operation.…”