Applications - Predictive microbiology

Description

• Collaborator Institution:  Spanish Inter-Ministerial Commision of Science and Technology, European Regional Development fund, “Junta de Andalucia” (Spain) and Spanish Ministry of Education and Science. Department of Food Science and Technology of University of Córdoba (Spain).
• Main targeted goal: Design mathematical models for predicting the growth limits in microbiology field with a high confidence level. Implementation of risk management measures in food industries. This suppose a breakthrough in guaranteeing microbial food safety.
• Methodological subfield: Supervised Classification, Logistic Regression, Artificial Neural Networks, Evolutionary Computation, Metaheuristics, Decision-making process.
• Methodological contribution: New Artificial Neural Networks models with projection and kernel basis functions, Memetic Evolutionary Algorithms for unbalanced data, Hybrid models and Oversampling techniques.
• Impact in domain field:  More accurate predictions and to provide additional information regarding the variability of microbial responses under limiting conditions. Help to predictive modelers to better define the growth boundaries of microorganisms and to model the microbial variability associated with these conditions.

Publications

• Neural Network Ensembles to Determine Growth Multi-classes in Predictive Microbiology
• Evolutionary q-Gaussian Radial Basis Function Neural Network to determine the microbial growth/no growth interface of Staphylococcus aureus
• Memetic Pareto Evolutionary Artificial Neural Networks to determine growth/no-growth in predictive microbiology
• Development of a multi-classification neural network model to determine the microbial growth/no growth interface
• Memetic pareto differential evolutionary artificial neural networks to determine growth multi-classes in predictive microbiology