Memetic pareto differential evolutionary artificial neural networks to determine growth multi-classes in predictive microbiology

The main objective of this research is to automatically design Artificial Neural Network models with sigmoid basis units for multiclassification tasks in predictive microbiology. The classifiers obtained achieve a double objective: a high classification level in the dataset and high classification levels for each class. The Memetic Pareto Differential Evolution Neural Network chosen to learn the structure and weights of the Neural Networks is a Differential Evolutionary approach based on the Pareto Differential Evolution multiobjective evolutionary algorithm. The Pareto Differential Evolution algorithm is augmented with a local search using the improved Resilient Backpropagation with backtracking–iRprop+ algorithm. To analyze the robustness of this methodology, it has been applied to two complex classification problems in predictive microbiology (Staphylococcus aureus and Shigella flexneri). The results obtained show that the generalization ability and the classification rate in each class can be more efficiently improved within this multiobjective algorithm.

[1]  A. F. Adams,et al.  The Survey , 2021, Dyslexia in Higher Education.

[2]  Simon X. Yang,et al.  A neural network approach to predict survival/death and growth/no-growth interfaces for Escherichia coli O157:H7. , 2006, Food microbiology.

[3]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[4]  César Hervás-Martínez,et al.  Improving artificial neural networks with a pruning methodology and genetic algorithms for their application in microbial growth prediction in food. , 2002, International journal of food microbiology.

[5]  Juan Carlos Moltó,et al.  Enterotoxigenic staphylococci and their toxins in restaurant foods , 2002 .

[6]  Erol Gelenbe,et al.  Learning in the multiple class random neural network , 2002, IEEE Trans. Neural Networks.

[7]  C. Hervás-Martínez,et al.  Modelling the growth of Leuconostoc mesenteroides by Artificial Neural Networks. , 2005, International journal of food microbiology.

[8]  H. Abbass,et al.  PDE: a Pareto-frontier differential evolution approach for multi-objective optimization problems , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[9]  C. Hervás,et al.  Searching for new mathematical growth model approaches for Listeria monocytogenes. , 2007, Journal of food science.

[10]  M Hajmeer,et al.  A probabilistic neural network approach for modeling and classification of bacterial growth/no-growth data. , 2002, Journal of microbiological methods.

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  C. Hervás,et al.  Product unit neural network models for predicting the growth limits of Listeria monocytogenes. , 2007, Food microbiology.

[13]  B. Natarajan.  Machine Learning: A Theoretical Approach , 1992 .

[14]  M. Hajmeer,et al.  Reliability-based estimation of the survival of Listeria monocytogenes in chorizos , 2006 .

[15]  Arie Ben-David,et al.  A lot of randomness is hiding in accuracy , 2007, Eng. Appl. Artif. Intell..

[16]  Gérard Dreyfus,et al.  Pairwise Neural Network Classifiers with Probabilistic Outputs , 1994, NIPS.

[17]  József Baranyi,et al.  Methods to determine the growth domain in a multidimensional environmental space. , 2005, International journal of food microbiology.

[18]  Pedro Antonio Gutiérrez,et al.  Development of a multi-classification neural network model to determine the microbial growth/no growth interface. , 2010, International journal of food microbiology.

[19]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[20]  R. García-Gimeno,et al.  Modelling the growth boundaries of Staphylococcus aureus: Effect of temperature, pH and water activity. , 2009, International journal of food microbiology.

[21]  Bernhard Sendhoff,et al.  Pareto-Based Multiobjective Machine Learning: An Overview and Case Studies , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[22]  G. Zurera-Cosano,et al.  Improving microbial growth prediction by product unit neural networks , 2006 .

[23]  K. Davey.  Applicability of the Davey (linear Arrhenius) predictive model to the lag phase of microbial growth , 1991 .

[24]  Hussein A. Abbass,et al.  A Memetic Pareto Evolutionary Approach to Artificial Neural Networks , 2001, Australian Joint Conference on Artificial Intelligence.

[25]  J G Phillips,et al.  Model for the combined effects of temperature, initial pH, sodium chloride and sodium nitrite concentrations on anaerobic growth of Shigella flexneri. , 1994, International journal of food microbiology.

[26]  Pablo Moscato,et al.  A Gentle Introduction to Memetic Algorithms , 2003, Handbook of Metaheuristics.

[27]  T. A. Roberts,et al.  Effects of parameterization on the performance of empirical models used in `predictive microbiology' , 1996 .

[28]  R L Buchanan,et al.  Expansion of response surface models for the growth of Escherichia coli O157:H7 to include sodium nitrite as a variable. , 1994, International journal of food microbiology.

[29]  R. Pitt.  A Descriptive Model of Mold Growth and Aflatoxin Formation as Affected by Environmental Conditions. , 1993, Journal of food protection.

[30]  Christian Igel,et al.  Improving the Rprop Learning Algorithm , 2000 .

[31]  Sonia Marín,et al.  Predicting mycotoxins in foods: a review. , 2009, Food microbiology.

[32]  David E. Rumelhart,et al.  Product Units: A Computationally Powerful and Biologically Plausible Extension to Backpropagation Networks , 1989, Neural Computation.

[33]  T. Ross,et al.  Modelling the Growth Limits (Growth/No Growth Interface) of Escherichia coli as a Function of Temperature, pH, Lactic Acid Concentration, and Water Activity , 1998, Applied and Environmental Microbiology.

[34]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[35]  Christian Igel,et al.  Empirical evaluation of the improved Rprop learning algorithms , 2003, Neurocomputing.

[36]  J Baranyi,et al.  Mathematics of predictive food microbiology. , 1995, International journal of food microbiology.

[37]  T. Ross,et al.  Modelling the bacterial growth/no growth interface , 1995 .

[38]  Pedro Antonio Gutiérrez,et al.  Sensitivity Versus Accuracy in Multiclass Problems Using Memetic Pareto Evolutionary Neural Networks , 2010, IEEE Transactions on Neural Networks.

[39]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[40]  G. Zurera,et al.  Optimization of Computational Neural Network for Its Application in the Prediction of Microbial Growth in Foods , 2001 .

[41]  K Koutsoumanis,et al.  Development of a Safety Monitoring and Assurance System for chilled food products. , 2005, International journal of food microbiology.

[42]  G. Zurera-Cosano,et al.  An Artificial Neural Network Approach to Escherichia Coli O157:H7 Growth Estimation , 2003 .

[43]  J Andrew Hudson,et al.  Construction of and Comparisons Between Response Surface Models for Aeromonas hydrophila ATCC 7966 and a Food Isolate Under Aerobic Conditions. , 1992, Journal of food protection.

[44]  M N Hajmeer,et al.  Computational neural networks for predictive microbiology. II. Application to microbial growth. , 1997, International journal of food microbiology.

[45]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[46]  K. Koutsoumanisa,et al.  Development of a Safety Monitoring and Assurance System for chilled food products , 2004 .

[47]  Rainer Storn,et al.  Differential Evolution Research – Trends and Open Questions , 2008 .

[48]  Pedro Antonio Gutiérrez,et al.  Memetic Pareto Differential Evolution for Designing Artificial Neural Networks in Multiclassification Problems Using Cross-Entropy Versus Sensitivity , 2009, HAIS.

[49]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[50]  C. Hervás-Martínez,et al.  Estimation of Microbial Growth Parameters by Means of Artificial Neural Networks , 2002 .

[51]  I A Basheer,et al.  A hybrid Bayesian-neural network approach for probabilistic modeling of bacterial growth/no-growth interface. , 2003, International journal of food microbiology.