Estimation of Microbial Growth Parameters by Means of Artificial Neural Networks

An alternative method based on artificial neural networks (ANN) for the estimation of kinetic growth parameters of a microorganism is performed by applying an automatic regression on different sections of the growth curve so as to obtain more precise growth rate and lag-time values. Through the combination of genetic algorithms and pruning methods more simple neural networks are obtained, where the goodness of fitness is a combination of an error function with another function associated with the network's complexity. An interesting application of this method was the estimation of kinetic parameters in microbial growth (growth rate and lag-time) and specifically in our case, the analysis of the effect of NaCl concentration, pH level and storage temperature on the growth curves of Lactobacillus plantarum. In this study it was hoped that the architecture of the obtained model would be very simple, but still keep its adequate capacity of generalization. The comparison performed between the average standard error of predictions (SEP) obtained for the estimation of growth rate and lag-time by the automatic regression (20 and 24%, respectively) and by the Gompertz estimation (22 and 28%) showed the utility of this method. Se ha desarrollado un método alternativo para la estimación de los parámetros cinéticos de crecimiento de un microorganismo basado en redes neuronales artificiales (ANN). El método se basó en la aplicación de regresión automática sobre diferentes secciones de la curva de crecimiento para obtener valores más precisos de la tasa de crecimiento y del tiempo de adaptación. Con la combinación de algoritmos genéticos y métodos de poda se obtuvieron redes más sencillas, donde la bondad del ajuste es una combinación de una función de error con otra función asociada con la complejidad de la red. Una aplicación interesante de este método fue la estimación de los parámetros cinéticos de crecimiento (tasa de crecimiento y tiempo de adaptación) de Lactobacillus plantarum, en función de la concentración de NaCl, pH y temperatura de almacenamiento. En este estudio se intentó conseguir que la arquitectura del modelo obtenido fuera muy sencilla, pero que mantuviera una adecuada capacidad de generalización. La comparación realizada de las medias de los errores estándares de predicción (SEP) obtenidos para la estimación de la tasa de crecimiento y tiempo de adaptación por medio de la regresión automática de ventanas (20 y 24%, respectivamente) y la ecuación de Gompertz (22 y 28%, respectivamente) muestran la utilidad de este método.

[1]  T. A. Roberts,et al.  Predicting microbial growth: growth responses of salmonellae in a laboratory medium as affected by pH, sodium chloride and storage temperature. , 1988, International journal of food microbiology.

[2]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[3]  T. A. Roberts,et al.  Predicting microbial growth: the consequences of quantity of data. , 1989, International journal of food microbiology.

[4]  Ali A. Minai,et al.  Back-propagation heuristics: a study of the extended delta-bar-delta algorithm , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[5]  F. Rombouts,et al.  Modeling of the Bacterial Growth Curve , 1990, Applied and environmental microbiology.

[6]  David E. Rumelhart,et al.  Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

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

[8]  J. Baranyi.  Notes on reparameterization of bacterial growth curves , 1992 .

[9]  J F Van Impe,et al.  Dynamic mathematical model to predict microbial growth and inactivation during food processing , 1992, Applied and environmental microbiology.

[10]  J Baranyi,et al.  A predictive model for the combined effect of pH, sodium chloride and storage temperature on the growth of Brochothrix thermosphacta. , 1993, International journal of food microbiology.

[11]  P Dalgaard,et al.  Estimation of bacterial growth rates from turbidimetric and viable count data. , 1994, International journal of food microbiology.

[12]  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.

[13]  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.

[14]  M. H. Zwietering,et al.  Modeling of Bacterial Growth with Shifts in Temperature , 1994, Applied and environmental microbiology.

[15]  J F Van Impe,et al.  Predictive microbiology in a dynamic environment: a system theory approach. , 1995, International journal of food microbiology.

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

[17]  Peter M. Williams,et al.  Bayesian Regularization and Pruning Using a Laplace Prior , 1995, Neural Computation.

[18]  Martin T. Hagan,et al.  Neural network design , 1995 .

[19]  A. Lebert,et al.  Recommendations for calculating growth parameters by optical density measurements , 1996 .

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

[21]  J. V. Van Impe,et al.  Effect of dissolved carbon dioxide and temperature on the growth of Lactobacillus sake in modified atmospheres. , 1998, International journal of food microbiology.

[22]  A H Geeraerd,et al.  Application of artificial neural networks as a non-linear modular modeling technique to describe bacterial growth in chilled food products. , 1998, International journal of food microbiology.

[23]  Schepers,et al.  Comparison of simple neural networks and nonlinear regression models for descriptive modeling of Lactobacillus helveticus growth in pH-controlled batch cultures. , 2000, Enzyme and microbial technology.

[24]  César Hervás-Martínez,et al.  Correction of Temperature Variations in Kinetic-Based Determinations by Use of Pruning Computational Neural Networks in Conjunction with Genetic Algorithms , 2000, J. Chem. Inf. Comput. Sci..

[25]  S. Jeyamkonda,et al.  Microbial growth modelling with artificial neural networks. , 2001, International journal of food microbiology.

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

[27]  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.