Computational neural networks for predictive microbiology II. Application to microbial growth

• Published in: International journal of food microbiology Vol. 34; no. 1; pp. 51 - 66
• Main Authors: Hajmeer, Maha N., Basheer, Imad A., Najjar, Yacoub M.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 1997; Elsevier
• Subjects: Biological and medical sciences; comparisons; Computational neural networks; equations; Food industries; Food microbiology; Fundamental and applied biological sciences. Psychology; Gompertz model; growth; growth & development; growth models; Microbial growth; microbial growth prediction; modified gompertz model; Multiple linear regression; multiple regression; neural networks; Neural Networks (Computer); prediction; Regression Analysis; Response surface models; Sensitivity and Specificity; Shigella flexneri; Shigella flexneri - growth & development; Gompertz model; Response surface models; Microbial growth; Shigella flexneri; Computational neural networks; Multiple linear regression; Performance evaluation; Microorganism growth; Linear regression; Prediction; Theoretical study; Foodstuff; Neural network; Multiple regression; Pathogenic; Computerized processing; Bacteria; Response surface; Biological contamination; Comparative study; Enterobacteriaceae
• ISSN: 0168-1605; 1879-3460
• DOI: 10.1016/S0168-1605(96)01169-5

The growth of a specific microorganism on a certain food is influenced by a number of environmental factors such as temperature, pH, and salt concentration. Models that delineate the history of the growth of microorganisms are always subject to a considerable debate and scrutiny in the field of predictive microbiology. Regardless of its type, a growth model (e.g., modified Gompertz model) contains several parameters that vary depending on the microorganisms/food combination and the associated prevailing environmental conditions. The growth model parameters for a set of operating conditions are commonly determined from expressions developed via multiple linear regression. In the present study, a substitute for the nonlinear regression-based equations is developed using computational neural networks. Computational neural networks are applied herein on experimental data pertaining to the anaerobic growth of Shigella flexneri. Results have indicated that predictions by neural networks offer better agreement with experimental data as compared to predictions obtained via corresponding regression equations.