A probabilistic neural network approach for modeling and classification of bacterial growth/no-growth data.

In this paper, we propose to use probabilistic neural networks (PNNs) for classification of bacterial growth/no-growth data and modeling the probability of growth. The PNN approach combines both Bayes theorem of conditional probability and Parzen's method for estimating the probability density functions of the random variables. Unlike other neural network training paradigms, PNNs are characterized by high training speed and their ability to produce confidence levels for their classification decision. As a practical application of the proposed approach, PNNs were investigated for their ability in classification of growth/no-growth state of a pathogenic Escherichia coli R31 in response to temperature and water activity. A comparison with the most frequently used traditional statistical method based on logistic regression and multilayer feedforward artificial neural network (MFANN) trained by error backpropagation was also carried out. The PNN-based models were found to outperform linear and nonlinear logistic regression and MFANN in both the classification accuracy and ease by which PNN-based models are developed.

[1]  I A Basheer,et al.  Computational neural networks for predictive microbiology: I. Methodology. , 1997, International journal of food microbiology.

[2]  J F Frank,et al.  Defining the growth/no-growth interface for Listeria monocytogenes in Mexican-style cheese based on salt, pH, and moisture content. , 1999, Journal of food protection.

[3]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[4]  S. Nakai,et al.  Application of artificial neural networks for predicting the thermal inactivation of bacteria: a combined effect of temperature, pH and water activity , 2001 .

[5]  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.

[6]  Simon,et al.  Probabilistic neural networks using Bayesian decision strategies and a modified Gompertz model for growth phase classification in the batch culture of Bacillus subtilis. , 2001, Biochemical engineering journal.

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

[8]  T. Cacoullos.  Estimation of a multivariate density , 1966 .

[9]  Caren Marzban,et al.  A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes , 1996 .

[10]  D. A. Ratkowsky,et al.  Growth Limits of Listeria monocytogenesas a Function of Temperature, pH, NaCl, and Lactic Acid , 2000, Applied and Environmental Microbiology.

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

[12]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

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

[14]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[15]  T. Ross,et al.  Modelling the combined temperature and salt (NaCl) limits for growth of a pathogenic Escherichia coli strain using nonlinear logistic regression. , 2000, International journal of food microbiology.

[16]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[17]  I. A. Basheer,et al.  A NONLINEAR RESPONSE SURFACE MODEL BASED ON ARTIFICIAL NEURAL NETWORKS FOR GROWTH OF SACCHAROMYCES CEREVISME1 , 1998 .

[18]  Timothy Masters,et al.  Advanced algorithms for neural networks: a C++ sourcebook , 1995 .

[19]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[20]  T. Ross,et al.  Modelling the growth rate of Escherichia coli as a function of pH and lactic acid concentration , 1997, Applied and environmental microbiology.

[21]  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.

[22]  S M Alzamora,et al.  Probabilistic modeling of Saccharomyces cerevisiae inhibition under the effects of water activity, pH, and potassium sorbate concentration. , 2000, Journal of food protection.

[23]  Daniel Y. C. Fung,et al.  NEW APPROACH FOR MODELING GENERALIZED MICROBIAL GROWTH CURVES USING ARTIFICIAL NEURAL NETWORKS1 , 2000 .