Response surface optimization of an artificial neural network for predicting the size of re-assembled casein micelles

An artificial neural network (ANN) was designed to predict the size of re-assembled micelles in casein solutions as influenced by pH of solution and ultrasonic treatment. A generalized feed-forward network consisted of five neurons in the input layer, one hidden layer and an output layer with one neuron optimized using response surface methodology (RSM). Number of hidden neurons, momentum coefficient and step size in the hidden layer, number of epochs and training runs were the variables optimized. A quadratic equation was applied to mean absolute error (MAE) of 52 artificial neural networks as the response. It was found that the first-order effect of epoch number is the most significant term in determination of MAE, followed by the interactive effect of epoch number and step size. Minimum response (MAE) was obtained by employing the following optimum conditions for the artificial neural network: hidden neurons number=10, momentum coefficient=0.6, step size=0.34, epoch number=6230 and training run=1.

[1]  Shyam S. Sablani,et al.  Neural networks for predicting thermal conductivity of bakery products , 2002 .

[2]  Mukta Paliwal,et al.  Neural networks and statistical techniques: A review of applications , 2009, Expert Syst. Appl..

[3]  P. Walstra.  Casein sub-micelles: do they exist? , 1999 .

[4]  T. Payens.  Association of caseins and their possible relation to structure of the casein micelle. , 1966, Journal of dairy science.

[5]  Chaoxin Zheng,et al.  Predicting shrinkage of ellipsoid beef joints as affected by water immersion cooking using image analysis and neural network , 2007 .

[6]  José S. Torrecilla,et al.  Application of artificial neural network to the determination of phenolic compounds in olive oil mill wastewater , 2007 .

[7]  D. Horne.  Casein structure, self-assembly and gelation , 2002 .

[8]  T. Huppertz,et al.  Reformation of casein particles from alkaline-disrupted casein micelles , 2008, Journal of Dairy Research.

[9]  J. O. Olajide,et al.  Prediction of oil yield from groundnut kernels in an hydraulic press using artificial neural network (ANN) , 2007 .

[10]  S. Goñi,et al.  Prediction of foods freezing and thawing times: Artificial neural networks and genetic algorithm approach , 2008 .

[11]  P. Walstra.  On the stability of casein micelles. , 1990 .

[12]  A. Lips,et al.  On the self-assembly of sodium caseinate , 1999 .

[13]  Yoav D. Livney,et al.  Casein micelle as a natural nano-capsular vehicle for nutraceuticals , 2007 .

[14]  Javad Khazaei,et al.  Prediction of process and product parameters in an orange juice spray dryer using artificial neural networks , 2008 .

[15]  R. Guo,et al.  pH-dependent structures and properties of casein micelles. , 2008, Biophysical chemistry.

[16]  E. Bayraktar,et al.  Response surface optimization of the separation of dl-tryptophan using an emulsion liquid membrane , 2001 .

[17]  C. Kruif.  Casein micelle interactions , 1999 .

[18]  C. Riverol,et al.  Estimation of the ester formation during beer fermentation using neural networks , 2007 .

[19]  Weibiao Zhou,et al.  Artificial neural network modelling of the electrical conductivity property of recombined milk , 2001 .

[20]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[21]  Javad Khazaei,et al.  Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by using artificial neural networks , 2007 .

[22]  B. O'kennedy,et al.  Comparison of re-micellised casein prepared from acid casein with micellar casein prepared by membrane filtration , 2005 .

[23]  I. Boyaci,et al.  Modeling and optimization II: Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction , 2007 .

[24]  G. Majumdar,et al.  Prediction of the viscosity of clarified fruit juice using artificial neural network: a combined effect of concentration and temperature , 2005 .

[25]  José S. Torrecilla,et al.  A neural network approach for thermal/pressure food processing , 2004 .

[26]  Deniz Baş,et al.  Modeling and optimization I: Usability of response surface methodology , 2007 .

[27]  Terrence L. Fine,et al.  Feedforward Neural Network Methodology , 1999, Information Science and Statistics.

[28]  Deniz Baş,et al.  Modeling and optimization III: Reaction rate estimation using artificial neural network (ANN) without a kinetic model , 2007 .

[29]  C. Akoh,et al.  Enzymatic production of infant milk fat analogs containing palmitic acid: optimization of reactions by response surface methodology. , 2007, Journal of dairy science.