Neural network prediction of physical property changes of dried carrot as a function of fractal dimension and moisture content

Abstract The relationship between microstructural and physical properties of dried foods is difficult to quantify. This study uses artificial neural network analysis (ANN) to predict shrinkage and rehydration of dried carrots, based on inputs of moisture content and normalized fractal dimension analysis (Δ D / D 0 ) of the cell wall structure. Several drying techniques were used including conventional hot air (HAD), low pressure superheated steam (LPSSD), and freeze drying (FD). Dried carrot sections were examined by light microscopy and the fractal dimension (D) determined using a box counting technique. Optimized ANN models were developed for HAD, LPSSD, HAD + LPSSD, and HAD + LPSSD + FD, based on 1–10 hidden layers and neurons per hidden layer. ANN models were then tested against an independent dataset. Measured values of shrinkage and rehydration were predicted with an R 2  > 0.95 in all cases.

[1]  I. Saguy,et al.  Fractal analysis and crust water diffusivity of a restructured potato product during deep-fat frying , 1997 .

[2]  Jane Sélia dos Reis Coimbra,et al.  Modeling sterilization process of canned foods using artificial neural networks , 2005 .

[3]  Shyam S. Sablani,et al.  Using neural networks to predict thermal conductivity of food as a function of moisture content, temperature and apparent porosity , 2003 .

[4]  Benoit B. Mandelbrot,et al.  Fractal Geometry of Nature , 1984 .

[5]  S. Devahastin,et al.  Fractal Characterization of Some Physical Properties of a Food Product under Various Drying Conditions , 2007 .

[6]  José Miguel Aguilera,et al.  Description of the Convective Air-Drying of a Food Model by Means of the Fractal Theory , 2003 .

[7]  José Miguel Aguilera,et al.  Description of food surfaces and microstructural changes using fractal image texture analysis , 2002 .

[8]  Mark D. Normand,et al.  Characterization of the Ruggedness of Instant Coffee Particle Shape by Natural Fractals , 1985 .

[9]  Blas J. BARLElTA,et al.  Fractal Analysis to Characterize Ruggedness Changes in Tapped Agglomerated Food Powders , 1993 .

[10]  C. Ratti.  Shrinkage during drying of foodstuffs , 1994 .

[11]  J. C. Graf.  The importance of resolution limits to the interpretation of fractal descriptions of fine particles , 1991 .

[12]  Alberto M. Sereno,et al.  Modelling shrinkage during convective drying of food materials: a review , 2004 .

[13]  José S. Torrecilla,et al.  Artificial neural networks : a promising tool to design and optimize high-pressure food processes , 2005 .

[14]  Shan-hui Hsu,et al.  Viscoelastic Changes of Rice Starch Suspensions During Gelatinization , 2000 .

[15]  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 .

[16]  M. R. Ochoa,et al.  VOLUME AND AREA SHRINKAGE OF WHOLE SOUR CHERRY FRUITS (PRUNUS CERASUS) DURING DEHYDRATION , 2002 .

[17]  Arun S. Mujumdar,et al.  A Comparative Study of Low-Pressure Superheated Steam and Vacuum Drying of a Heat-Sensitive Material , 2004 .