Publication no. C-2001-0601-04R |  VIEW ARTICLE

Prediction of Cooked Rice Texture Using an Extrusion Test in Combination with Partial Least Squares Regression and Artificial Neural Networks.

Chanintorn Sitakalin (1) and Jean-Francois C. Meullenet (1,2). (1) Department of Food Science, University of Arkansas, 2650N. Young Avenue, Fayetteville 72704; (2) Corresponding author. Phone: 501-575 6822. Fax: 501-575 6936. E-mail: <jfmeull@comp.uark.edu> Cereal Chem. 78(4):391-394. Accepted March 6, 2001. Copyright 2001 American Association of Cereal Chemists, Inc.

Spectral stress strain analysis was used in combination with partial least squares (PLS) regression and artificial neural networks (ANN) to predict nine sensory texture attributes of cooked rice. The models calculated with ANN were significantly more accurate in predicting most of the sensory texture characteristics evaluated than the PLS models. Furthermore, ANN models were more robust and discriminative than PLS models.