ARTIFICIAL NEURAL NETWORKS IN MODELING OSMOTIC DEHYDRATION OF FOODS CHARLES TORTOE 1,5 , JOHN ORCHARD 2 , ANTHONY BEEZER 3 and JOHN TETTEH 4 1 Food Research Institute (Council for Scientific and Industrial Research) PO Box M20, Accra, Ghana 2 Natural Resources Institute–FMMG University of Greenwich Medway Campus Central Avenue Chatham, Kent, ME4 4TB, U.K. 3 School of Pharmacy University of London 29-39 Brunswick Square, London, WC1N 1AX, U.K. 4 Medway Sciences University of Greenwich Medway Campus Central Avenue Chatham, Kent, ME4 4TB, U.K. Accepted for Publication December 12, 2007 ABSTRACT Artificial neural network (ANN) models for water loss (WL) and solid gain (SG) were evaluated as potential alternative to multiple linear regression (MLR) for osmotic dehydration of apple, banana and potato. The radial basis function (RBF) network with a Gaussian function was used in this study. The RBF employed the orthogonal least square learning method. When predictions of experimental data from MLR and ANN were compared, an agreement was found for ANN models than MLR models for SG than WL. The regression coefficient for determination (R 2 ) for SG in MLR models was 0.31, and for ANN was 0.91. The R 2 in MLR for WL was 0.89, whereas ANN was 0.84. Osmotic dehydration experiments found that the amount of WL and SG occurred in the following descending order: Golden Delicious apple > Cox apple > potato > banana. The effect of temperature and concentration of 5 Corresponding author. TEL: +233-21519091; FAX: +233-21500111; EMAIL: ctortoe@yahoo.co.uk Journal of Food Processing and Preservation 32 (2008) 270–285. All Rights Reserved. © 2008, The Author(s) Journal compilation © 2008, Blackwell Publishing 270