Estimation of oxygen uptake rate of tomato (Lycopersicon esculentum Mill.) fruits by artificial neural networks modelled using near-infrared spectral absorbance and fruit mass

The oxygen uptake rate of tomato fruits was estimated by an artificial neural network (ANN) model using near-infrared (NIR) spectral absorbance and fruit mass. The absorption peak apex from cytochrome c oxidase (COX) was confirmed at 841 nm for mitochondrial preparation and at 833 nm for intact fruits. The results of a proteome analysis that detected the putative COX subunit II PS17 from the mitochondrial preparation biochemically supported the presence of the absorption peak due to COX. An ANN model for estimating O-2 uptake rate was developed from the absorbance data at 11 wavelengths from 645 to 979 nm including 833 nm and fruit mass as input variables. The O-2 uptake rate was estimated by the proposed model with a correlation coefficient of 0.79 and a standard error of prediction of 0.091 mmol kg(-1) h(-1). This method may be effective for rapid estimation of shelf life and physiological activity of tomato fruits. (C) 2009 Elsevier Ltd. All rights reserved.