Near infrared spectroscopy as a fast and non-destructive technique for total acidity prediction of intact mango: Comparison among regression approaches

Abstract

In the present study, the potential of near infrared spectroscopy (NIRS) as a rapid and non-destructive tools for quality attributes measurement of intact mango was investigated. Three different regression approaches namely partial least square regression (PLSR), support vector machine regression (SVMR), and artificial neural network (ANN) were used and compared in predicting total acidity (TA) of intact mangos. This quality parameter prediction models were established based on near infrared diffuse reflectance spectra acquired in wavelength range from 1000 to 2500 nm. Standard normal variate (SNV) transformation was applied as spectra enhancement prior to prediction models development. The results obtained show that ANN and SVMR are better than PLSR for TA prediction. The optimal prediction model for TA quality attribute were obtained by ANN with the first 4 principal components (PCs) scores as input. The coefficient determination of calibration (R2cal) and prediction (R2pred), the root-mean square error of calibration (RMSEC) and prediction (RMSEP), and the ratio of prediction to deviation (RPD) were 0.97, 0.89, 25.29 mg100g−1, 28.42 mg100g−1 and 4.02, respectively. The overall results satisfactorily demonstrate that NIRS technology combined with proper regression approaches has the promising results to determine TA of intact mango non-destructively.