Near infrared spectroscopy coupled chemometric algorithms for prediction of the antioxidant activity of peanut seed (Arachis hypogaea)

In the present research work, near infrared (NIR) spectroscopy coupled with chemometric algorithms such as partial least-squares (PLS) regression and some effective variable selection algorithms (synergy interval-PLS (Si-PLS), Backward interval-PLS (Bi-PLS), and genetic algorithm-PLS (GA-PLS)) were used for the quantification of antioxidant properties of peanut seed samples. The compositional parameters, such as DPPH, ABTS, FRAP, TPC, FCA, TFC, and TAC, were quantified using NIR spectroscopy. The developed models were assessed using correlation coefficients of the calibration (R-2) and prediction (r(2)); root mean standard error of cross-validation, RMSECV; root mean square error of prediction, RMSEP and residual predictive deviation, RPD. The efficiency of the developed model was significantly enhanced with the use of Si-PLS, Bi-PLS, and GA-PLS as compared to the classical PLS model. The results of the R-2 and r(2) set varied from 0.76 to 0.95 and 0.72 to 0.94, respectively. The obtained results revealed that NIR spectroscopy, coupled with different chemometric algorithms, has the potential to be used for rapid assessment of the antioxidant properties of peanut seed.