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 including, amongst others, total phenolic content, total flavanoid content and total antioxidant capacity. The developed models were assessed using coefficients of determination for the calibration (R2) and prediction (r2); 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 R2 for calibration and r2 for prediction 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.