A Data Fusion Model to Merge the Spectra Data of Intact and Powdered Cayenne Pepper for the Fast Inspection of Antioxidant Properties

Spectroscopy technology has been widely used for the quality assessment of agricultural products, but the models produced in recent studies usually focus on only one sample form. Meanwhile, most products, especially cayenne pepper, are not only in the form of fresh samples but also in powder. Therefore, the research used visible/near-infrared (Vis/NIR) spectroscopy to predict the antioxidant properties using a fusion model derived from both intact and powdered cayenne pepper. The parameters used to determine these properties include the %inhibition, antioxidant activity, and antioxidant capacity. The results showed that the fusion model at %inhibition was 0.90 (R-cal), 7.63 (RMSEC), 0.84 (R-pred), and 9.16 (RMSEP) while the antioxidant activity had 0.94, 181.82, 0.81 and 340.06, whereas antioxidant capacity produced 0.94, 14.42, 0.82 and 22.64 for R-cal, RMSEC, Rpred, and RMSEP, respectively. The Vis/NIR spectroscopy was able to predict the antioxidant properties in both the intact and powdered cayenne pepper using the fusion model.