Portable NIR Spectroscopic Application for Coffee Integrity and Detection of Adulteration with Coffee Husk

Reliable and user-friendly discrimination of coffee bean integrity quantification adulteration in the processing value chain would be vital for ensuring consumer trust quality control traceability management. In this research, a portable short-wave NIR spectroscopy coupled with chemometric data analysis was employed under different pre-treatments to develop rapid detection technique. Different pre-processing treatments (multiplicative scatter correction; MSC, standard normal variant; SNV, first derivative; FD) together multivariate techniques; support vector machine (SVM), linear discriminant (LDA), neural network (NN), random forest (RF) were comparatively assessed using accuracy correlation coefficient (R) quantification. The results showed that FD-LDA model had 97.78% 100 % both calibration set prediction set. comparison, SPA-PLS R = 0.9711 0.9897 outcome study spectroscopic techniques could used examining coffee.