The Measurement of Luwak Content in Coffee Blends Using UV-Visible Spectroscopy Combined with Support Vector Machine Regression (SVMR)

Abstract

In this study, an investigation of using UV-Vis spectroscopy combined with support vector machine regression (SVMR) was evaluated for luwak coffee authentication. For this purpose, we provide 98 samples of coffee blends (mixed of luwak and non-luwak coffee). The range of luwak content in coffee blends was 50-100%. UV-Vis spectral data of the all samples were acquired using a UV-Vis spectrometer in transmittance mode. The coefficient of determination (R2), root mean square error of calibration (RMSEC), and residual prediction deviation (RPD) were used to evaluate the accuracy of the developed SVMR calibration model. The results show that UV-Vis spectroscopy combined with SVMR method was a promising method to quantify luwak content in coffee blends with high R2 and low RMSEC. The RPD value of more than three was also obtained.