UV- Vis Spectroscopy and Chemometrics Analysis in Distinguishing Different Types of Bulgarian Honey

Abstract

The purpose of the present paper is studying the potential of honey discrimination based on its botanical origins using UV - Vis spectroscopy and subsequent statistical cluster analysis. For calibration of the honey classifier, thirty-six samples from three types of honey (produced from acacia, linden, and honeydew) are measured by a spectrophotometer “Cary100” with recorded wavelength range of 190~900 nm. Initially, we use the method of principal components analysis (PCA) to lower the number of wavelengths (inputs) and to produce a proper visualization of the experimental results. Next, the first two principal components are combined separately with Naïve Bayes classification (NBC) and k-means clustering (KMC) to develop PC-NBC and PC-KMC models. The high accuracy of the proposed honey classifiers is confirmed by a leave-one-out cross-validation test performed in MATLAB environment.