Classification of bottled mineral waters using solution cathode glow discharge optical emission spectroscopy and chemometrics methods

Abstract

Water is the most important substance for daily life and contains minerals which play an important role in nutrition. In this study, seven kinds of bottled water in Chinese market were analysed and identified by the solution-cathode glow discharge optical emission spectroscopy (SCGD-OES) combined with chemometrics methods. The score matrix was obtained by principal component analysis (PCA), and the back propagation artificial neural network (BP-ANN) model was established to identify the kind of the brands of the bottled water based on their spectral properties. The average classification accuracy based on BP-ANN is 99.74%, support vector machine (SVM) model and linear discrimination analysis (LDA) model were also employed to classify the kind of the brands of the bottled water based on the PCA analysis results, and the correct identification rate based on SVM model and LDA model are 99.50% and 98.00%, respectively. It is confirmed that SCGD-OES combined with chemometrics methods is promising for automatic real time, reliable and robust measurement, and can be integrated into a simplified form for non-specialist users.