Detection of Pesticides in Water through an Electronic Tongue and Data Processing Methods

Abstract

This study highlights the implementation of an electronic tongue composed of carbon screen-printed electrodes, which were used to discriminate and classify pesticides, such as Curathane, Numetrin, and Nativo in water. Therefore, to verify the capacity and performance of the sensory system, solutions of each of the pesticides at a concentration of 10 ppm were prepared in the laboratory and compared with distilled water. Furthermore, to evaluate the minimum detection limit of the electronic tongue, solutions were prepared at different concentrations: 0.02, 0.04, 0.06, 0.08, 0.1, 0.15, 0.2, and 0.25 ppm, respectively. The analysis and classification of the different categories and concentrations were obtained from the use of pattern recognition and automatic learning methods, such as principal component analysis (PCA), linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbors (kNN), and naïve Bayes, during this process; the techniques accomplished more than 90% accuracy in pesticide concentrations. Finally, a 100% success rate in classifying the compound types was completely achieved.

Keywords

• electronic tongue
• pesticides
• screen-printed electrodes
• pattern recognition
• machine learning