Automatic classification of water samples using an optimized SVM model applied to cyclic voltammetry signals.

Hugo Italo Romero, Ivan Ramirez, Cinthia Romero


In the present work, a novel automatic classification model that differentiates bottled water from tap water, is evaluated. The voltammetric technique consisted of three electrode setup. The output current has been considered for data analysis. From the results of grid search, six pairs of values were pre-selected for the parameters of σ and C whose results were similar. High values of accuracy, specificity and sensitivity were achieved in test dataset. The final decision was made after performing an ANOVA test of 100 repetitions of 5-fold cross-validation, 3000 models were evaluated with the parameter combinations described above for the SVM. The oxidation and reduction peaks of the water samples have been observed to be prominent.  Absolute values of current (I) increases in the case of public water samples, possibly due to the largest concentration of chloride ions which have a higher contributions to the conductivity.


electronic tongue, water quality, authenticity, machine learning, voltammetry.

Full Text:

Abstract : 3 PDF : 1

Article Metrics

Metrics Loading ...

Metrics powered by PLOS ALM

Esta publicación hace parte del Sistema de Revistas de la Universidad de Antioquia
¿Quieres aprender a usar el Open Journal system? Ingresa al Curso virtual
Este sistema es administrado por el Programa Integración de Tecnologías a la Docencia
Universidad de Antioquia
Powered by Public Knowledge Project