Abstract

Abstract The electronic tongue (ET) system contains an ion selective electrode (ISE) array, with a signal recording system and data processing methodology. It is developed for simultaneous determination of multiple free ions dissolved in solutions for real-time in situ monitoring. This article outlines an application of the ET system to determine chloride (Cl) simultaneously, and multi cationic metal ions, including calcium (Ca), cadmium (Cd), copper (Cu) and lead (Pb). In this study, Principal Component Analysis (PCA) was applied as a data compaction technique to reduce the complexity of data from the ISE array without losing much information. A patent data preprocessing method, genetic ICA, was utilized to improve the prediction accuracy of ANN. Moreover, Orthogonal Experiment Design was employed for minimizing the number of training samples without losing any quality characteristics for the specific ions. Using our methodology means that results can be obtained rapidly and accurately without disturbing the natural speciation. The robustness and appropriateness of the approach were assessed using the mean relative error (MRE). When configured and optimized, the ET system can quantify the concentration of the four desired metals and chloride with the average MRE being lower than 0.10.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call