Simultaneous Determination of Ethanol, Fructose, and Glucose at an Unmodified Platinum Electrode Using Artificial Neural Networks

Dual pulse staircase voltammetry (DPSV)a combination of pulsed electrochemical detection and staircase voltammetryis investigated for the simultaneous determination of glucose, fructose, and ethanol in mixtures. Each analyte is found to elicit a distinctive response at a platinum electrode in an alkaline solution. A method is devised for visualizing the electrochemical responses of numerous mixtures of the three compounds simultaneously, and application of this method reveals that the mixed responses contain characteristics of the individual analytes approximately in proportion to their concentrations but that the combination of the individual responses is not a simple summation. Extraction of individual analyte concentrations from combined DPSV responses is subsequently achieved using artificial neural networks (ANNs). The effects of the amount of training data, the number of hidden neurons, the hidden neuron transfer function, and the network training time are investigated. Large amounts of training data and a hidden layer with log-sigmoidal transfer functions are found to give the best results. Networks with relatively small hidden layers and relatively little training are found to produce the most generalized models, giving the most accurate concentration predictions when tested on analyte concentrations not present in the training data. The lowest rms errors achieved were 40 μM, 40 μM, and 0.5 mM for fructose, glucose, and ethanol, respectively, over a range of approximately 0−700 μM for the sugars and a range of 0−12 mM for ethanol. The success of this novel combination of DPSV and ANNs opens new possibilities for the simultaneous detection of mixtures of aliphatic compounds, which are traditionally considered difficult to detect.