Extending the dynamic range of copper determination in differential pulse adsorption cathodic stripping voltammetry using wavelet neural network

A wavelet neural network (WNN) model is proposed for extending the dynamic range of Cu(II) determination by differential pulse adsorption cathodic stripping voltammetry (DP-AdSV) using xylenol orange (XO) as a suitable ligand. All of voltammograms data consisting of Cu(II) and Cu(II)–XO peak currents were used in WNN model. The WNN model consisted of three layers (2-8-1) with the Morlet mother wavelet transfer function in the hidden layer. The model was able to extend the dynamic range of Cu(II) from its narrow linear range (1–50 ng ml^?1) to the higher dynamic range (1–1500 ng ml^?1). The results of the WNN model was also compared with artificial neural network (ANN) model and it was demonstrated the superiority of the WNN model relative to ANN model.