Abstract :
This paper suggests a novel method named DOSCWTRBFN based on radial basis function neural network (RBFN) with direct orthogonal signal correction (DOSC) and wavelet transform (WT) as a pre-processing tool for the simultaneous spectrophotometric determination of Mn(II), Zn(II), Co(II) and Cd(II). In this case, by optimization, the number of DOSC components, tolerance factor, wavelet function, decomposition level, the numbers of hidden nodes and the width sigma of RBFN for DOSCWTRBFN were selected as 1, 0.001, Symmlet 5, 3, 20 and 1.2 respectively. The relative standard errors of prediction (RSEP) for all components with DOSCWTRBFN, WTRBFN and RBFN were 7.5, 8.3 and 8.9 percent respectively. The proposed method has been successfully applied to analyze overlapping spectra and was proven to be better than other techniques.
Keywords :
radial basis function networks; signal processing; wavelet transforms; Cd; Co; DOSCWTRBFN; Mn; RBFN; WTRBFN; Zn; decomposition level; direct orthogonal signal correction; overlapping spectra; radial basis function neural network; relative standard errors; simultaneous spectrophotometric determination; tolerance factor; wavelet function; wavelet transform; Artificial neural networks; Calibration; Chemistry; Data mining; Joining processes; Neural networks; Radial basis function networks; Signal analysis; Wavelet analysis; Wavelet transforms; direct orthogonal signal correction; overlapping spectra; wavelet transform with radial rasis function neural network;
