مشخصات پژوهش

عنوان	Genetic Algorithm Strategy for Potential Selection in Simultaneous Voltammetric Determination of Vanillin and Vanillic Acid Using PC-ANN on Modified Glassy Carbon Electrode with Carbon Nanotube
نوع پژوهش	مقاله ارائه شده کنفرانسی
کلیدواژه‌ها	Differential pulse voltammetry; Vanillin; Vanillic acid; MWCNT; Potential selection; Principal component; Genetic algorithm; Artificial neural networks
چکیده	A voltammetric method with glassy carbon electrode-modified with multi-wall carbon nanotube (GCE-MWCNT) in Britton-Robinson buffer of pH = 4.0 for simultaneous analysis of vanillin and vanillic acid for first time is proposed by application of genetic algorithm-principal component-artificial neural networks (GA-PC-ANN) on the differential pulse voltammetric data. In analysis of these analytes in the same samples, the main difficulty is the high degree of overlapping of voltammograms. The relationships between the currents and the concentrations are complex and highly nonlinear. On the basis of the difference in the electroanalytical behavior between the two compounds, these two phenolic compounds can be determined simultaneous in binary mixtures. Feed-forward neural networks have been trained to quantity considered vanillin and vanillic acid in mixtures under optimum conditions. In this way, a one-layer network was trained. tansig and linear transfer functions were used in the hidden and output layers, respectively. Linear calibration graphs were obtained in the concentration range of 0.5-14.0 μgml-1 for vanillin and 0.6-15.0 μgml-1 for vanillic acid. The analytical performance of this method was characterized by the root mean square error and relative prediction error.
پژوهشگران	فاطمه فلاحتگر خمیران (نفر دوم)، رئوف قوامی زروان (نفر اول)