[Determination and identification of synthetic food colors based on fluorescence spectroscopy and radial basis function neural networks].

Taking ponceau 4R and amaranth as an example, concentration prediction and kind identification of synthetic food colors by fluorescence spectroscopy and radial basis function neural networks are introduced. By using SP-2558 multifunctional spectral measuring system, the fluorescence spectra were measured for solution of ponceau 4R and amaranth excited respectively by the light with the wavelength of 300 and 400 nm. For each sample solution of ponceau 4R, 15 emission wavelength values were selected. The fluorescence intensity corresponding to the selected wavelength was used as the network characteristic parameters, and a radial basis function neural network for concentration prediction was trained and constructed. It was employed to predict ponceau 4R solution concentration of the three kinds of samples, and the relative errors of prediction were 1.42%, 1.44% and 3.93% respectively. In addition, for solution of ponceau 4R and amaranth, the fluorescence intensity corresponding to the fluorescence wavelength was used as the network characteristic parameters, and a radial basis function neural network for kind identification was trained and constructed. It was employed to identify the kind of food colors, and the accuracy is 100%. These results show that the method is convenient, fast, and highly accurate, and can be used for the detection of synthetic food color in food safety supervision and management.