Simultaneous quantitative UV spectrophotometric determination of multicomponents of amino acids using linear neural network.

Simultaneous determination of multicomponents of six amino acids with a novel chemometric technique-a linear neural network (LNN) algorithm is reported in this study. Based on the data correlation coefficient and standard deviation method, 17 representative wavelength points are selected from the original UV spectral data (343 points) as the original input patterns for LNN to build a neural network model. The results obtained only by iterating 15 times is satisfying, with a correlation coefficient of 0.999 and a relative small standard deviation.