This paper demonstrates the use of the artificial neural networks (ANN) for multicomponent spectrometric anal. The artificial neural networks algorithm, and its effect factors were investigated. Ultra-violet spectrophotometric anal. of a five-component system (vitamin B1, B2, B6, O, and niacinamide) is described and compared to the results from CPA method based on Beer's law (C. W. Brown, et al., 1982). The feature of the ANN approach is the anal. can be automatically adjusted by using the computing process to accommodate linear and nonlinear response in different spectral regions. The result of the study showed that the method is superior to some other popular methods.

Key words: ULTRAVIOLET SPECTROPHOTOMETRY, SPECTROPHOTOMETRY, VITAMIN B1, MULTICOMPONENT SYSTEM, COMPUTER APPLICATIONS, NICOTINAMIDE, VITAMIN C, VITAMIN B6, VITAMIN B2, NEURAL NETWORK