Simultaneous Determination of Vitamin B Complex Using Wavelet Neural Network

• 来源期刊: 中国化学(英文版)
• 学科: 化学
• 年，卷（期）: 2001,（9）
• 页码范围: 836-841
• 页数: 6页
• 分类号: O6
• 语种: 英文

摘要

A simultaneous determination of four conponents of B-groupvitamin, using a novel wavelet-based neural network (WNN), combined with correlation coefficient and standard deviation approach for wavelength selection, was reported in this work. Eleven representative wavelength points were selected from each o inginal UV spectrun, based on correlation coefficients and standard deviations of the observed data. A family of wavelet basic functions built from Morlet wavelet was adopted to improve the transfer quality of output data and solve the problems of training difficultly involved in neural networks, Tne predicted results, with fitting correlation coefficients (R = 0.9998-0.9999) and rooted mean squares errors (RMS =0.0578-0.1478), are satisfactory.