Application of artificial neural networks in HPLC method development

被引：30

作者：

Agatonovic-Kustrin, S ^{[1
]}

Zecevic, M

Zivanovic, L

Tucker, IG

机构：

[1] Univ Otago, Sch Pharm, Dunedin, New Zealand

[2] Fac Pharm Belgrade, Inst Pharmaceut Chem & Drug Anal, YU-11000 Belgrade, Yugoslavia

来源：

JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS | 1998年 / 17卷 / 01期

关键词：

artificial neural network; backpropagation; HPLC; amiloride; methychlothiazide;

D O I：

10.1016/S0731-7085(97)00170-2

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

The use of artificial neural networks (ANNs) for response surface modelling in HPLC method development for amiloride and methychlothiazide separation is reported. The independent input variables were pH and methanol percentage in mobile phase. The outputs were capacity factors. The results were compared with a statistical method (multiple nonlinear regression analysis). Networks were able to predict the experimental responses more accurately than the regression analysis. (C) 1998 Elsevier Science B.V. All rights reserved.

引用

页码：69 / 76

页数：8

共 12 条

[1]

DEMING SN, 1987, EXPT DESIGN CHEMOMET, V3

[2] INTRODUCTION TO BACKPROPAGATION NEURAL NETWORK COMPUTATION [J].