PATTERN-RECOGNITION OF JET FUEL CHROMATOGRAPHIC DATA BY ARTIFICIAL NEURAL NETWORKS WITH BACK-PROPAGATION OF ERROR

被引：54

作者：

LONG, JR ^{[1
]}

MAYFIELD, HT ^{[1
]}

HENLEY, MV ^{[1
]}

KROMANN, PR ^{[1
]}

机构：

[1] FT VALLEY STATE UNIV,DEPT CHEM,FT VALLEY,GA 31030

来源：

ANALYTICAL CHEMISTRY | 1991年 / 63卷 / 13期

关键词：

D O I：

10.1021/ac00013a014

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

The purpose of this article is to demonstrate the application of artificial neural networks as a pattern recognition tool for chromatographic data. Multilayer feedforward networks using back-propagation and the generalized delta rule were simulated on a microcomputer. Network parameters and architectures were optimized to give maximum network classification performance. The chromatographic data for seven different classes of jet fuels were collected by GC and GC/MS. Binary patterns were used to represent various classes. The technique was tested and compared to K nearest neighbor, KNN, and soft independent modeling of class analogy, SIMCA.

引用

页码：1256 / 1261

页数：6

共 13 条

[1] EXPERIMENTS ON NEURAL NET RECOGNITION OF SPOKEN AND WRITTEN TEXT [J].