APPLICATION OF PATTERN-RECOGNITION AND FEATURE EXTRACTION TECHNIQUES TO VOLATILE CONSTITUENT METABOLIC PROFILES OBTAINED BY CAPILLARY GAS-CHROMATOGRAPHY

被引：46

作者：

MCCONNELL, ML ^{[1
]}

RHODES, G ^{[1
]}

WATSON, U ^{[1
]}

NOVOTNY, M ^{[1
]}

机构：

[1] INDIANA UNIV,DEPT CHEM,BLOOMINGTON,IN 47401

来源：

JOURNAL OF CHROMATOGRAPHY | 1979年 / 162卷 / 04期

关键词：

D O I：

10.1016/S0378-4347(00)81830-7

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

The applicability of threshold logic units, a form of nonparametric pattern recognition, to the processing of metabolic profile data obtained by high-efficiency glass capillary column gas chromatography has been investigated. The test data included profiles of the volatile constituents of urine from normal individuals and from individuals with diabetes mellitus. A feature extraction algorithm allowed for dimensionality reduction and indicated the constituents most important in the normal versus pathological distinction. With an optimum number of dimensions, a normal versus pathological prediction rate of 93.75% was achieved. Gas chromatography-mass spectrometry was utilized to identify important profile constituents. © 1979.

引用

页码：495 / 506

页数：12

共 31 条

[1]

[Anonymous], 1972, COMPUTER ORIENTED AP

[2] QUALITATIVE DETERMINATION OF PETROLEUM SAMPLE TYPE FROM GAS CHROMATOGRAMS USING PATTERN-RECOGNITION TECHNIQUES [J].