1998
DOI: 10.1021/ac980078m
|View full text |Cite
|
Sign up to set email alerts
|

Chemical Information Based on Neural Network Processing of Near-IR Spectra

Abstract: Three 100-compound spectra libraries have been used to evaluate artificial neural network classifications of functional groups. A near-IR gas-phase library was used to compare neural network classifications with those obtained by two-dimensional principal component analysis (PCA) score plots and by the use of the Mahalanobis distance metric based on multidimensional (score) vectors. The neural network using a radial basis function algorithm was able to correctly classify all aromatic and nonaromatic samples in… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
12
0
1

Year Published

1999
1999
2005
2005

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 24 publications
(14 citation statements)
references
References 24 publications
(29 reference statements)
1
12
0
1
Order By: Relevance
“…71,72 For quantitative treatment, it is worth mentioning Artificial Neural Networks (ANN) as an emerging alternative for NIR calibration. 73,74 This technique may present some advantages when non-linearity (not easily accommodated by PCR and PLS) between the spectral data and the quantitative information of interest exists.…”
Section: Chemometricsmentioning
confidence: 99%
“…71,72 For quantitative treatment, it is worth mentioning Artificial Neural Networks (ANN) as an emerging alternative for NIR calibration. 73,74 This technique may present some advantages when non-linearity (not easily accommodated by PCR and PLS) between the spectral data and the quantitative information of interest exists.…”
Section: Chemometricsmentioning
confidence: 99%
“…Applications of NNs exist in almost all fields of analytical chemistry. They have also been applied to the analysis of spectroscopic data, as well as for mass [7], near-infrared [8], fluorescence [9] and NMR [10] spectra, to list only a few current examples.…”
Section: Application Of Neural Networkmentioning
confidence: 99%
“…The NN will start to fit the noise in the training set, and the result is a so-called 'overtrained' net. By using the trained net to predict the output of a second monitoring data set simultaneously, it is possible to determine the optimum number of iterations for the training set [8]. During the learning phase the mean deviation between the computed and the correct output values of the training set decreased constantly.…”
Section: Min_k /D Min_0mentioning
confidence: 99%
“…Uma técnica recente, apresentada neste trabalho, é o uso de redes neurais artificiais (RNAs) [7,12]. Na química, problemas classicamente resolvidos por técnicas multivariadas como a análise de componentes principais, por exemplo, são agora comparados com a solução através de redes neurais [6].…”
Section: Introductionunclassified