scholarly journals Inference of Surface Parameters from Near-Infrared Spectra of Crystalline H2O Ice with Neural Learning

2010 ◽  
Vol 122 (893) ◽  
pp. 839-852 ◽  
Author(s):  
Lili Zhang ◽  
Erzsébet Merényi ◽  
William M. Grundy ◽  
Eliot F. Young
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Surface Parameters ◽  
Neural Learning ◽  
Near Infrared Spectra

Non-Supervised Neural Categorisation of near Infrared Spectra. Application to Pure Compounds

1995 ◽  
Vol 3 (2) ◽  
pp. 97-110 ◽  
Author(s):  
Paloma Cáceres-Alonso ◽  
Alvaro García-Tejedor
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Complex Data ◽  
Neural Learning ◽  
Near Infrared Spectra ◽  
Pure Compounds ◽  
Open Issue ◽  
Preliminary Study ◽  
Recognition Technique

Near infrared (NIR) spectroscopy is recognised world-wide as a powerful tool for substance quantification and identification provided that good data analysis tools are used. Most of the identification algorithms use supervised learning and require previous knowledge of existing categories to construct the mathematical models that will be later used at runtime. The use of non-supervised neural learning algorithms is not a common tool in identification of near infrared spectra, although they are widely employed as a pattern recognition technique. Problems analogous to NIR identification have already been solved by means of non-supervised neural networks. Their main advantages are the ability to learn from examples as well as the processing speed, once they are trained. We present in this work a preliminary study of a non-supervised classifier built using Kohonen self-organising maps (SOM). The result is a model useful for identification of a group of NIR spectra belonging to 15 pure products. The accuracy of the classification is discussed. The generalisation of the method for more complex data is still an open issue.

Rapid Determining Contents of the Rhubarb Anthraquinones Compounds by Support Vector Machines Modeling based on Near Infrared Spectra

2020 ◽  
Vol 16 ◽  
Author(s):  
Linqi Liu ◽  
JInhua Luo ◽  
Chenxi Zhao ◽  
Bingxue Zhang ◽  
Wei Fan ◽  
...  
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Mean Squared Error ◽  
Rapid Determination ◽  
Partial Least Square ◽  
Least Square ◽  
Support Vector ◽  
Near Infrared Spectra ◽  
Aloe Emodin ◽  
Relative Differences

BACKGROUND: Measuring medicinal compounds to evaluate their quality and efficacy has been recognized as a useful approach in treatment. Rhubarb anthraquinones compounds (mainly including aloe-emodin, rhein, emodin, chrysophanol and physcion) are its main effective components as purgating drug. In the current Chinese Pharmacopoeia, the total anthraquinones content is designated as its quantitative quality and control index while the content of each compound has not been specified. METHODS: On the basis of forty rhubarb samples, the correlation models between the near infrared spectra and UPLC analysis data were constructed using support vector machine (SVM) and partial least square (PLS) methods according to Kennard and Stone algorithm for dividing the calibration/prediction datasets. Good models mean they have high correlation coefficients (R2) and low root mean squared error of prediction (RMSEP) values. RESULTS: The models constructed by SVM have much better performance than those by PLS methods. The SVM models have high R2 of 0.8951, 0.9738, 0.9849, 0.9779, 0.9411 and 0.9862 that correspond to aloe-emodin, rhein, emodin, chrysophanol, physcion and total anthraquinones contents, respectively. The corresponding RMSEPs are 0.3592, 0.4182, 0.4508, 0.7121, 0.8365 and 1.7910, respectively. 75% of the predicted results have relative differences being lower than 10%. As for rhein and total anthraquinones, all of the predicted results have relative differences being lower than 10%. CONCLUSION: The nonlinear models constructed by SVM showed good performances with predicted values close to the experimental values. This can perform the rapid determination of the main medicinal ingredients in rhubarb medicinal materials.

Discrimination of transgenic tomatoes based on visible/near-infrared spectra

2007 ◽  
Vol 584 (2) ◽  
pp. 379-384 ◽  
Author(s):  
Lijuan Xie ◽  
Yibin Ying ◽  
Tiejin Ying ◽  
Haiyan Yu ◽  
Xiaping Fu
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Near Infrared Spectra ◽  
Transgenic Tomatoes

Mid and near Infrared Study of Carbohydrates by Canonical Correlation Analysis

1993 ◽  
Vol 1 (2) ◽  
pp. 99-108 ◽  
Author(s):  
P. Robert ◽  
M.F. Devaux ◽  
A. Qannari ◽  
M. Safar
Keyword(s):  
Correlation Analysis ◽  
Infrared Spectra ◽  
Canonical Correlation ◽  
Near Infrared ◽  
Sugar Content ◽  
Infrared Region ◽  
Total Sugar ◽  
Mid Infrared ◽  
Total Sugar Content ◽  
Near Infrared Spectra

Multivariate data treatments were applied to mid and near infrared spectra of glucose, fructose and sucrose solutions in order to specify near infrared frequencies that characterise each carbohydrate. As a first step, the mid and near infrared regions were separately studied by performing Principal Component Analyses. While glucose, fructose and sucrose could be clearly identified on the similarity maps derived from the mid infrared spectra, only the total sugar content of the solutions was observed when using the near infrared region. Characteristic wavelengths of the total sugar content were found at 2118, 2270 and 2324 nm. In a second step, the mid and near infrared regions were jointly studied by a Canonical Correlation Analysis. As the assignments of frequencies are generally well known in the mid infrared region, it should be useful to study the relationships between the two infrared regions. Thus, the canonical patterns obtained from the near infrared spectra revealed wavelengths that characterised each carbohydrate. The OH and CH combination bands were observed at: 2088 and 2332 nm for glucose, 2134 and 2252 nm for fructose, 2058 and 2278 nm for sucrose. Although a precise assignment of the near infrared bands to chemical groups within the molecules was not possible, the present work showed that near infrared spectra of carbohydrates presented specific features.

Analysis of the near-infrared spectra of C60−

1995 ◽  
Vol 247 (1-2) ◽  
pp. 57-62 ◽  
Author(s):  
Robert D. Bolskar ◽  
Sean H. Gallagher ◽  
Robert S. Armstrong ◽  
Peter A. Lay ◽  
Christopher A. Reed
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Near Infrared Spectra
Sign in / Sign up

Export Citation Format

Share Document