Screening oil spills by mid-IR spectroscopy and supervised pattern recognition techniques

Gómez-Carracedo, M.P.; Fernández-Varela, R.; Ballabio, Davide; Andrade, J.M.

doi:10.1016/j.chemolab.2012.03.013

Cited by 21 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Soft independent modeling of class analogies is a commonly used supervised classification method . This technique of pattern recognition describes q samples of different classes based on the classification rules using the principal component analysis for each class.…”

Section: Methodsmentioning

confidence: 99%

Quality control of fragrances using Raman spectroscopy and multivariate analysis

Santos¹,

Poppi

2015

J Raman Spectroscopy

View full text Add to dashboard Cite

An analytical methodology using Raman spectroscopy and chemometrics was developed for direct, fast and non‐destructive discrimination and prediction of the properties of fragrances according to their composition. The soft independent modeling of class analogies was used as a supervised classification method for fragrances classification, and partial least squares regression as a multivariate calibration method for the prediction of physicochemical properties of fragrances, such as density and refractive index. From 155 fragrance samples, the model exhibited a high success rate for all of the studied fragrance classes, with 100% correct classification. In the multivariate calibration model, adequate correlation was observed between the measured and partial least squares regression‐predicted data for refractive index and density, with a relative standard error of prediction between 0.02% and 0.07%, respectively. This study demonstrates the wide applicability of the methodology for the discrimination, classification, and prediction of complex olfactory mixtures in quality control of fragrances. Copyright © 2015 John Wiley & Sons, Ltd.

show abstract

Section: Methodsmentioning

confidence: 99%

Quality control of fragrances using Raman spectroscopy and multivariate analysis

Santos¹,

Poppi

2015

J Raman Spectroscopy

View full text Add to dashboard Cite

show abstract

“…The optimal hyperplane is established based on nonlinear kernel function, and the margin of two sides is kept maximum. In this sense, SVM is the calculation of binary classification . Here, the calculation kernel is a symmetric function φ that maps K : X × X → F , and for all x i and x j , K ( x i , x j ) = { φ ( x i ), φ ( x j )}, which can transform the input space X into the feature space F , as shown in Fig.…”

Section: Proposed Svm Methods Of Color Recognitionmentioning

confidence: 99%

“…In fact, there are no real parallel algorithms. The current research on algorithms, for example, One Versus Rest, One Versus Another, Directed Acyclic Graph SVM, focus on how to change multiclass recognition into binary recognition . Here, we use the idea of One Versus Rest, as shown in the following.…”

Section: Proposed Svm Methods Of Color Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

A novel analysis of color component for top dyed melange yarn with support vector machine

Shen

Chen

et al. 2015

Color Research & Application

View full text Add to dashboard Cite

In view of the difficulty of distinguishing the color component in top dyed melange yarn due to the spectral overlap of the component colors, a novel color component analysis method based on support vector machine is presented. With this method, spectra data can be distinguished more accurately and effectively than with the traditional method-human-eye detection-and therefore, the method will be very helpful for accurate color matching. In our work, the core idea was to convert the overlapped spectra data into linearly separable ones in a high dimension space, followed by recognition and determination of the composition of melange yarn by trained support vector machine classifier. The effects of four kernel functions, i.e., linear, radial basis kernel, sigmoid, and polynomial, as well as five spectral preprocessing methods, including amplification, first derivative, second derivative, principal components analysis, and L*a*b* values were studied. The results demonstrated that with the amplification factor of 100 of reflectance spectra coupled with L*a*b* as input data, and using radial basis kernel as kernel function, the highest recognition rate was achieved, with an average recognition rate of eight colors of 96.5%, indicating that it was a better color component analysis method for top dyed melange yarn.

show abstract

“…Other applications have been reported using different classification algorithms to authenticate and identify the geographic origin of chemical samples collected at different locations. In this approach to geographical classification [13][14][15][16][17][18][19][20][21][22], chemical measurements made on a set of training samples with known geographical regions are used to build a classification model, which is capable of predicting the geographical regions of new samples. It is also possible to predict a general location or to identify a set of target variables that are location relevant from chemical measurements or spectral information using regression analysis by partial least squares (PLS) [23][24][25][26][27], by a spatial regression analysis such as kriging, by a geographically weighted regression, or by Bayesian inference using Gibbs sampling [28][29][30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

Use of a tree‐structured hierarchical model for estimation of location and uncertainty in multivariate spatial data

Chen

Brown

2014

Journal of Chemometrics

View full text Add to dashboard Cite

Analysis and modeling of spatial data are of considerable interest in many applications. However, the prediction of geographical features from a set of chemical measurements on a set of geographically distinct samples has never been explored. We report a new, tree‐structured hierarchical model for the estimation of geographical location of spatially distributed samples from their chemical measurements. The tree‐structured hierarchical modeling used in this study involves a set of geographic regions stored in a hierarchical tree structure, with each nonterminal node representing a classifier and each terminal node representing a regression model. Once the tree‐structured model is constructed, given a sample with only chemical measurements available, the predicted regional location of the sample is gradually restricted as it is passed through a series of classification steps. The geographic location of the sample can be predicted using a regression model within the terminal subregion. We show that the tree‐structured modeling approach provides reasonable estimates of geographical region and geographic location for surface water samples taken across the entire USA. Further, the location uncertainty, an estimate of a probability that a test sample could be located within a pre‐estimated, joint prediction interval that is much smaller than the terminal subregion, can also be assessed. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Screening oil spills by mid-IR spectroscopy and supervised pattern recognition techniques

Cited by 21 publications

References 33 publications

Quality control of fragrances using Raman spectroscopy and multivariate analysis

Quality control of fragrances using Raman spectroscopy and multivariate analysis

A novel analysis of color component for top dyed melange yarn with support vector machine

Use of a tree‐structured hierarchical model for estimation of location and uncertainty in multivariate spatial data

Contact Info

Product

Resources

About