Search results for "Principal component regression"

showing 10 items of 14 documents

Multivariate standardisation for non-linear calibration range in the chemiluminescence determination of chromium.

2006

Multivariate standardisation is proposed for the successful chemiluminescence determination of chromium based on luminol-hydrogen peroxide reaction. In an extended concentration range, non-linear calibration model is needed. The studied instrumental situations were different detection cells, instruments, assemblies, time and their possible combinations. Chemiluminescence kinetic registers have been transferred using piecewise direct standardisation (PDS) method. The optimisation of transfer parameters has been carried out based on the prediction residual error criteria. Non-linear principal component regression (NL-PCR) and non-linear partial least square regression (NL-PLS) were chosen for…

Accuracy and precisionMultivariate statisticsChemistrylawDirect methodPartial least squares regressionLinear regressionCalibrationAnalytical chemistryPrincipal component regressionAnalytical ChemistryChemiluminescencelaw.inventionTalanta
researchProduct

Reproducing kernel hilbert spaces regression methods for genomic assisted prediction of quantitative traits.

2008

Abstract Reproducing kernel Hilbert spaces regression procedures for prediction of total genetic value for quantitative traits, which make use of phenotypic and genomic data simultaneously, are discussed from a theoretical perspective. It is argued that a nonparametric treatment may be needed for capturing the multiple and complex interactions potentially arising in whole-genome models, i.e., those based on thousands of single-nucleotide polymorphism (SNP) markers. After a review of reproducing kernel Hilbert spaces regression, it is shown that the statistical specification admits a standard mixed-effects linear model representation, with smoothing parameters treated as variance components.…

BiologyInvestigationsBayesian inferenceMachine learningcomputer.software_genreKernel principal component analysisChromosomessymbols.namesakeQuantitative Trait HeritableGeneticsAnimalsGeneticsGenomeModels GeneticRepresenter theorembusiness.industryHilbert spaceLinear modelBayes TheoremQuantitative Biology::GenomicsKernel embedding of distributionsKernel (statistics)symbolsPrincipal component regressionRegression AnalysisArtificial intelligencebusinesscomputerChickensGenetics
researchProduct

Analysis of enantiomers giving partially overlapped peaks by using different treatments of the chromatographic ultraviolet signals: quantification of…

2001

Abstract Different strategies for the quantification of partially coeluting optical isomers have been investigated. The methods tested are based on the use of different features as the analytical UV signals: peak heights, perpendicular drop areas, first and second derivatives of the chromatograms, peak areas obtained by deconvolution of the overlapped peaks with data fitting optimization, and a multivariate model (principal component regression, PCR). The amphetamine-derivative drug pseudoephedrine was selected as a model compound. For chromatography, LiChrospher 100 RP 18 and a mobile-phase consisting of methanol and a solution of carboxymethyl-β-cyclodextrin (the chiral selector) were use…

EphedrineChromatographyChemistryOrganic ChemistryAnalytical chemistryStereoisomerismGeneral MedicineReversed-phase chromatographyBiochemistryHigh-performance liquid chromatographyAnalytical ChemistryNasal decongestantPrincipal component analysisCurve fittingPrincipal component regressionSpectrophotometry UltravioletEnantiomerSecond derivativeJournal of Chromatography A
researchProduct

Multivariate versus univariate calibration for nonlinear chemiluminescence data

2001

Abstract Multivariate calibration is tested as an alternative to model chromium(III) concentration versus chemiluminescence registers obtained from luminol-hydrogen peroxide reaction. The multivariate calibration approaches included have been: conventional linear methods (principal component regression (PCR) and partial least squares (PLS)), nonlinear methods (nonlinear variants and variants of locally weighted regression) and linear methods combined with variable selection performed in the original or in the transformed data (stepwise multiple linear regression procedure). Both the direct and inverse univariate approaches have been also tested. The use of a double logarithmic transformatio…

General linear modelMultivariate statisticsChemistryLocal regressionBiochemistryAnalytical ChemistryBayesian multivariate linear regressionStatisticsLinear regressionPartial least squares regressionEnvironmental ChemistryPrincipal component regressionBiological systemNonlinear regressionSpectroscopyAnalytica Chimica Acta
researchProduct

Semisupervised nonlinear feature extraction for image classification

2012

Feature extraction is of paramount importance for an accurate classification of remote sensing images. Techniques based on data transformations are widely used in this context. However, linear feature extraction algorithms, such as the principal component analysis and partial least squares, can address this problem in a suboptimal way because the data relations are often nonlinear. Kernel methods may alleviate this problem only when the structure of the data manifold is properly captured. However, this is difficult to achieve when small-size training sets are available. In these cases, exploiting the information contained in unlabeled samples together with the available training data can si…

Graph kernelComputer scienceFeature extractioncomputer.software_genreKernel principal component analysisk-nearest neighbors algorithmKernel (linear algebra)Polynomial kernelPartial least squares regressionLeast squares support vector machineCluster analysisTraining setContextual image classificationbusiness.industryDimensionality reductionPattern recognitionManifoldKernel methodKernel embedding of distributionsKernel (statistics)Principal component analysisRadial basis function kernelPrincipal component regressionData miningArtificial intelligencebusinesscomputer2012 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

Chemometric investigation on structural changes in pine kraft lignin during pulping

2000

Abstract Various structural changes which take place in dissolved lignin during the laboratory-scale kraft pulping of Scots pine (Pinus sylvestris) were studied. Lignin samples were subjected to the alkaline cupric oxide oxidation and the analytical data further processed by various multivariate chemometric techniques (principal component analysis, PCA; principal component regression, PCR; and projection to latent structures, PLS). Several models applicable to the indirect measurement of common pine kraft pulp properties (i.e., total cooking yield, kappa number and ISO brightness) were produced.

Kraft ligninbiologyChemistryProcess Chemistry and TechnologyfungiScots pinefood and beveragesKappa numberPulp and paper industrybiology.organism_classificationcomplex mixturesComputer Science ApplicationsAnalytical ChemistryPinus <genus>chemistry.chemical_compoundKraft processPrincipal component analysisPrincipal component regressionLigninSpectroscopySoftwareChemometrics and Intelligent Laboratory Systems
researchProduct

Comparison of different predictive models for nutrient estimation in a sequencing batch reactor for wastewater treatment

2006

Abstract In this paper different predictive models for nutrient estimation in a sequencing batch reactor (SBR) for wastewater treatment are compared: principal component regression (PCR), partial least squares (PLS), and artificial neural networks (ANNs). Two unfolding procedures were used: batch-wise and variable-wise. For the latter unfolding method, X and Y matrix augmentation with lagged variables were used in some models to incorporate process dynamics. The results have shown that batch-wise unfolding PLS models outperform the other approaches. The ANN models are good predictive models, but in this particular case-study, they do not outperform those multivariate projection models that …

Multivariate statisticsArtificial neural networkbusiness.industryComputer scienceProcess Chemistry and TechnologySequencing batch reactorSoft sensorMachine learningcomputer.software_genreMissing dataComputer Science ApplicationsAnalytical ChemistryPartial least squares regressionPrincipal component regressionArtificial intelligenceData miningbusinesscomputerModel buildingSpectroscopySoftwareChemometrics and Intelligent Laboratory Systems
researchProduct

A spectroscopic method for determining lignin content of softwood and hardwood kraft pulps

1998

Abstract A rapid method for determining the kappa number of unbleached and oxygen-delignified kraft pulps in the range 3–35 is presented. This novel method was based on the multivariate analysis of VIS spectral data on pulp samples. The calculated models and the test results indicated that partial least squares (PLS) and principal component regression (PCR) models yielded similar results, PLS being slightly more accurate. It was also found that for practical purposes a separate model for each wood feedstock and delignification process is needed.

SoftwoodChemistryProcess Chemistry and TechnologyPulp (paper)engineering.materialKappa numberPulp and paper industryComputer Science ApplicationsAnalytical ChemistryKraft processPartial least squares regressionHardwoodengineeringPrincipal component regressionSpectroscopySoftwareKraft paperChemometrics and Intelligent Laboratory Systems
researchProduct

Simulation in the Simple Linear Regression Model

2002

Summary This article presents an activity which simulates the linear regression model in order to verify the probabilistic behaviour of the resulting least-squares statistics in practice.

Statistics and ProbabilityPolynomial regressionGeneral linear modelProper linear modelMultivariate adaptive regression splinesComputer scienceStatisticsLinear modelApplied mathematicsPrincipal component regressionLog-linear modelSimple linear regressionEducationTeaching Statistics
researchProduct

Linear and ellipsoidal restrictions in linear regression

1991

The problem of combining linear and ellipsoidal restrictions in linear regression is investigated. Necessary and sufficient conditions for compactness of the restriction set are proved assuring the existence of a minimax estimator. When the restriction set is not compact a minimax estimator may still exist for special loss functions arid regression designs

Statistics and ProbabilityPolynomial regressionStatistics::TheoryMathematical optimizationProper linear modelLinear predictor functionBayesian multivariate linear regressionLinear regressionLinear modelPrincipal component regressionStatistics Probability and UncertaintySimple linear regressionMathematicsStatistics
researchProduct