Search results for "Partial Least Squares Regression"
showing 10 items of 122 documents
Multivariate data analysis of quality parameters in drinking water.
2001
The quality of water destined for human consumption has been treated as a multivariate property. Since most of the quality parameters are obtained by applying analytical methods, the routine analytical laboratory (responsible for the accuracy of analytical data) has been treated as a process system for water quality estimation. Multivariate tools, based on principal component analysis (PCA) and partial least squares (PLS) regression, are used in the present paper to: (i) study the main factors of the latent data structure and (ii) characterize the water samples and the analytical methods in terms of multivariate quality control (MQC). Such tools could warn of both possible health risks rela…
Comparison of two partial least squares infrared spectrometric methods for the quality control of pediculosis lotions.
2006
Two vibrational spectroscopy procedures have been developed and compared for the direct and simultaneous determination of piperonyl butoxide and tetramethrin, the active ingredients of alcoholic capillary lotions, for hair pediculosis diseases. Nine lotions, purchased from the Spanish market, were analyzed using both, attenuated total reflectance (ATR) and transmission FT-IR measurements, and based on the use of partial least squares (PLS) multivariate calibration. A reduced set of 15 matched standards (11 for calibration and 4 for validation) was employed using both measurement modes. The spectral wave number ranges between 1757 and 1712 cm(-1) was selected to determine tetramethrin by bot…
Chromatographic multivariate quality control of pharmaceuticals giving strongly overlapped peaks based on the chromatogram profile
2004
In the present paper, the simultaneous quantification of two analytes showing strongly overlapped chromatographic peaks (alpha = 1.02), under the assumption that both available equipment and training of the laboratory staff are basic, is studied. A pharmaceutical preparation (Mutabase) containing two drugs of similar physicochemical properties (amitriptyline and perphenazine) is selected as case of study. The assays are carried out under realistic working conditions (i.e. routine testing laboratories). Uncertainty considerations are introduced in the study. A partial least squares model is directly applied to the chromatographic data (with no previous signal transformation) to perform quali…
Polarity study of ionic liquids with the solvatochromic dye Nile Red: a QSPR approach using in silico VolSurf+ descriptors
2016
The in silico VolSurfþ descriptors, accounting for both cationic and anionic structural features of ionic liquids (ILs) were used to develop a Partial Least Squares (PLS) model able to establish a Quantitative Structure Property Relationship (QSPR) correlation with their solvatochromic dye Nile Red polarity. The PLS model allowed prediction of ENR values for 116 ILs providing an in silico ILs polarity database.
Application of the modelling power approach to variable subset selection for GA-PLS QSAR models
2007
A previously developed function, the Modelling Power Plot, has been applied to QSARs developed using partial least squares (PLS) following variable selection from a genetic algorithm (GA). Modelling power (Mp) integrates the predictive and descriptive capabilities of a QSAR. With regard to QSARs for narcotic toxic potency, Mp was able to guide the optimal selection of variables using a GA. The results emphasise the importance of Mp to assess the success of the variable selection and that techniques such as PLS are more robust following variable selection.
Prediction of ionic liquid's heat capacity by means of their in silico principal properties
2016
The in silico principal properties (PPs) of ionic liquids (ILs), derived by means of the VolSurf+ approach, were used to develop a Partial Least Squares (PLS) model able to find a quantitative correlation among IL descriptors (accounting for both cationic and anionic structural features) and heat capacity values, providing affordable predictions validated by experimental Cp measurements for an external set of ILs. In silico predictions allowed the selection of a limited number of structurally different ILs with similar Cp values, providing the possibility to select an optimal IL according to efficiency, as well as to environmental and economic sustainability. The present general procedure, …
Modeling the chiral resolution ability of highly sulfated β-cyclodextrin for basic compounds in electrokinetic chromatography
2013
Abstract Despite the fact that extensive research in the field of enantioseparations by capillary electrophoresis has been carried out, it is difficult to predict whether a concrete chiral selector would be useful for the separation of a racemic compound. Hence, several experimental effort is necessary to test the abilities of individual chiral selectors, usually by trial and error procedures. Thus, the enantioseparation of a new racemate becomes a time- and money-consuming task. In this work, the ability of highly sulfated β-cyclodextrin (HS-β-CD) as chiral selector in electrokinetic chromatography (EKC) is modeled for the first time, using exclusively directly-available structural data of…
Determination of the energetic value of fruit and milk-based beverages through partial-least-squares attenuated total reflectance-Fourier transform i…
2005
Abstract The estimation of important nutritional parameters, such as carbohydrates content and energetic value (calories) in commercially available fruit juice and flavour milk shakes has been made by attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) using a partial-least-square (PLS) calibration approach. A highly heterogeneous population of 65 samples obtained from the Spanish market, covering fruit juices, flavour milk shakes and milk-added fruit juices was used. The spectral range and the size of the calibration set for building the PLS model have been evaluated. Considering a calibration set comprised of 27 samples, selected via hierarchical cluster analys…
Estuarine sediment quality assessment by Fourier-transform infrared spectroscopy
2010
Partial least squares Fourier-transform infrared (PLS-FTIR) models were developed for the quality assessment of estuarine sediments through the evaluation of several physico-chemical parameters. Models were based on the chemometric treatment of attenuated total reflection (ATR) spectra directly obtained from samples previously lyophilized and sieved through a lower than 63 μm grid. Spectra were scanned from 3997 to 523 cm-1, averaging 36 scans per spectrum with a nominal resolution of 8 cm-1. Models were built using reference data obtained for sediment samples collected from Ria de Arousa estuary. Hierarchical cluster classification of sediment ATR spectra was employed for the establishment…
Value, supplier dependence and long‐term orientation
2011
PurposeIn organizational markets, many companies tend to reduce the number of providers to focus on establishing relationships with few of them. The purpose of this paper is to analyze the influence of relationship value and dependence of supplier on long‐term orientation and customer loyalty in the setting of relationships between travel agencies and their main providers.Design/methodology/approachA partial least square regression is performed to test a proposed model that links several relational variables with outcomes in terms of customer loyalty.FindingsResults provide support for the positive indirect influence of relationship value on long‐term orientation, while customer dependence …