Application of PLS multivariate calibration for the determination of the hydroxyl group content in calcined silica by DRIFTS

Peussa, Marko; Hrknen, Satu; Puputti, Janne; Niinist�, Lauri

doi:10.1002/1099-128x(200009/12)14:5/6<501::aid-cem613>3.0.co;2-m

Cited by 12 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a comparative study of Time-Linear Regression (LR), Polynomial Regression (PR)31, Support Vector Regression (SVR)323334, Artificial Neural Networks (ANN)353637 and Partial Least Squares Regression (PLSR)3839 methods which are applied in a real data set of the drug efficacy of Wuji pill, our framework demonstrates the superiority.…”

mentioning

confidence: 98%

A novel multi-target regression framework for time-series prediction of drug efficacy

Zhang

Chen

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Excavating from small samples is a challenging pharmacokinetic problem, where statistical methods can be applied. Pharmacokinetic data is special due to the small samples of high dimensionality, which makes it difficult to adopt conventional methods to predict the efficacy of traditional Chinese medicine (TCM) prescription. The main purpose of our study is to obtain some knowledge of the correlation in TCM prescription. Here, a novel method named Multi-target Regression Framework to deal with the problem of efficacy prediction is proposed. We employ the correlation between the values of different time sequences and add predictive targets of previous time as features to predict the value of current time. Several experiments are conducted to test the validity of our method and the results of leave-one-out cross-validation clearly manifest the competitiveness of our framework. Compared with linear regression, artificial neural networks, and partial least squares, support vector regression combined with our framework demonstrates the best performance, and appears to be more suitable for this task.

show abstract

mentioning

confidence: 98%

A novel multi-target regression framework for time-series prediction of drug efficacy

Zhang

Chen

et al. 2017

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Both the calcite and olomite are characterised by the strong absorption bands due to the asymmetric stretching vibrations of the between 1540 and 1400 cm et al, 1995). The silicates spectra are characterised by Si-O stretching and bending vibrations between 1200 and 800 cm phyllosilicates can be separated from the tectosilicates based on the occurrence of the O-H stretch vibrations at 3750 to 3400cm (Peussa et al, 2000;Hughes et al, 1995) The ability of the model to successfully predict the concentration of each mineral standard in the validation set and rock samples is represented in Fig 2. The figure shows the model output obtained from Pirouette software showing the correlation nts (rCal) and includes the number of factors used (at the right end of the measured Y). For example, four factors were used to obtain a correlation coefficient of 0.994.…”

Section: Resultsmentioning

confidence: 99%

“…(Hughes et al, 1995) applied Partial Least Squares (PLS) algorithms to DRIFT spectra to Portland cement and were able to describe up to 14 components with adequate accuracy. In another study, (Janik and Skjemstand, 1995) combined PLS and DRIFTS for the successful analysis of tubular halloysite in kaoline samples, whilst (Peussa et al, 2000) were able to determine, with sufficient accuracy, the hydroxyl group content in calcined silica thus removing that dependence on time consuming thermo-gravimetric analysis. In CLS computation, the complex relationship between a very large number of X independent variables and dependent Y variables is compressed into a small number of linear combinations of the original X variables, and only those components are used in the calibration (Naes et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

Fourier Transform Infrared Spectroscopic Determination of Shale Minerals in Reservoir Rocks

Adamu¹

2010

Nig J Bas App Sci

View full text Add to dashboard Cite

Attenuated Total Reflectance Fourier transform infrared spectroscopy together with multivariate statistical regression was used to produce calibrations between spectra of standard mineral mixtures and gas shale reservoir rocks. A Classical Least Square (CLS) model was developed from the attenuated spectra of mixtures of five mineral standards chosen to represent the most frequently encountered minerals in shale-type reservoir rocks namely: quartz, illite/smectite (30:70), kaolinite, calcite and dolomite. The CLS model developed was able to quantify the mineral components of independent mixtures with an absolute error between 1 to 3wt% for all the pure minerals in the mixtures. Samples from a suite of shale reservoir rocks were analysed using standard Quantitative X-Ray Diffraction (QXRD) and with FTIR. Unknown mineral concentrations in the samples were then predicted using spectra and the calibration equations. Good correlations were achieved between the QXRD and ATR-CLS predicted concentrations (r 2 >0.8), with average absolute error of between 1 to 6wt%. This provides evidence that attenuated FTIR is a promising method for rapid and accurate determination of minerals in reservoir rocks for building higher resolution data without additional time consuming and expensive traditional analyses.

show abstract

“…Partial least squares (PLS) as a popular chemometrics algorithm has been used in NIR research and application for decades (Peussa et al 2000;Rohe et al 1999). Our process of building a PLS calibration model was carried out in the conventional leave-one-out cross-validation way.…”

Section: Chemometrics Modelmentioning

confidence: 99%

Studying the uptake of aniline vapor by active alumina through in-line monitoring a differential adsorption bed with near-infrared diffuse reflectance spectroscopy

et al. 2008

View full text Add to dashboard Cite

Through non-invasive monitoring the uptake of aniline vapor by active alumina in a differential adsorption bed (DAB) with near-infrared diffuse reflectance spectroscopy (NIR-DRS), we have studied several features of the adsorption, including isotherm, kinetics and the chemical state of aniline molecules in aniline-alumina system. What is perhaps more important, since the information above is obtained synchronously, the proposed methodology could provide information about the type of adsorption (chemical or physical adsorption), the change of chemical state of aniline in the system during the adsorption process, whether the chemical adsorption and physical adsorption took place simultaneously, the rate of the chemical and physical adsorption, and so on.

show abstract

Application of PLS multivariate calibration for the determination of the hydroxyl group content in calcined silica by DRIFTS

Cited by 12 publications

References 9 publications

A novel multi-target regression framework for time-series prediction of drug efficacy

A novel multi-target regression framework for time-series prediction of drug efficacy

Fourier Transform Infrared Spectroscopic Determination of Shale Minerals in Reservoir Rocks

Studying the uptake of aniline vapor by active alumina through in-line monitoring a differential adsorption bed with near-infrared diffuse reflectance spectroscopy

Contact Info

Product

Resources

About