Journal of Chemometrics
Công bố khoa học tiêu biểu
Sắp xếp:
Multi‐way prediction in the presence of uncalibrated interferents Abstract The second‐order advantage states that predictions are possible for new samples even if they contain new interferents not taken into account in the calibration model. Traditionally generalised rank annihilation has been widely used for second‐order calibration, but alternative models and algorithms such as PARAFAC is known to often be more accurate when many samples are available. While the calibration step of second‐order calibration has received considerable attention in the literature, the procedure of how to predict has not been investigated in detail when PARAFAC is used. In this paper we test the second‐order advantage using different calibration approaches based on PARAFAC with both simulated and real datasets, focussing on prediction quality as a function of the size of the calibration set, the number and degree of overlap of new interferents and the type and magnitude of noise. Guidelines are given on how to implement predictions in PARAFAC‐based second‐order calibration. Copyright © 2007 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 21 Số 1-2 - Trang 76-86 - 2007
Recent developments of chemical multiway calibration methodologies with second‐order or higher‐order advantages Developments in chemical multiway calibration methodologies in chemometrics that have taken place in tune with advances in modern (hyphenated) analytical instrumentation have been reviewed in this article. These advances in the ability to predict the concentration of an analyte using information‐rich data collected from such instruments are outstanding examples of the philosophy of analytical method development outlined by Bruce R. Kowalski more than three decades ago. With the increase in the complexity of analytical objects, sophistication in analytical instrumentation has also been enhanced. Chemometrics classifies analytical instruments as zeroth‐order, first‐order, second‐order, and higher‐order according to the order of data that the instrument produces. Different multiway calibration methodologies have been developed to calibrate the instrument and predict the concentration of analytes. In this review, select works of Kowalski and co‐workers in the context of second‐order calibrations, as well as other recent developments in multiway calibration, especially the three‐way and four‐way calibrations, which preserve the second‐order or high‐order advantages, are highlighted. Copyright © 2013 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 28 Số 5 - Trang 476-489 - 2014
Comparative study of Box–Behnken, central composite, and Doehlert matrix for multivariate optimization of Pb (II) adsorption onto <i>Robinia</i> tree leaves A comparative study of Box–Behnken, central composite, and Doehlert matrix was performed on the adsorption of Pb (II) by Robinia tree leaves in a batch system. As a case study, uptake capacity (q ) and removal efficiency (R ) of Pb (II) biosorption have been evaluated with all theses approaches. The advantages and limitations of these different response surface techniques have been experimentally considered. The results show the different statistical predictability of Doehlert matrix and Box–Behnken design at 95% confidence level comparable with some extent with that of central composite design at some extreme conditions. An environmental and economical comparison was also carried out between individual and simultaneous optimization of removal efficiency (R ) and uptake capacity (q ) using desirability function. Optimization of q proves only to have advantages over R or simultaneous optimization of R and q in this particular biosorption process. Copyright © 2013 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 27 Số 1-2 - Trang 12-20 - 2013
Partial least squares discriminant analysis: taking the magic away Partial least squares discriminant analysis (PLS‐DA) has been available for nearly 20 years yet is poorly understood by most users. By simple examples, it is shown graphically and algebraically that for two equal class sizes, PLS‐DA using one partial least squares (PLS) component provides equivalent classification results to Euclidean distance to centroids, and by using all nonzero components to linear discriminant analysis. Extensions where there are unequal class sizes and more than two classes are discussed including common pitfalls and dilemmas. Finally, the problems of overfitting and PLS scores plots are discussed. It is concluded that for classification purposes, PLS‐DA has no significant advantages over traditional procedures and is an algorithm full of dangers. It should not be viewed as a single integrated method but as step in a full classification procedure. However, despite these limitations, PLS‐DA can provide good insight into the causes of discrimination via weights and loadings, which gives it a unique role in exploratory data analysis, for example in metabolomics via visualisation of significant variables such as metabolites or spectroscopic peaks. Copyright © 2014 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 28 Số 4 - Trang 213-225 - 2014
Multilevel component analysis and multilevel PLS of chemical process data Abstract Principal component analysis (PCA) and partial least squares (PLS) are well‐established techniques for analyzing multivariate process data. However, chemical processes often vary at different levels, due to, for instance, catalyst deactivation or fouling. In such cases, data from a time period that comprises multiple catalyst or fouling runs contain both variation within runs at the lower level and variation between runs at the higher level. In ordinary PCA and PLS models, these sources of variation are confounded. Multiway PCA and PLS are usually not appropriate either, because the runs in the data set can be very different, which means that the overall data set does not have a proper multiway structure. Multilevel component analysis (MLCA) and multilevel partial least squares (MLPLS) are proposed as better options for analyzing such process data. The models obtained with these techniques contain submodels for the different levels in the data, and thereby separate the within‐run and between‐run variation in the process variables (X ). In addition, MLPLS can use response variables (Y ) to guide the projections into meaningful directions, and provide information on the sources of variation in Y and the relationship between X and Y . Extensions to more than two levels are straightforward, and can be used, for instance, for the comparison of runs from different plants. Copyright © 2006 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 19 Số 5-7 - Trang 301-307 - 2005
Multivariate dynamic data modeling for analysis and statistical process control of batch processes, start‐ups and grade transitions
Journal of Chemometrics - Tập 17 Số 1 - Trang 93-109 - 2003
Univariate regression models with errors in both axes Abstract Calibration is a fundamental step in the calculation of the unknown concentration of analyte in most analytical methods. It is known that for certain methodologies, if only the errors in the independent variable are taken into account, there may be considerable errors in the estimation of the value of the regression coefficients, the derived statistical parameters and in some cases the sought for response and concentration values. This paper reviews the calibration methods including some references to procedures for the detection of outliers and robust regression when there are errors in both axes. The advantages and limitations of the different approaches are discussed and a comparative study is made of the approaches of several techniques for which computer programmes have been developed based on the algorithms put forward by the different authors. Finally, some trends of future development in this field are envisaged.
Journal of Chemometrics - Tập 9 Số 5 - Trang 343-362 - 1995
Process analytical technology: a critical view of the chemometricians The role of chemometrics in process analytical technology (PAT) solutions development is presented in the review on the basis of publications from 1993 to 2011. Main areas of application, stages of implementation, instruments, and chemometric methods used for the PAT implementations are reviewed. Generally speaking, PAT is considered to be an approach applicable not only in pharmaceutical industry but also in any production area such as food industry and biotechnology. PAT is claimed to be a new flexible manufacturing concept that accounts for variability and adapts the process to fit it. Copyright © 2012 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 26 Số 6 - Trang 299-310 - 2012
Harnessing the complexity of metabolomic data with chemometrics Because of the ever‐increasing number of signals that can be measured within a single run by modern platforms in analytical chemistry, life sciences datasets become not only gradually larger but also more intricate in their structures. Challenges related to making use of this wealth of data include extracting relevant elements within massive amounts of signals possibly spread across different tables, reducing dimensionality, summarising dynamic information in a comprehensible way and displaying it for interpretation purposes. Metabolomics constitutes a representative example of fast‐moving research fields taking advantage of recent technological advances to provide extensive sample monitoring. Because of the wide chemical diversity of metabolites, several analytical setups are required to provide a broad coverage of complex samples. The integration and visualisation of multiple highly multivariate datasets constitute key issues for effective analysis leading to valuable biological or chemical knowledge. Additionally, high‐order data structures arise from experimental setups involving time‐resolved measurements. These data are intrinsically multiway, and classical statistical tools cannot be applied without altering their organisation with the risk of information loss. Dedicated modelling algorithms, able to cope with the inherent properties of these metabolomic datasets, are therefore mandatory for harnessing their complexity and provide relevant information. In that perspective, chemometrics has a central role to play. Copyright © 2013 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 28 Số 1 - Trang 1-9 - 2014
A chemometrics toolbox based on projections and latent variables A personal view is given about the gradual development of projection methods—also called bilinear, latent variable, and more—and their use in chemometrics. We start with the principal components analysis (PCA) being the basis for more elaborate methods for more complex problems such as soft independent modeling of class analogy, partial least squares (PLS), hierarchical PCA and PLS, PLS‐discriminant analysis, Orthogonal projection to latent structures (OPLS), OPLS‐discriminant analysis and more. From its start around 1970, this development was strongly influenced by Bruce Kowalski and his group in Seattle, and his realization that the multidimensional data profiles emerging from spectrometers, chromatographs, and other electronic instruments, contained interesting information that was not recognized by the current one variable at a time approaches to chemical data analysis. This led to the adoption of what in statistics is called the data analytical approach, often called also the data driven approach, soft modeling, and more. This approach combined with PCA and later PLS, turned out to work very well in the analysis of chemical data. This because of the close correspondence between, on the one hand, the matrix decomposition at the heart of PCA and PLS and, on the other hand, the analogy concept on which so much of chemical theory and experimentation are based. This extends to numerical and conceptual stability and good approximation properties of these models. The development is informally summarized and described and illustrated by a few examples and anecdotes. Copyright © 2014 John Wiley & Sons, Ltd.
Journal of Chemometrics - Tập 28 Số 5 - Trang 332-346 - 2014
Tổng số: 23
- 1
- 2
- 3