### Contact Info

Stuart Chalk, Ph.D.

Department of Chemistry

University of North Florida

Phone: 1-904-620-1938

Fax: 1-904-620-3535

Email: schalk@unf.edu

Website: @unf

## Journal of Chemometrics

**Publisher:**Wiley**FAD Code:**JCHM**CODEN:**JOCHEU**ISSN:**0886-9383**Abbreviation:**J. Chemom.**DOI Prefix:**10.1002/cem**Language:**English**Comments:**Fulltext from 1987 V1

### Citations 8

**"Selecting Significant Factors By The Noise Addition Method In Principal Component Analysis"**

*J. Chemom.
2001 Volume 15, Issue 7 Pages 591-613*

Brian K. Dable, Karl S. Booksh

**Abstract:**The noise addition method (NAM) is presented as a tool for determining the number of significant factors in a data set. The NAM is compared to residual standard deviation (RSD), the factor indicator function (IND), chi-squared (χ2) and cross-validation (CV) for establishing the number of significant factors in three data sets. The comparison and validation of the NAM are performed through Monte Carlo simulations with noise distributions of varying standard deviation, HPLC/UV-vis chromatographs of a mixture of aromatic hydrocarbons, and FIA of methyl orange. The NAM succeeds in correctly identifying the proper number of significant factors 98% of the time with the simulated data, 99% in the HPLC data sets and 98% with the FIA data. RSD and χ2 fail to choose the proper number of factors in all three data sets. IND identifies the correct number of factors in the simulated data sets but fails with the HPLC and FIA data sets. Both CV methods fail in the HPLC and FIA data sets. CV. also fails for the simulated data sets, while the modified CV correctly chooses the proper number of factors an average of 80% of the time.

**"Least Squares Algorithms Under Unimodality And Non-negativity Constraints"**

*J. Chemom.
1998 Volume 12, Issue 4 Pages 223-247*

Rasmus Bro *, Nicholaos D. Sidiropoulos

**Abstract:**A least squares method is developed for minimizing .dblvert.Y-XBT.dblvert.2F over the matrix B subject to the constraint that the columns of B are unimodal, i.e. each has only one peak, and .dblvert.M.dblvert.2F being the sum of squares of all elements of M. This method is directly applicable in many curve resoln. problems, but also for stabilizing other problems where unimodality is known to be a valid assumption. Typical problems arise in certain types of time series anal. such as chromatography or flow injection analysis A fundamental and surprising result of this work is that unimodal least squares regression (including optimization of mode location) is not any more difficult than two simple Kruskal monotone regressions. This had not been realized earlier, leading to the use of either undesirable ad hoc methods or very time-consuming exhaustive search algorithms. The new method is useful in and exemplified with two- and multi-way methods based on alternating least squares regression solving problems from fluorescence spectroscopy and flow injection anal.

**"Multivariate Resolution Of Rank-deficient Spectrophotometric Data From First-order Kinetic Decomposition Reactions"**

*J. Chemom.
1998 Volume 12, Issue 3 Pages 183-203*

J. Saurina, S. Hernández-Cassou, R. Tauler*, A. Izquierdo-Ridorsa

**Abstract:**The effect of a rank deficiency upon curve resolution in simple kinetic reaction-based systems is studied. Firstly, simulated rank-deficient spectrophotometric data of a mixture of two reagents, each one yielding its own reaction product by a first-order kinetic reaction, are analyzed. Four different situations are considered according to the differences in the spectral responses of the reaction constituents and to the differences in the rate constants between the two kinetic processes. A variation of the rate constant between runs for a certain kinetic process is also taken into account. Secondly, the resolution of a real rank-deficient data system, corresponding to the study of the pH-dependent decomposition of 1,2-naphthoquinone-4-sulfonate, is investigated. All these studies were carried out using a multivariate curve resolution method based on the alternating least squares optimization of the kinetic and spectral profiles of the species present in the system.

**"Screening Method For Metals Based On Array Spectrophotometry And Multivariate-analysis"**

*J. Chemom.
1996 Volume 10, Issue 5-6 Pages 509-520*

Eva Engström, Bo Karlberg

**Abstract:**A rapid screening method for detection of heavy metals in aqueous samples has been developed. The method simply involves mixing the sample with a buffer containing the chelating agent PAR in volume proportion 1:1 and then measuring the absorbance of the mixture in the range 190-820 nm. Partial least squares modeling has been applied for prepared mixtures of the metal ions Cd2+, Cu2+, Pb2+ and Zn2+, and identification and quantification of individual metals could be made in the total concentration range 1-20 µM. Typical root mean square errors of prediction were of the order of 0.5 µM. Classification of real samples was made by using principal component analysis. The limit of detection for the total metal concentration was estimated as 1.5 µM for the synthetic samples and about 4 µM for the real samples. Identification of samples containing large amounts of iron and copper respectively was possible. The levels of explained Y-variance reached 82% for iron, 76% for copper and 78% for the total metal concentration.

**"Window Factor Analysis: Theoretical Derivation And Application To Flow Injection Analysis Data"**

*J. Chemom.
1992 Volume 6, Issue 1 Pages 29-40*

Edmund R. Malinowski

**Abstract:**A detailed derivation of the window factor analysis methodology is presented, showing how quantification of a single species can be achieved. The method takes advantage of the fact that each component lies in a specific region along the evolutionary axis, called the 'window'. For comparative and illustrative purposes the method was applied to the flow injection analysis data of Gemperline and Hamilton (Ibid., 1989, 3, 455). Window factor anal. (WFA) is a self-modeling method for extracting the concentration profiles of individual components from evolutionary processes such as flow injection, chromatography, titrations and reaction kinetics. The method takes advantage of the fact that each component lies in a specific region along the evolutionary axis, called the 'window'. Theoretical equations are derived. The method is used to extract the concentration profiles and spectra of seven bismuth species from data obtained by Gemperline and Hamilton, who injected bismuth perchlorate into a flowing stream of hydrochloric acid.

**"Evolving Factor Analysis Applied To Flow Injection Analysis Data"**

*J. Chemom.
1989 Volume 3, Issue 3 Pages 455-461*

Paul J. Gemperline, J. Craig Hamilton

**Abstract:**Evolving factor analysis is used to estimate the concentration profiles and spectra of Bi3+ and the bismuth chloride complexes BiC12+ through BiCl6,3- formed by injection of bismuth perchlorate into a flowing stream of 1.0 mol L-1 HCl. The estimated spectra compare favorably with previously published spectra of the complexes.

**"Application Of The Powell Method To The Optimization Of Flow Injection Systems"**

*J. Chemom.
1988 Volume 3, Issue S1 Pages 285-292*

M. del Valle, J. Alonso, M. Poch, J. Bartrolí

**Abstract:**This paper describes the application of the Powell algorithm to the optimization of a flow injection system configuration. The performance of this algorithm has been compared with the modified simplex method. The system studied is the determination of ammonia, based on the indophenol blue reaction. A linear combination of sensitivity and sample throughput is used as the objective function because of its simultaneous optimization capability. Results obtained show that the proposed method may reach the optimal conditions with a lower number of experimental evaluations.

**"Use Of A Linear Function Of Several Variables In Simplex Optimization As A Procedure For Assessing Analytical Versatility In FIA"**

*J. Chemom.
1988 Volume 3, Issue S1 Pages 249-256*

Alonso, J. Bartroli, M. del Valle, A. A. S. C. Machado, L. M. A. Ribeiro

**Abstract:**The simplex optimization procedure described previously (Anal. Lett., 1987, 20, 1247) was used in conjunction with a linear response function involving sensitivity (peak height) and sampling rate (residence time, which should be minimized) to optimize a flow injection system similar to that of Nakashima et al. (cf. Anal. Abstr., 1984, 46, 7H41) for the determination of NO2- in water. It is concluded that sampling rates can be more than doubled compared with those of Nakashima et al. when analyzing residual waters containing >10 ppb of NO2-.