摘要:

AbstractThis work addresses the classification of high‐dimensional time‐dependent pyrolysis mass spectra of biological samples. The aim was the detection and classification of biological agents, and the developed approach resembles mixture analysis. The data were projected on to a low‐dimensional subspace using singular value decomposition. Then a convex cone was formed on this subspace, showing as its corners physically meaningful components of the sample. This technique enabled separation of a biological material signal largely independent of the absolute amount of sample. The detection of the presence of any biological material could be accomplished based on the convex cone alone, without other reference to the mass spectra. Automated clustering of samples was successfully carried out using a minimal spanning

ISSN:0886-9383    

DOI:10.1002/cem.1180080503

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

摘要:

AbstractAttenuated total reflectance Fourier transform infrared spectrometry (ATR‐FTIR) has been used to determine the amount of styrene–butadiene latex on the surface of coated papers and to predict the composition of the polymer. Spectrum recording was performed on the sample in its usual form without any modification.For quantitative analysis, partial least squares (PLS) regression, principal component regression (PCR) and multi‐linear regression (MLR) were used to calculate models for prediction. The best result is obtained with PLS.We analysed two series of paper samples. The first analysis concerns the measurement of the quantity of latex of a constant quality on the coating surface. For 15 samples the concentration varied between 5 and 25 parts (grams per 100g of mineral pigments). We compared the predictive results at various resolutions. We obtained a relative error of 0.15 parts in latex at 4 cm−1resolution. The second analysis concerns the measurement of the styrene/butadiene ratio in various types of latex. We obtained a relative error of 0.156 parts for styrene determination and 0.161 parts for butadiene determ

ISSN:0886-9383    

DOI:10.1002/cem.1180080504

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

摘要:

AbstractA modified PLS algorithm is introduced with the goal of achieving improved prediction ability. The method, denoted IVS‐PLS, is based on dimension‐wise selective reweighting of single elements in the PLS weight vectorw. Cross‐validation, a criterion for the estimation of predictive quality, is used for guiding the selection procedure in the modelling stage. A threshold that controls the size of the selected values inwis put inside a cross‐validation loop. This loop is repeated for each dimension and the results are interpreted graphically. The manipulation ofwleads to rotation of the classical PLS solution. The results of IVS‐PLS are different from simply selectingX‐variables prior to modelling. The theory is explained and the algorithm is demonstrated for a simulated data set with 200 variables and 40 objects, representing a typical spectral calibration situation with four analytes. Improvements of up to 70% in external PRESS over the classical PLS algorithm are shown to

ISSN:0886-9383    

DOI:10.1002/cem.1180080505

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

摘要:

AbstractThe purpose of this short communication is to illustrate the use of conditional maximization (CM) in chemometric applications. The CM algorithm is useful in reducing the computational complexity when a high‐dimensional and complicated maximization problem arises from fitting chemometric models. It can also be efficiently combined with the expectation‐maximization (EM) algorithm for handling incomplete data, a problem that sometimes arises when only a part of the intended data can be collected. Three models from fluorescence spectroscopy are used for illustrat

ISSN:0886-9383    

DOI:10.1002/cem.1180080506

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180080507

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180080508

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY

ISSN:0886-9383    

DOI:10.1002/cem.1180080502

出版商:John Wiley&Sons, Ltd.    

年代:1994

数据来源: WILEY