Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial
A tutorial is presented on the operation and properties of the non-linear multivariate regression model kernel partial least-squares (KPLS). After the discussion of a simple non-linear univariate problem, solved by regressing a dependent variable on the projection of an independent variable onto a s...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | Talanta Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666831923000553 |
| _version_ | 1827932903822065664 |
|---|---|
| author | Franco Allegrini Alejandro C. Olivieri |
| author_facet | Franco Allegrini Alejandro C. Olivieri |
| author_sort | Franco Allegrini |
| collection | DOAJ |
| description | A tutorial is presented on the operation and properties of the non-linear multivariate regression model kernel partial least-squares (KPLS). After the discussion of a simple non-linear univariate problem, solved by regressing a dependent variable on the projection of an independent variable onto a set of Gaussian functions, the principles of KPLS are introduced for processing non-linear multivariate data. The following aspects are covered: (1) the estimation of the model sensitivity as a function of analyte concentration from error propagation concepts, (2) the proposal of a parameter measuring the degree of non-linearity, to avoid a black-and-white description of data sets as either linear or non-linear, (3) the use of the model parameters for variable selection. The application of KPLS to both simulated and experimental data sets is discussed, in the latter case involving near infrared spectra employed for the determination of quality parameters in foodstuff samples and fluorescence spectroscopic data for the study of systems of biological relevance. Computer codes written in the popular MATLAB and R environments are also provided. |
| first_indexed | 2024-03-13T07:17:02Z |
| format | Article |
| id | doaj.art-60c1e224ce774d26bc134615232d11c4 |
| institution | Directory Open Access Journal |
| issn | 2666-8319 |
| language | English |
| last_indexed | 2024-03-13T07:17:02Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Talanta Open |
| spelling | doaj.art-60c1e224ce774d26bc134615232d11c42023-06-05T04:13:23ZengElsevierTalanta Open2666-83192023-08-017100235Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorialFranco Allegrini0Alejandro C. Olivieri1Calle 9 de Julio 2045 Dto. 6B, Rosario (2000), ArgentinaDepartamento de Química Analítica, Facultad de Ciencias Bioquímicas y Farmacéuticas, Universidad Nacional de Rosario, Instituto de Química Rosario (CONICET-UNR), Suipacha 531 (2000) Rosario, Argentina; Corresponding author.A tutorial is presented on the operation and properties of the non-linear multivariate regression model kernel partial least-squares (KPLS). After the discussion of a simple non-linear univariate problem, solved by regressing a dependent variable on the projection of an independent variable onto a set of Gaussian functions, the principles of KPLS are introduced for processing non-linear multivariate data. The following aspects are covered: (1) the estimation of the model sensitivity as a function of analyte concentration from error propagation concepts, (2) the proposal of a parameter measuring the degree of non-linearity, to avoid a black-and-white description of data sets as either linear or non-linear, (3) the use of the model parameters for variable selection. The application of KPLS to both simulated and experimental data sets is discussed, in the latter case involving near infrared spectra employed for the determination of quality parameters in foodstuff samples and fluorescence spectroscopic data for the study of systems of biological relevance. Computer codes written in the popular MATLAB and R environments are also provided.http://www.sciencedirect.com/science/article/pii/S2666831923000553Kernel partial least-squaresMultivariate calibrationNear infrared spectraFluorescence dataDetection of non-linearity |
| spellingShingle | Franco Allegrini Alejandro C. Olivieri Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial Talanta Open Kernel partial least-squares Multivariate calibration Near infrared spectra Fluorescence data Detection of non-linearity |
| title | Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial |
| title_full | Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial |
| title_fullStr | Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial |
| title_full_unstemmed | Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial |
| title_short | Two sides of the same coin: Kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. A tutorial |
| title_sort | two sides of the same coin kernel partial least squares kpls for linear and non linear multivariate calibration a tutorial |
| topic | Kernel partial least-squares Multivariate calibration Near infrared spectra Fluorescence data Detection of non-linearity |
| url | http://www.sciencedirect.com/science/article/pii/S2666831923000553 |
| work_keys_str_mv | AT francoallegrini twosidesofthesamecoinkernelpartialleastsquareskplsforlinearandnonlinearmultivariatecalibrationatutorial AT alejandrocolivieri twosidesofthesamecoinkernelpartialleastsquareskplsforlinearandnonlinearmultivariatecalibrationatutorial |