Command Line iPLS for MATLAB
by Lars Nørgaard
Introduction
This is a command-line version of the Interval PLS. It is used to develop local PLS models on equidistant subintervals of the full spectrum region. Its main force in this context is to provide an overall picture of the relevant information in different spectral subdivisions and thereby narrowing the important spectral variables. Furthermore m-files for calculation of PLS models on several intervals are included (all combinations of 2, 3 and 4 intervals). Reference: L. Nørgaard, A. Saudland, J. Wagner, J.P. Nielsen, L. Munck and S.B. Engelsen., Interval Partial Least Squares Regression (iPLS): A Comparative Chemometric Study with an Example from Near-Infrared Spectroscopy, Applied Spectroscopy, 54, 2000.
Method
Local PLS models are developed on spectral subintervals of equal width, and the prediction performance of these local models and the global (full spectrum) model is compared. The comparison is mainly based on the validation parameter RMSECV (Root Mean Square Error of Cross Validation), but other parameters such as r2 (squared correlation coefficient), slope and offset are also consulted to ensure a comprehensive model overview.
The command line iPLS toolbox for MATLAB is freely available
Read the information on this page and download the files to your own computer.
The command line iPLS toolbox for MATLAB has been developed for MATLAB version 5.3.
If you use the command line iPLS toolbox for MATLAB we would appreciate a reference to the toolbox. This may for example be
The command line iPLS toolbox for MATLAB, ver. 2.0, 2000 L. Nørgaard KVL, Denmark http://www.models.life.ku.dk/source/ipls/
If you have any questions, suggestions or comments please feel free to contact us at lan@kvl.dk
NOTE: The Toolbox uses the PLS_toolbox 2.0 from Eigenvector Research, Inc., http://www.eigenvector.com
Download the Command Line iPLS Toolbox
The iPLS Toolbox for MATLAB (lniplsv2_1.zip 377KB) (Updated March 17, 2000)