Abstract
We present two strategies to determine the kernel switching order for the non-linear multi-kernel PLSR algorithm. The multi-kernel PLS (MKPLS) algorithm builds upon a one kernel PLSR which uses a kernel matrix to hold the inner products of the projection of the independent data set onto a feature space. After building a PLSR model, MKPLS deflates the kernel matrix so that only that part which cannot be predicted by the model remains. This remainder is projected onto a different feature space and a new PLSR model is built. The switching algorithms presented for this approach address two questions: which kernel should be used at each iteration and; how many factors should be extracted before switching to another kernel.
Similar content being viewed by others
References
Baffi G, Martin E, Morris A (1999) Non-linear projection to latent structures revisited: the quadratic pls algorithm. Comput Chem Eng 23:395–411
Geladi P, Kowalski BR (1986) Partial least squares regression: a tutorial. Anal Chim Acta 185:1–17
Kettaneh N, Wold S (2001) Pca and pls with very large data sets. In: 2nd International symposium on PLS and related methods, Capri, Italy, pp 1–2
Milidiú R, Rentería R (2005) Dpls and ppls: two pls algorithms for large data sets. Comput Stat Data Anal 48:125–138
Rentería R, Milidiú R (2003) A multi-kernel approach for non-linear kernel plsr. In: 3rd International symposium on PLS and related methods, Lisboa, Portugal, pp 527–536
Rännar S, lindgren F, Geladi P, Wold S (1994) A pls kernel algorithm for data sets with many variables and fewer objects. part 1: Theory and algorithm. J Chemom 8:111–125
Rosipal R, Trejo LJ (2001) Kernel partial least squares regression in reproducing kernel hilbert space. J Mach Learn 2:97–123
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, London
Tecator IA (1995) Prediction of fat content of a meat sample. StatLib Datasets Archive
Wold S, Kettaneh-Wold N, Skagerberg B (1989) Non-linear pls modelling. Chemom Intell Lab Syst 7:53–65
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rentería, R., Milidiú, R. & Souza, R. MKPLS approach: switching strategies for the non-linear multi-kernel PLSR. Computational Statistics 22, 323–330 (2007). https://doi.org/10.1007/s00180-007-0040-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-007-0040-5