Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/100953
Title: Localized, adaptive recursive partial least squares regression for dynamic system modeling
Authors: Brown, Steven D.
Ni, Wangdong
Tan, Soon Keat
Ng, Wun Jern
Keywords: DRNTU::Engineering::Environmental engineering
Issue Date: 2012
Source: Ni, W., Tan, S. K., Ng, W. J., & Brown, S. D. (2012). Localized, adaptive recursive partial least squares regression for dynamic system modeling. Industrial & Engineering Chemistry Research, 51(23), 8025-8039.
Series/Report no.: Industrial & Engineering Chemistry Research
Abstract: A localized and adaptive recursive partial least squares algorithm (LARPLS), based on the local learning framework, is presented in this paper. The algorithm is used to address, among other issues in the recursive partial least-squares (RPLS) regression algorithm, the “forgetting factor” and sensitivity of variable scaling. Two levels of local adaptation, namely, (1) local model adaptation and (2) local time regions adaptation, and three adaptive strategies, (a) means and variances adaptation, (b) adaptive forgetting factor, and (c) adaptive extraction of local time regions, are provided using the LARPLS algorithm. Compared to RPLS, the LARPLS model is proven to be more adaptive in the face of process change, maintaining superior predictive performance, as demonstrated in the modeling of three different types of processes.
URI: https://hdl.handle.net/10356/100953
http://hdl.handle.net/10220/16707
ISSN: 0888-5885
DOI: 10.1021/ie203043q
Rights: © 2012 American Chemical Society
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:NEWRI Journal Articles

SCOPUSTM   
Citations

42
Updated on Sep 6, 2020

PublonsTM
Citations

39
Updated on Dec 1, 2020

Page view(s) 20

429
Updated on Dec 1, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.