Localized, adaptive recursive partial least squares regression for dynamic system modeling
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 sensiti...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/100953 http://hdl.handle.net/10220/16707 |
| _version_ | 1826111005493559296 |
|---|---|
| author | Brown, Steven D. Ni, Wangdong Tan, Soon Keat Ng, Wun Jern |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Brown, Steven D. Ni, Wangdong Tan, Soon Keat Ng, Wun Jern |
| author_sort | Brown, Steven D. |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T02:43:31Z |
| format | Journal Article |
| id | ntu-10356/100953 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:43:31Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1009532020-03-07T12:48:43Z Localized, adaptive recursive partial least squares regression for dynamic system modeling Brown, Steven D. Ni, Wangdong Tan, Soon Keat Ng, Wun Jern School of Civil and Environmental Engineering Nanyang Environment and Water Research Institute DRNTU::Engineering::Environmental engineering 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. 2013-10-23T05:44:15Z 2019-12-06T20:31:24Z 2013-10-23T05:44:15Z 2019-12-06T20:31:24Z 2012 2012 Journal Article 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. 0888-5885 https://hdl.handle.net/10356/100953 http://hdl.handle.net/10220/16707 10.1021/ie203043q en Industrial & Engineering Chemistry Research © 2012 American Chemical Society |
| spellingShingle | DRNTU::Engineering::Environmental engineering Brown, Steven D. Ni, Wangdong Tan, Soon Keat Ng, Wun Jern Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title | Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title_full | Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title_fullStr | Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title_full_unstemmed | Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title_short | Localized, adaptive recursive partial least squares regression for dynamic system modeling |
| title_sort | localized adaptive recursive partial least squares regression for dynamic system modeling |
| topic | DRNTU::Engineering::Environmental engineering |
| url | https://hdl.handle.net/10356/100953 http://hdl.handle.net/10220/16707 |
| work_keys_str_mv | AT brownstevend localizedadaptiverecursivepartialleastsquaresregressionfordynamicsystemmodeling AT niwangdong localizedadaptiverecursivepartialleastsquaresregressionfordynamicsystemmodeling AT tansoonkeat localizedadaptiverecursivepartialleastsquaresregressionfordynamicsystemmodeling AT ngwunjern localizedadaptiverecursivepartialleastsquaresregressionfordynamicsystemmodeling |