Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm
Wavelength selection is crucial to the success of near-infrared (NIR) spectroscopy analysis as it considerably improves the generalization of the multivariate model and reduces model complexity. This study proposes a new wavelength selection method, interval flower pollination algorithm (iFPA), fo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/10158/1/J16308_a58a04fb74a4c20d3aa9da2a1947e460.pdf |
| _version_ | 1825638301311172608 |
|---|---|
| author | Pauline Ong, Pauline Ong Jinbao Jian, Jinbao Jian Jianghua Yin, Jianghua Yin Guodong Ma, Guodong Ma |
| author_facet | Pauline Ong, Pauline Ong Jinbao Jian, Jinbao Jian Jianghua Yin, Jianghua Yin Guodong Ma, Guodong Ma |
| author_sort | Pauline Ong, Pauline Ong |
| collection | UTHM |
| description | Wavelength selection is crucial to the success of near-infrared (NIR) spectroscopy analysis as it considerably
improves the generalization of the multivariate model and reduces model complexity. This study proposes a new
wavelength selection method, interval flower pollination algorithm (iFPA), for spectral variable selection in the
partial least squares regression (PLSR) model. The proposed iFPA consists of three phases. First, the flower pollination algorithm is applied to search for informative spectral variables, followed by variable elimination. Subsequently, the iFPA performs a local search to determine the best continuous interval spectral variables. The interpretability of the selected variables is assessed on three public NIR datasets (corn, diesel and soil datasets). Performance comparison with other competing wavelength selection methods shows that the iFPA used in conjunction with the PLSR model gives better prediction performance, with the root mean square error of prediction values of 0.0096–0.0727, 0.0015–3.9717 and 1.3388–29.1144 are obtained for various responses in corn, diesel and soil datasets, respectively. |
| first_indexed | 2024-03-05T22:04:43Z |
| format | Article |
| id | uthm.eprints-10158 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:04:43Z |
| publishDate | 2023 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | uthm.eprints-101582023-10-17T07:41:02Z http://eprints.uthm.edu.my/10158/ Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm Pauline Ong, Pauline Ong Jinbao Jian, Jinbao Jian Jianghua Yin, Jianghua Yin Guodong Ma, Guodong Ma T Technology (General) Wavelength selection is crucial to the success of near-infrared (NIR) spectroscopy analysis as it considerably improves the generalization of the multivariate model and reduces model complexity. This study proposes a new wavelength selection method, interval flower pollination algorithm (iFPA), for spectral variable selection in the partial least squares regression (PLSR) model. The proposed iFPA consists of three phases. First, the flower pollination algorithm is applied to search for informative spectral variables, followed by variable elimination. Subsequently, the iFPA performs a local search to determine the best continuous interval spectral variables. The interpretability of the selected variables is assessed on three public NIR datasets (corn, diesel and soil datasets). Performance comparison with other competing wavelength selection methods shows that the iFPA used in conjunction with the PLSR model gives better prediction performance, with the root mean square error of prediction values of 0.0096–0.0727, 0.0015–3.9717 and 1.3388–29.1144 are obtained for various responses in corn, diesel and soil datasets, respectively. Elsevier 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/10158/1/J16308_a58a04fb74a4c20d3aa9da2a1947e460.pdf Pauline Ong, Pauline Ong and Jinbao Jian, Jinbao Jian and Jianghua Yin, Jianghua Yin and Guodong Ma, Guodong Ma (2023) Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 302. pp. 1-17. https://doi.org/10.1016/j.saa.2023.123095 |
| spellingShingle | T Technology (General) Pauline Ong, Pauline Ong Jinbao Jian, Jinbao Jian Jianghua Yin, Jianghua Yin Guodong Ma, Guodong Ma Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title | Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title_full | Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title_fullStr | Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title_full_unstemmed | Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title_short | Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| title_sort | characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/10158/1/J16308_a58a04fb74a4c20d3aa9da2a1947e460.pdf |
| work_keys_str_mv | AT paulineongpaulineong characteristicwavelengthoptimizationforpartialleastsquaresregressionusingimprovedflowerpollinationalgorithm AT jinbaojianjinbaojian characteristicwavelengthoptimizationforpartialleastsquaresregressionusingimprovedflowerpollinationalgorithm AT jianghuayinjianghuayin characteristicwavelengthoptimizationforpartialleastsquaresregressionusingimprovedflowerpollinationalgorithm AT guodongmaguodongma characteristicwavelengthoptimizationforpartialleastsquaresregressionusingimprovedflowerpollinationalgorithm |