Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm

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.

[img] Text
J16308_a58a04fb74a4c20d3aa9da2a1947e460.pdf
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

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.

Item Type: Article
Uncontrolled Keywords: Flower pollination algorithm Near-infrared spectroscopy Partial least squares regression Wavelength selection
Subjects: T Technology > T Technology (General)
Divisions: Faculty of Mechanical and Manufacturing Engineering
Depositing User: Mr. Mohamad Zulkhibri Rahmad
Date Deposited: 17 Oct 2023 07:41
Last Modified: 17 Oct 2023 07:41
URI: http://eprints.uthm.edu.my/id/eprint/10158

Actions (login required)

View Item View Item