Title: NIR spectroscopy fruit quality detection algorithm based on the least angle regression model

Authors: Songjian Dan

Addresses: School of Continuing Education, Chongqing University of Education, Chongqing 400067, China

Abstract: To enhance the effectiveness and precision of fruit internal quality detection, the determination model of internal quality of fruit based on the least angle regression (LAR) is proposed. Compared with existing nonlinear and linear models, i.e., least squares support vector machines (LS-SVM) and partial least squares (PLS) regression (the proposed LAR model generates the best prediction results and performs better than conventional PLS. In an aspect of computational complexity, LAR and PLS are better than LS-SVM model. In aspect of interpretability, the proposed LAR is superior to the PLS model. Although the precision rate of LAR is worse than LS-SVM, it has advantages for model realisation, computation complexity, and interpretability over LS-SVM. Thus the proposed LAR model can be applied effectively in the determination of the internal quality of fruit-based on NIR (Near-infrared) spectroscopy.

Keywords: LAR ; least angle regression; LS-SVM; least squares support vector machine; PLS; partial least square; NIR spectroscopy; fruit; determination of qualities; model realisation; computation complexity; interpretability.

DOI: 10.1504/IJHPSA.2020.111568

International Journal of High Performance Systems Architecture, 2020 Vol.9 No.2/3, pp.128 - 135

Received: 29 Apr 2020
Accepted: 05 Sep 2020
Published online: 01 Dec 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article