A comparative study for least angle regression on NIR spectra analysis to determine internal qualities of navel oranges

作者：

Highlights：

• Least angle regression (LAR) was applied to predict fruit qualities based on NIRS.

• LAR obtained more accurate prediction results than PLS.

• LAR is more efficient than PLS and LS-SVM in NIRS regression analysis.

• LAR is better at revealing most relevant NIRS wavelengths than PLS and LS-SVM.

摘要

•Least angle regression (LAR) was applied to predict fruit qualities based on NIRS.•LAR obtained more accurate prediction results than PLS.•LAR is more efficient than PLS and LS-SVM in NIRS regression analysis.•LAR is better at revealing most relevant NIRS wavelengths than PLS and LS-SVM.

论文关键词：Least angle regression,Machine learning,Near infrared spectra,Navel orange

论文评审过程：Received 1 February 2015, Revised 3 July 2015, Accepted 4 July 2015, Available online 17 July 2015, Version of Record 29 August 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.07.005