期刊论文

Zhou, Long

英文

Optik

0030-4026

2018

165

137-147

10.1016/j.ijleo.2017.12.126

This work is supported by Chutian Scholar Programm-Chutian Student of Hubei Provincial Department of Education , Hubei Provincial Department of Education (No. D20161705 ), Science and Technology Department of Hubei Province (No. 2016CFB298 ), Grain Administration of Hubei Province (No. 2060404 ), the Recruitment Program of Wuhan Polytechnic University (No. 2017RZ05 ), Research and Innovation Initiatives of WHPU (Nos. 2017y27 and 2016J06 ).

本校为第一且通讯机构

Partial least squares (PLS) has been extensively used to solve problems such as infrared quantitative analysis, economic data analysis, object tracking. PLS finds a linear regression model by projecting the predicted variables and the response to a new space. A major drawback of existing PLS methods is that regression coefficient will be affected by outliers. Thus, partial least squares experience significant performance degradation when gross outliers are presented. The problem of robust partial least squares has been relatively unexplored in ...