Premium
Ensemble calibration for the spectral quantitative analysis of complex samples
Author(s) -
Bian Xihui,
Diwu Pengyao,
Liu Yirui,
Liu Peng,
Li Qian,
Tan Xiaoyao
Publication year - 2018
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/cem.2940
Subject(s) - calibration , ensemble learning , ensemble forecasting , computer science , relation (database) , artificial intelligence , machine learning , data mining , statistics , mathematics
Abstract Ensemble strategies have gained increasing attention in multivariate calibration for quantitative analysis of complex samples. The aim of ensemble calibration is to obtain a more accurate, stable, and robust prediction by combining the predictions of multiple submodels. The generation and calibration of the training subsets, as well as the integration of the submodels, are three keys to the success of ensemble calibration. Many training subset generating and submodel integrating strategies have been developed to form numerous ensemble calibration methods for improving the performance of the basic calibration method. This contribution focuses on the recent ensemble strategies in relation to calibration, especially the ensemble modeling for quantitative analysis of complex samples. The limitations and perspectives of ensemble strategies are also discussed.