期刊
APPLIED SPECTROSCOPY
卷 63, 期 7, 页码 800-809出版社
SAGE PUBLICATIONS INC
DOI: 10.1366/000370209788701206
关键词
Multivariate calibration; Calibration maintenance; Calibration transfer; Calibration standardization; Tikhonov regularization; Partial least squares; PLS; Augmentation
资金
- National Science Foundation [CHE-0715179]
- MPS Chemistry and DMS Statistics Divisions
- Universidad Nacional del Litoral and Consejo Nacional de Investigaciones Cientfficas y Tecnicas (CONICET)
- CONICET
Maintaining multivariate calibrations is essential and involves keeping models developed on an instrument applicable to predicting new samples over time. Sometimes a primary instrument model is needed to predict samples measured on secondary instruments. This situation is referred to as calibration transfer. This paper reports on using a Tikhonov regularization (TR) based method in both cases. A distinction of the TR design for calibration maintenance and transfer is a defined weighting scheme for a small set of new (transfer or standardization) samples augmented to the full set of calibration samples. Because straight application of basic TR theory is not always possible with calibration maintenance and transfer, this paper develops a generic solution to always enable application of TR. Harmonious (bias/variance tradeoff) and parsimonious (effective rank) considerations for TR are compared with the same TR format applied to partial least squares (PLS), showing that both approaches are viable solutions to the calibration maintenance and transfer problems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据