Improving the Robustness and Stability of Partial Least Squares Regression for Near-infrared Spectral Analysis
Improving the Robustness and Stability of Partial Least Squares Regression for Near-infrared Spectral Analysis
复制标题
提高近红外光谱分析的偏最小二乘回归的鲁棒性和稳定性
DOI：
10.1002/cjoc.200990222
复制
发表时间：
2009-07
影响因子：
5.4
通讯作者：
Cai Wensheng
中科院分区：
文献类型：
--
作者：
Shao Xueguang;Chen Da;Xu Heng;Liu Zhichao;Cai Wensheng
偏最小二乘回归是光谱定量测量的有力工具。然而，由于在分析复杂样本或校准数据集中含有离群点的情况下，很难建立稳定的模型，因此仍需提高偏最小二乘模型的稳健性和稳定性。为了达到这一目的，提出了一种基于概率重采样的稳健集成偏最小二乘技术，称为RE-PLS。在所提出的方法中，首先从稳健回归中的残差获得每个校准样本的概率。然后，基于概率重采样建立多个偏最小二乘模型。最后利用多个偏最小二乘模型对未知样本进行预测，将多个模型预测结果的平均值作为最终预测结果。为了验证该方法的有效性和普适性，将其应用于两组不同的近红外光谱。结果表明，RE-偏最小二乘法不仅能有效地避免异常值的干扰，而且提高了预测精度和偏最小二乘回归的稳定性。因此，它可以为具有多个异常值的多变量校正提供一个有用的工具。
Partial least-squares (PLS) regression has been presented as a powerful tool for spectral quantitative measurement. However, the improvement of the robustness and stability of PLS models is still needed, because it is difficult to build a stable model when complex samples are analyzed or outliers are contained in the calibration data set. To achieve the purpose, a robust ensemble PLS technique based on probability resampling was proposed, which is named RE-PLS. In the proposed method, a probability is firstly obtained for each calibration sample from its residual in a robust regression. Then, multiple PLS models are constructed based on probability resampling. At last, the multiple PLS models are used to predict unknown samples by taking the average of the predictions from the multiple models as final prediction result. To validate the effectiveness and universality of the proposed method, it was applied to two different sets of NIR spectra. The results show that RE-PLS can not only effectively avoid the interference of outliers but also enhance the precision of prediction and the stability of PLS regression. Thus, it may provide a useful tool for multivariate calibration with multiple outliers.
登录
查看更多内容
影响因子：
6.2
作者：
Tom Lillhonga;P. Geladi
通讯作者：
Tom Lillhonga;P. Geladi
影响因子：
2
作者：
Z. Su;W. Tong;Leming Shi;X. Shao;W. Cai
通讯作者：
Z. Su;W. Tong;Leming Shi;X. Shao;W. Cai
DOI：
10.1039/b305023h
发表时间：
2003-08
期刊：
The Analyst
影响因子：
--
作者：
Chen Da;F. Wang;X. Shao;Q. Su
通讯作者：
Chen Da;F. Wang;X. Shao;Q. Su
影响因子：
3.5
作者：
Yusuf Sulub;G. W. Small
通讯作者：
Yusuf Sulub;G. W. Small
影响因子：
3.9
作者：
B. Walczak;D. Massart
通讯作者：
B. Walczak;D. Massart