基于集成最小二乘支持向量机方法的近红外光谱分析

针对近红外（Near Infrared,NIR）光谱测量中的小样本问题。本文提出了一种集成最小二乘支持向量机（Ensemble Least Squares Support Vector Machine,ELS-SVM）新算法。首先使用随机子空间算法（Random Subspace Method,RSM）原始高维变量空间划分为若干个低维度的子空间,然后分别在各个子空间建立最小二乘支持向量机（LS-SVM）模型,最后构造一个集成结果来进行预测。针对一批柴油样本的实验结果表明,本法对柴油十六烷值的预测精度优于传统的LS-SVM方法。

Near Infrared Spectral Analysis Based on Ensemble Least Squares Support Vector Machine Method

According to handling the small sample size(SSS) problem in near infrared(NIR) spectra measurement,an ensemble least squares support vector machines(ELS-SVM) approach was proposed.Firstly,the random subspace method(RSM) was introduced to divide the original high-dimensional space into some low-dimensional subspaces,then the LS-SVM prediction models were constructed on each subspace.Finally,an ensemble result was built for prediction.Applying the proposed approach to a set of diesel samples,the experimental ...