支持向量机回归法在近红外光谱测定植物纤维原料中甲氧基含量中的应用

APPLICATION OF SUPPORT VECTOR MACHINE (SVM) REGRESSION METHOD IN DETERMINATION OF METHOXYL GROUP CONTENT IN PLANT FIBROUS MATERIAL BY NEAR-INFRARED SPECTROSCOPY

以26个植物纤维原料为实验材料,由20个样品作校正样品,采用径向基核函数方法对纤维原料中甲氧基含量与纤维原料样品近红外光谱进行支持向量机(SVM)回归建模。以所建SVM回归模型对6个纤维原料样品中甲氧基含量进行预测,回归模型的预测结果与采用改良的维伯克法确定的甲氧基含量的相关系数为0.977,预测样本集的标准偏差为0.43。将SVM回归模型的预测效果与PLS回归模型的预测结果进行比较,所建近红外光谱测定植物纤维原料中甲氧基含量的SVM回归模型可用于实际植物纤维原料样品的定量分析,且具有较好的分析效果。

The application of support vector machine(SVM) regression method based on statistical theory to the determination of methoxyl content in plant fibrous material with near-infrared (NIR) spectroscopy was introuduced. 26 plant fibrous material samples were used as experimental materials,and 20 of them were used as calibration samples. The methoxyl contents and NIR spectra of the calibration samples were used to build SVM regression model by radial base function.The methoxyl content of the predicting samples we...