摘要
采用化学方法测定了不同女贞子样品的蛋白质、脂肪和可溶性多糖含量,并对女贞子样品同时进行了近红外光谱测定.基于离散小波变换对女贞子近红外光谱的处理,探讨了同时测定女贞子蛋白质、脂肪和多糖含量的支持向量回归模型和偏最小二乘方法.结果表明:将离散小波变换与支持向量回归模型结合,可明显提高支持向量回归模型对女贞子样品中蛋白质、脂肪和可溶性多糖的预测准确度,结果满意.
The content of protein,fat and soluble polysaccharide in different fruit samples of Ligustrum lucidum were determined by chemical method and near infrared spectroscopy at the same time.The support vector regression model and partial least squares(PLS)method for the determination of protein,fat and polysaccharide in L.lucidum simultaneously were discussed based on the treatment of near infrared spectroscopy of fruit of L.lucidum by discrete wavelet transform.The results showed that the combination of discrete wavelet transform and support vector regression model can improve the prediction accuracy of protein,fat and soluble polysaccharide in fruit of L.lucidum samples compared with the support vector regression model.The results were satisfactory.
作者
段凌瑶
侯超逸
李芸玲
高慧玲
娄慧慧
侯振雨
DUAN Lingyao;HOU Chaoyi;LI Yunling;GAO Huiling;LOU Huihui;HOU Zhenyu(School of Chemistry and Chemical Engineer,Henan Institute of Science and Technology,Xinxiang 453003,China)
出处
《河南科技学院学报(自然科学版)》
2018年第1期54-58,共5页
Journal of Henan Institute of Science and Technology(Natural Science Edition)
基金
2012年河南省科技攻关项目(122102310278)
2013年河南省教育厅重点研究项目(13A150282)
关键词
女贞子
蛋白质
脂肪
多糖
近红外光谱
支持向量回归
fruit of Ligustrum lucidum
protein
fat
polysaccharide
near infrared spectroscopy
support vector regression