摘要
为了对烟叶等级进行快速分类,采用云南曲靖地区150个烟草样品近红外光谱,结合偏最小二乘判别分析(PLS-DA),建立了烟叶等级分类模型,并对60个预测集样品进行了等级分类预测。结果表明:①训练集和预测集的预测正确率分别为100.0%(150/150)和96.7%(58/60)。②PLS-DA对烟叶等级具有良好的分类效果。该模型为烟叶等级分类提供了一种新的快速鉴别分析的方法。
In order to rapidly classifying tobacco grades, the classification model of tobacco grades was established by partial least squares discrimination analysis （PLS-DA） with the near-infrared spectra of 150 tobacco samples collected from Qujing in Yunnan. The prediction were carried out on the 60 samples in the prediction set with the established model. The results indicated that： 1） The prediction accuracies of training and prediction sets were 100.0% （150/150） and 96.7% （58/60）, respectively; 2） PLS-DA was efficient in tobacco grade classifying. This model provides a new rapid discrimination analysis method for the classification of tobacco grades.
出处
《烟草科技》
EI
CAS
北大核心
2013年第4期60-62,共3页
Tobacco Science & Technology
基金
中国烟草总公司"近红外光谱结合数据融合技术在烟叶内在质量评价中的应用"项目资助(2010YN65)
关键词
近红外光谱
偏最小二乘判别分析(PLS-DA)
烟叶等级分类
Near infrared spectroscopy
Partial least squares discrimination analysis （PLS-DA）
Classification of tobacco grade
