多个化学成分指标烟叶样品的聚类分析研究

A study on the cluster analysis of 48 leaf-tobacco samples with 8 chemical compositions

对 4 8个不同烟叶样品的化学成分性状按欧式距离类平均法进行聚类分析并对类间进行特征差异分析。结果表明 ,4 8个烟叶样品可以聚为 4个类别 ,各类别化学成分的平均值和变异系数等特征数存在差异 ,不同类别在主要化学成分间存在显著性差异。这些结果或许可供深入开展计算机产品设计的个别环节参考。

Samples of 48 leaf\|tobacco were classified based on 8 chemical compositions using the method of cluster analysis. Differences between these classes were tested with T\|test. Results indicated that the 48 leaf tobacco samples can be classified into 4 classes and there were significant differences between classes for most characters tested. There were also differences between classes in average value and variance coefficient of the characters. These results can be useful for the study of designing cigarette products with computer.