基于主成分分析和聚类分析的烤烟质量评价模型构建  被引量:54

Model of the Quality Evaluation of Flue-cured Tobacco Based on Principal Component Analysis and Cluster Analysis

在线阅读下载全文

作  者:叶协锋[1] 魏跃伟[1] 杨宇熙[2] 陈秀花[2] 黄元炯[2] 李亚娟[1] 李东霞 刘国顺[1] 

机构地区:[1]河南农业大学国家烟草栽培生理生化研究基地烟草行业栽培重点实验室,河南郑州450002 [2]河南省烟草公司,河南郑州450003 [3]山东平邑烟草公司,山东平邑273300

出  处:《农业系统科学与综合研究》2009年第3期268-271,276,共5页System Sciemces and Comprehensive Studies In Agriculture

基  金:国家烟草专卖局重点科研项目(110200401017110200401021)

摘  要:为了建立更为科学、客观的烟叶质量评价方法,采用外观质量评价与常规化学成分评价相结合的方法,研究8个外观质量指标和8个化学成分指标,建立了基于主成分分析和聚类分析的Fisher判别函数的烟叶质量评价模型,并对河南省平顶山市42个烟叶样品进行了分类。采用主成分分析方法共提取了6个主成分,并对各个样品6个主成分得分进行聚类分析,同时根据6个主成分得分和聚类分析结果进行判别分析,对比Fisher判别函数和聚类分析的结果,两者有较好的一致性。因此,可以利用这个烟叶评价模型对烟叶进行质量评价。这使得烟叶质量评价方法更加客观,也开辟了烟叶质量评价的新途径。表5,参16。To be more scientific and more external, combined with appearance evaluation method and conventional chemical evaluation method, 8 appearance quality characteristics and 8 chemical quality characteristics were researched. And a flue-cured quality evaluation model was es- tablished based on principal component analysis, cluster analysis and Fisher discriminant functions. 42 samples were classified with this model in Ping ding-shan city He' nan Province. 6 main components were extracted with principal component analysis. 42 samples were clustered by 6 main components scores with cluster analysis. Discriminant analysis used based on 6 main components scores and the result of cluster analysis. The model was acceptable because the results of Fisher discrimiuant functions and cluster analysis had a well consistent with each other. Accordingly, this study suggested that the model be a new method with more external evaluation for tobacco quality.

关 键 词:烤烟 质量评价 主成分分析 聚类分析 判别分析 

分 类 号:S114[农业科学—农业基础科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象