基于主成分分析法的美八苹果品质综合评价体系构建  

Establishing comprehensive evalution system of American No.8 fresh apples based on principal component analysis

作　　者：孟永宏[1] 张英[1] 王晓培[1] 魏丽娜[1] 马玉娟[1] 邓红[1] 郭玉蓉[1] 

机构地区：[1]陕西师范大学,食品工程与营养科学学院,陕西西安710119

出　　处：《食品工业科技》2015年第9期296-300,共5页Science and Technology of Food Industry

基　　金：陕西科技统筹计划项目(2011KTCQ02-03);中国农业研究体系(CA-28)

摘　　要：用主成分分析得出代表美八苹果品质的综合指标,依据建立的综合评价模型对苹果进行分级。用SPSS 19.0软件对120个美八鲜果的13项品质指标进行主成分分析筛选出主成分因子,Excel软件辅助得出各个主成分因子的得分以及鲜果的综合得分,然后利用k-均值聚类分析将鲜果分级。结果显示,前7项主成分因子的累计方差贡献率达91.490%,能够反映出原始样本的大部分信息。根据各个样本的前7项主成分因子得分及各个因子的方差贡献率得出样本综合评分公式,计算样本的综合得分。然后根据综合得分利用k-均值聚类分析可将120个美八鲜果划分为5级,各级数量的百分比为15.00%、28.33%、33.33%、19.17%、4.17%。本研究为美八鲜果理化品质分析建立了一种客观、可行的多指标综合评价及分类模型。Five levels apples were classified by the comprehensive evalution indices of American No.8 fresh apples based on principal component analysis method.In this experiment,thirteen kinds of quality indices of 120 American No.8 fresh apples were determined by using conventional method,and the achieved indices were analyzed by using SPSS 19.0 software which aimed to select principal component factors. The results demonstrated that the former seven principal component factors could reflect the most information of original samples,whose cumulative contribution of variance accounted to 91.490%. The integrated scores were obtained through the former seven principal component values based on the important calculation of the principal component contribution proportion.Then fresh apples were classified into several levels by k- means clustering analysis based on each principal component factor scores and comprehensive scores of fresh apples,and the proportion of each level was 15.00%,28.33%,33.33%,19.17%,4.17%.The comprehensive evaluation and classification model which was established can provide scientific basis for comprehensive quality evaluation and classifying of American No.8 fresh apples.

关 键 词：美八苹果 主成分分析 K-均值聚类 综合评价体系 

分 类 号：TS255.7[轻工技术与工程—农产品加工及贮藏工程]