ABSTRACT
In order to analyze the quality similarity of tobacco leaves in different tobacco planting areas, 21 quality indices of flue-cured tobacco were collected from different production areas, extracted principal components by factor analysis, classified by 3 clustering analysis methods, and the classification results were compared and statistically tested. The result indicated that: (1) The quality of tobacco leaves was different, and high degree of information overlap was detected among different indices of tobacco appearance, chemical and sensory quality; (2) The cumulative variance contribution rate of 5 extracted principal component factors was 85.445%, and the eigenvalues were 7.761, 4.758, 2.472, 1.674 and 1.278, respectively; (3) The results of 3 cluster analysis methods were not the same. The results of the weighted principal component distance cluster and the weighted principal component cluster were similar, which were different from the general principal component cluster; (4) The results of statistical test showed that the weighted principal component distance cluster method had the largest F-test value (5.900), the smallest sum of squares within the group (8.164), and the largest sum of squares between groups (19.267). And the weighting results for different principal component factors were more reasonable which also had more objective classification results. The cluster results of weighted principal component distance and weighted principal component were better than that of general principal component. And the cluster results of weighted principal component distance were more interpretable which had better the statistical test results.
- Hu Jianjun. Tobacco leaf quality evaluation optimization and empirical research[D]. Hunan Agricultural University, 2009.Google Scholar
- Gao Lin, Tian Feng, Chen Qianfeng, et al. Evaluation of quality and style characteristics of flue-cured tobacco in Xiangxi Prefecture[J]. Tobacco Science & Technology, 2019 (9): 31--38.Google Scholar
- Wang Nan, Luo Xinggang, Zhang Zhongliang, et al. Cigarette formula maintenance based on non-negative matrix factorization[J]. Tobacco Science & Technology, 2019(8): 67--76.Google Scholar
- Lv Yanwei, Lou Xianjun, Li Ping. Weighted principal component distance cluster analysis method and its application[J]. Statistics & Decision, 2018 (15): 87--90.Google Scholar
- Zhu Jianping, Wang Deqing, Fang Kuangnan. Static analysis of China's regional innovation capability------based on the adaptive weighted principal component clustering model[J]. Journal of Applied Statistics and Management, 2013 (5): 761--768.Google Scholar
- Chen Junfei, Chen Lin. Environmental quality assessment of Jiangsu Province based on weighted principal component distance clustering[J]. Resource Development & Market, 2018 (10): 1383--1388.Google Scholar
- Wang Deqing, Zhu Jianping, Xie Bangchang. Thinking on validity of principal component cluster analysis[J]. Statistical Research, 2012 (11): 84--87.Google Scholar
- Lai Yanhua, Chen Cuiling, Ouyang Lusi, et al. Comprehensive evaluation of cigarette quality stability------based on multi-feature similarity analysis and principal component analysis[J]. Acta Tabacaria Sinica, 2017 (5): 22--30.Google Scholar
- Wang Deqing, Zhu Jianping, Wang Jiedan. Research on functional data clustering method based on adaptive weight[J]. Journal of Applied Statistics and Management, 2015 (1): 84--92.Google Scholar
- Lv Yanwei, Li Ping. A cluster analysis method based on weighted principal component distance[J]. Statistical Research, 2016 (11): 102--108.Google Scholar
- Chu Xu, Wang Keqing, Wei Jianrong, et al. Quality evaluation of flue-cured tobacco leaf based on comprehensive weighting method[J]. Tobacco Science & Technology, 2019 (10): 28--36.Google Scholar
- Hu Zhongsheng, Chen Jingbo, Zhou Xinghua, et al. Application of Fuzzy Evaluation and Euclidean Distance Method in Tobacco Chemical Composition Evaluation[J]. Tobacco Science & Technology, 2012 (11): 33--37.Google Scholar
- Cai Xianjie, Wang Xinmin, Yin Qisheng. Preliminary study on quantitative analysis of flue-cured tobacco appearance quality indicators[J]. Tobacco Science & Technology, 2004(6): 37--39.Google Scholar
- Deng Xiaohua, Zhou Jiheng, Chen Xinlian, et al. Research on the correlation between tobacco leaf quality evaluation indicators[J]. Acta Tabacaria Sinica, 2008 (2): 1--8.Google Scholar
- Deng Xiaohua, Deng Jingqing, Xiao Chunsheng, et al. The distribution of flavor notes in strong flavor type tobacco leaves from Hunan province[J]. Acta Tabacaria Sinica, 2014 (2): 39--46.Google Scholar
- Deng Xiaohua, Yang Lili, Lu Zhongshan, et al. Sensory evaluation of quality, style and characteristics of Xiangxi tobacco leaves[J]. Acta Tabacaria Sinica, 2013 (5): 22--27.Google Scholar
- Chu Xu, Wang Keqing, Wei Jianrong, et al. Study on method combination for evaluation of fertility status of tobacco growing soil in Yunnan[J]. Acta Tabacaria Sinica, 2019 (2): 48--54.Google Scholar
- Zhao Qibo, Chen Jingbo, Wei Jianrong, et al. Application of combined evaluation method in comprehensive evaluation of tobacco leaf chemical quality[J]. Acta Tabacaria Sinica, 2013 (19): 1--6.Google Scholar
- Chen Junfei, Wu Mingfeng. Application of Principal Component Analysis in the Evaluation of Urban Complex System Development[J]. Soft Science, 2006 (1): 9--11.Google Scholar
- Wang Deqing, Liu Xiaowei, Zhu Jianping. Clustering Analysis for Functional Data based on Adaptive Iteration[J]. Statistical Research, 2015 (4): 91--96.Google Scholar
- Li Hua, Zhao Shuying, Sun Qiubai, et al. Construction and analysis of financial security index evaluation system based on weighted principal component distance clustering[J]. Mathematics in Practice and Theory, 2018 (1): 90--102.Google Scholar
Index Terms
- Study on Classification of Flue-cured Tobacco Planting area Based on Different Clustering Analysis Methods
Recommendations
Analysis of Determinants of Grain Output in Henan Province based on Principal Component Analysis
ICCIR '21: Proceedings of the 2021 1st International Conference on Control and Intelligent RoboticsAs a big province of agricultural production, in recent years, Henan's grain output has been in the forefront, and shows a trend of increasing year by year. In this paper, SPSS20.0 was used to analyze the principal component of six main factors ...
Feature-reinforced dual-encoder aggregation network for flue-cured tobacco grading
AbstractFlue-cured tobacco grading plays a vital role in product acquisition and planting management. Due to the appearance similarity of inter-class tobacco leaves, the grading accuracy of existing algorithms could not conform to the ...
Highlights- The dual-encoder structure can provide better feature representation.
- Effective ...
Kernel based symmetrical principal component analysis for face classification
Kernel method is a powerful technique in machine learning and it has been widely applied to feature extraction and classification. Symmetrical principal component analysis (SPCA) is an excellent feature extraction method for face classification because ...
Comments