HUBEI AGRICULTURAL SCIENCES ›› 2020, Vol. 59 ›› Issue (23): 81-86.doi: 10.14088/j.cnki.issn0439-8114.2020.23.019

• Horticulture & Local Products • Previous Articles     Next Articles

Prediction model of tobacco leaf sensory comfort based on chemical composition

YAN Tie-jun1, CHEN Si-meng2, ZHOU Hong-shen1, XU Zi-cheng2, PANG Zhe1, LIU Wen-feng1, PAN Ting-ting1, SHAO HUI-fang2   

  1. 1. Hubei China Tobacco Industry Co.,Ltd.,Wuhan 430040,China;
    2. College of Tobacco,Henan Agricultural University,Zhengzhou 450002,China
  • Received:2020-09-24 Online:2020-12-10 Published:2020-12-30

Abstract: To improve the effectiveness of evaluation of cigarette sensory quality comfort,170 standard samples of flue-cured tobacco in China's main tobacco-producing areas in 2019 were selected as materials.Based on the conventional chemical components and polyphenol compounds in the tobacco leaves,the descriptive statistics and simple correlation analysis were first used to analyze the chemical components.Then,the principal component analysis method was used to screen the chemical components,and then the stepwise regression analysis method was used to establish a model for the prediction of cigarette sensory comfort.Results showed that,compared with the real value,the prediction result obtained by the model had smaller error,and the result was relatively stable.Which indicate that the prediction model of tobacco sensory comfort established by principal component-stepwise regression analysis method has high accuracy and feasibility.

Key words: cigarette, chemical composition, sensory comfort, principal component analysis, stepwise regression analysis, prediction model

CLC Number: