数字农科院2.0

Machine learning-based classification and prediction of typical Chinese green tea taste profiles

文献类型： 外文期刊

作者： Yingbin Zhang;Xuwei Chen;Dingding Chen;Li Zhu;Guoqing Wang;Zhongxiu Chen

作者机构：

关键词： Chinese Green tea;H-K means cluster;RF model;Taste;Unsupervised and supervised learning

期刊名称： Food Research International

ISSN： 0963-9969

年卷期： 2025 年 203 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： The taste of Chinese green tea is highly diverse. In this study, a combination of unsupervised and supervised learning methods was utilized to develop a model for classifying and predicting typical Chinese green tea taste. Three clustering methods were assessed based on quantitative descriptive analysis (QDA) results, with the Hierarchical-K means method chosen to classify 88 tea infusions into seven distinct taste types. Electronic tongue sensors, near-infrared spectroscopy, and metabolomics, along with the analysis of key chemical constituents, were applied to construct various datasets as model data. The performance of four multivariate statistical methods and six artificial intelligence algorithms was compared across the three datasets. Dataset 3, comprising chemical components, taste activity value (Tav), and their ratios, achieved the highest accuracy. The random forest (RF) model achieved the highest accuracy (0.98) and Kappa value (0.97) in predictions. The results indicate that key chemical components, Tav, and their relationships are more critical for classifying green tea taste. This study can provide a more accurate representation and prediction of typical Chinese tea taste profiles from a consumer standpoint. Significant variations in sensory attributes and chemical composition were observed among the identified taste categories, with the MU type displaying the lowest TavTC (total Tav of catechins)/TavTAA (total Tav of amino acids) ratio, indicating the strongest umami and sweetness characteristics. The findings of this study offer the potential for the development of personalized tea products, thereby contributing to an enhanced consumer experience.

分类号：

  • 相关文献

[1]Effect of Ca2+ concentration on the tastes from the main chemicals in green tea infusions. Yin, Jun-Feng,Du, Qi-Zhen,Xu, Yong-Quan,Yin, Jun-Feng,Zhang, Ying-Na,Chen, Jian-Xin,Yuan, Hai-Bo,Xu, Yong-Quan. 2014

[2]Effects of nitrogen application on flavor compounds of cherry tomato fruits. Wang, Yu-Tao,Huang, Shao-Wen,Liu, Rong-Le,Jin, Ji-Yun. 2007

[3]Cloning and haplotype analysis of TaSTE, which is associated with plant height in bread wheat (Triticum aestivum L.). Zhang, Wenping,Zhang, Lei,Qiao, Linyi,Lv, Wenyan,Wu, Jing,Zhao, Guangyao,Jing, Ruilian,Jia, Jizeng.

[4]Analysis of chemical components in green tea in relation with perceived quality, a case study with Longjing teas. Wang, Kunbo,Ruan, Jianyun,Wang, Kunbo,Ruan, Jianyun,Wang, Kunbo,Wang, Kunbo.

[5]Effect of a Dairy Cow’s Feeding System on the Flavor of Raw Milk: Indoor Feeding or Grazing. Xuelu Chi,Ning Yuan,Yangdong Zhang,Nan Zheng,Huimin Liu. 2023

[6]Comprehensive evaluation of flavor in charcoal and electric-roasted tamarix lamb by hs-spme/gc-ms combined with electronic tongue and electronic nose. Yujun Xu,Dequan Zhang,Ruixia Chen,Xiaoyue Yang,Huan Liu,Zhenyu Wang,Teng Hui. 2021

[7]Identification and analysis of major flavor compounds in radish taproots by widely targeted metabolomics. Mei, Shiyong,He, Zhengjin,Zhang, Jifang. 2022

[8]Analyzing the influence of withering degree on the dynamic changes in non-volatile metabolites and sensory quality of Longjing green tea by non-targeted metabolomics. Xujiang Shan,Qinyan Yu,Le Chen,Shan Zhang,Jiayi Zhu,Yongwen Jiang,Haibo Yuan,Qinghua Zhou,Ji Li,Yujie Wang,Yuliang Deng,Jia Li. 2023

[9]A metabolic perspective of selection for fruit quality related to apple domestication and improvement. Qiong Lin,Jing Chen,Xuan Liu,Bin Wang,Yaoyao Zhao,Liao Liao,Andrew C. Allan,Chongde Sun,Yuquan Duan,Xuan Li,Donald Grierson,Julian C. Verdonk,Kunsong Chen,Yuepeng Han,Jinfeng Bi. 2023

[10]The Integration of Metabolomics, Electronic Tongue, and Chromatic Difference Reveals the Correlations between the Critical Compounds and Flavor Characteristics of Two Grades of High-Quality Dianhong Congou Black Tea. Shan Zhang,Xujiang Shan,Linchi Niu,Le Chen,Jinjin Wang,Qinghua Zhou,Haibo Yuan,Jia Li,Tian Wu. 2023

[11]Dynamic changes of key metabolites in Longjing green tea during processing revealed by widely targeted metabolomic profiling and sensory experiments. Lin Zeng,Yan Qing Fu,Ying Gao,Fang Wang,Shuang Liang,Jun Feng Yin,Marie Laure Fauconnier,Lijing Ke,Yong Quan Xu. 2024

[12]Re-rolling treatment in the fermentation process improves the taste and liquor color qualities of black tea. Qincao Chen,Ying Fu,Wenting Heng,Shuai Yu,Feng Xie,Fang Dong,Zhi Lin,Weidong Dai,Haihui Fu. 2024

[13]Effects of processing technology on tea quality analyzed using high-resolution mass spectrometry-based metabolomics. Wang J.,Li Z.. 2024

[14]Analysis of flavor and widely metabolomics differences in black sesame before and after processing. Yini Yang,Linhai Wang,Yunhai Wang,Yuting An,Qi Zhou,Xia Xiang. 2024

[15]Widely targeted metabolomics reveal the distribution of primary and secondary metabolites in pomegranate fruit. Chen, Lina,Liu, Ruitao,Zhu, Juanli,Wang, Luwei,Li, Haoxian,Liu, Junhao,Lu, Zhenhua. 2024

[16]The influence of fixation temperature on Longjing tea taste profile and the underlying non-volatile metabolites changes unraveled by combined analyses of metabolomics and E-tongue. Shan X.,Deng Y.,Niu L.,Chen L.,Zhang S.,Jiang Y.,Yuan H.,Wang Y.,Li J.. 2024

[17]Sensory qualities markers of n-3 PUFA enriched fresh pork meat fattened by linseed oil and selenium methionine. Hui, Teng,Li, Qianqian,Fang, Zhengfeng,Li, Ran,Sun, Yiming,Li, Jianxun,Yang, Yong. 2024

[18]Quantitative non-volatile sensometabolome of Longjing tea and discrimination of taste quality by sensory analysis, large-scale quantitative metabolomics and machine learning. Xujiang Shan,Linchi Niu,Qianting Zhang,Zhizhen Fang,Yuning Feng,Rui Liang,Zhenxing Xu,Shan Zhang,Le Chen,Weidong Dai,Qinghua Zhou,Yongwen Jiang,Haibo Yuan,Jia Li. 2025

[19]Deciphering composition-structure-taste relationship of black tea-infusion via assessments of nanoparticles by centrifugal treatment. Yifan Li,Weichun Pan,Zhihui Feng,Feina Gu,Jianxin Chen,Fang Wang,Jieqiong Wang,Mingming Zhang,Chunmei Li,David Julian McClements,Junfeng Yin. 2025

[20]Multi-scale quality evaluation and geographical origins discrimination of Ankang green tea by intelligent sensory analysis, selenium elemental analysis and quantitative non-volatile sensometabolomics. Feng, Yuning,Niu, Linchi,Zhang, Shan,Shan, Xujiang,Chen, Le,Zhang, Yingbin,Dai, Weidong,Zhou, Qinghua,Jiang, Yongwen,Yuan, Haibo,Li, Jia. 2025

作者其他论文 更多>>