A Method for Judging the Fermentation Quality of Congou Based on Hyperspectral
YANG Chong-shan1,2, DONG Chun-wang2*, JIANG Yong-wen2, AN Ting1,2, ZHAO Yan1*
1. School of Mechanical and Electrical Engineering, Shihezi University,Shihezi 832000,China
2. Tea Research Institute, Chinese Academy of Agricultural Sciences,Hangzhou 310008,China
Abstract:Fermentation is a crucial process that affects the quality of black tea. The quality of fermentation is mainly judged on artificial experience, hence making it difficult to accomplish an accurate and objective evaluation. The objective of this study is to investigate the fermentation quality of Congou at different times and temperatures using non-destructive techniques and intelligent discrimination methods (chemometrics). For this purpose, different congou fermentation samples were prepared at different fermentation timings. Thereafter, these samples under went testing by hyperspectral detection technology and chemometrics methods. First, the hyperspectral imager (400~1 000 nm) was used to collect the hyperspectral data of Congou fermentation samples. Next, according to the on-site production information, such as temperature, tea tenderness, withering condition, rolling process, fermentation leaf color, aroma, and so on, six different fermentation samples under different time series were divided into three categories according to the degree of fermentation (light, moderate, and excessive fermentation). Standard normal variate (SNV) and multiple scatter correction (MSC) were selected to preprocess the full-band spectrum.Principal components analysis (PCA) was applied to the preprocessed spectral data to obtain the three-dimensional load maps of the first three principal components (PCs). Thereafter, a better SNV preprocessing method was selected according to the spatial distribution characteristics of the samples in the map. The k-nearest neighbor (KNN), random forests (RF), and extreme learning machine (ELM) discriminant models were established by using the optimal PCs of the full-band spectrum as the model input.The recognition rates of KNN, RF, and ELM were 63.89%, 94.44%, and 86.11%, respectively. The results showed that the recognition rate of the non-linear model (RF, ELM) was higher, and the performance of the RF model was better than that of the ELM model. 31 characteristic wavelengths were extracted by successive projections algorithm (SPA) for PCA dimension reduction.The SPA-KNN, SPA-RF and SPA-ELM discriminant models were constructed, and their recognition rates were 83.33%, 91.67%, and 91.67%, respectively. After the variables were screened by SPA, the performances of SPA-KNN and SPA-ELM models were found to be significantly improved, and the recognition accuracy of the SPA-RF model was slightly decreased. As compared with the model established by the characteristic wavelength, the RF model established in the whole band showed the best performance, and the discrimination rates of light fermentation, moderate fermentation and excessive fermentation of Congoureached at 100%, 83.33%, and 83.33%, respectively. The research results provided a theoretical and scientific basis for advancing the realization of intelligent and digital processing of black tea.
基金资助: National Natural Science Foundation of China(31972466), Special Projects for Basic Scientific Research Business of Central Institutes(1610212016018)
作者简介: YANG Chong-shan, (1995—), Postgraduate of School of Mechanical and Electrical Engineering, Shihezi University
e-mail:1029345485@qq.com
引用本文:
杨崇山,董春旺,江用文,安 霆,赵 岩. 基于高光谱的工夫红茶发酵品质程度判别方法[J]. 光谱学与光谱分析, 2021, 41(04): 1320-1328.
YANG Chong-shan, DONG Chun-wang, JIANG Yong-wen, AN Ting, ZHAO Yan. A Method for Judging the Fermentation Quality of Congou Based on Hyperspectral. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1320-1328.
[1] JIANG Yong-wen,HUA Jin-jie,YUAN Hai-bo,et al. Food Science,2018,39(20):71.
[2] Qu F F,Zeng W C,Tong X,et al. LWT-Food Science and Technology,2020,117.
[3] HUANG Yu-ping,LIU Ying,YANG Yu-tu,et al. Spectroscopy and Spectral Analysis,2019,39(11):3585.
[4] Liu Y,Li M,Wang S W,et al. Journal of the Science of Food and Agriculture,2020,100(4).
[5] Tian X,Fan S X,Huang W H,et al. Postharvest Biology and Technology,2020,161.
[6] Yuan L,Yan P,Han W Y,et al. Computers and Electronics in Agriculture,2019,167.
[7] Farahmand B,Jitendra P,Chyngyz E. Postharvest Biology and Technology,2020,162.
[8] Ruben-Van D,Koen M,Kurt H,et al. Computers and Electronics in Agriculture,2020,168.
[9] Dong C W,Zhu H G,Wang J J,et al . Food Science and Biotechnology,2017,26(4).
[10] DONG Chun-wang,LIANG Gao-zhen,AN Ting,et al. Journal of Agricultural Engineering,2018,34(24):306.
[11] Zhu S L,Chao M N,Zhang J Y,et al. Sensors (Basel, Switzerland),2019,19(23).
[12] Arvind P R,Rao N,Debashis P,et al. Electronic Journal of Statistics,2020,14(1).
[13] SONG Tao,SONG Jun,LIU Yao-min,et al. Food Science,2015,36(24):260.
[14] Utrilla-Vázquez M,Rodríguez-Campos J,Avendaño-Arazate H C,et al. Food Research International,2020,129.
[15] Gerhardt N,Sebastian S,Sascha R,Pérez-Cacho P R,et al. Food Chemistry,2019,286.
[16] Tan K,Wang H M,Chen L H. Journal of Hazardous Materials,2020,382.
[17] NI Chao,LI Zhen-ye,ZHANG Xiong,et al. Journal of Agricultural Machinery,20191025.1317.011.html.