Cognitive spectroscopy for evaluating Chinese black tea grades (Camellia sinensis): near-infrared spectroscopy and evolutionary algorithms.
black tea
cognitive spectroscopy
evolutionary algorithm
grade
near-infrared spectroscopy
Journal
Journal of the science of food and agriculture
ISSN: 1097-0010
Titre abrégé: J Sci Food Agric
Pays: England
ID NLM: 0376334
Informations de publication
Date de publication:
Aug 2020
Aug 2020
Historique:
received:
25
12
2019
revised:
12
03
2020
accepted:
24
04
2020
pubmed:
25
4
2020
medline:
29
1
2021
entrez:
25
4
2020
Statut:
ppublish
Résumé
Grading represents an essential criterion for the quality assurance of black tea. The main objectives of the study were to develop a highly robust model for Chinese black tea of seven grades based on cognitive spectroscopy. Cognitive spectroscopy was proposed to combine near-infrared spectroscopy (NIRS) with machine learning and evolutionary algorithms, selected feature information from complex spectral data and show the best results without human intervention. The NIRS measuring system was used to obtain the spectra of Chinese black tea samples of seven grades. The spectra acquired were preprocessed by standard normal variate transformation (SNV), multiplicative scatter correction (MSC) and minimum/maximum normalization (MIN/MAX), and the optimal pretreating method was implemented using principal component analysis combined with linear discriminant analysis algorithm. Three feature selection evolutionary algorithms, which were a genetic algorithm (GA), simulated annealing (SA) and particle swarm optimization (PSO), were compared to search the best preprocessed characteristic wavelengths. Cognitive models of Chinese black tea ranks were constructed using extreme learning machine (ELM), K-nearest neighbor (KNN) and support vector machine (SVM) methods based on the selected characteristic variables. Experimental results revealed that the PSO-SVM model showed the best predictive performance with the correlation coefficients of prediction set (R The overall results demonstrated that cognitive spectroscopy could be utilized as a rapid strategy to identify Chinese black tea grades. © 2020 Society of Chemical Industry.
Sections du résumé
BACKGROUND
BACKGROUND
Grading represents an essential criterion for the quality assurance of black tea. The main objectives of the study were to develop a highly robust model for Chinese black tea of seven grades based on cognitive spectroscopy.
RESULTS
RESULTS
Cognitive spectroscopy was proposed to combine near-infrared spectroscopy (NIRS) with machine learning and evolutionary algorithms, selected feature information from complex spectral data and show the best results without human intervention. The NIRS measuring system was used to obtain the spectra of Chinese black tea samples of seven grades. The spectra acquired were preprocessed by standard normal variate transformation (SNV), multiplicative scatter correction (MSC) and minimum/maximum normalization (MIN/MAX), and the optimal pretreating method was implemented using principal component analysis combined with linear discriminant analysis algorithm. Three feature selection evolutionary algorithms, which were a genetic algorithm (GA), simulated annealing (SA) and particle swarm optimization (PSO), were compared to search the best preprocessed characteristic wavelengths. Cognitive models of Chinese black tea ranks were constructed using extreme learning machine (ELM), K-nearest neighbor (KNN) and support vector machine (SVM) methods based on the selected characteristic variables. Experimental results revealed that the PSO-SVM model showed the best predictive performance with the correlation coefficients of prediction set (R
CONCLUSION
CONCLUSIONS
The overall results demonstrated that cognitive spectroscopy could be utilized as a rapid strategy to identify Chinese black tea grades. © 2020 Society of Chemical Industry.
Types de publication
Evaluation Study
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3950-3959Subventions
Organisme : Ministry of Science and Technology of the People's Republic of China
ID : 2017YFD0400805
Organisme : National Key Research and Development Program of China
Informations de copyright
© 2020 Society of Chemical Industry.
Références
Ren G, Fan Q, He X, Li W and Tang X, Applicability of multifunctional preprocessing device for simultaneous estimation of spreading of green tea, withering of black tea and shaking of oolong tea. J Sci Food Agric 100:560-569 (2020).
Ren G, Wang S, Ning J, Xu R, Wang Y, Xing Z et al., Quantitative analysis and geographical traceability of black tea using Fourier transform near-infrared spectroscopy (FT-NIRS). Food Res Int 53:822-826 (2013).
Ouyang Q, Yang Y, Wu J, Liu Z, Chen X, Dong C et al., Rapid sensing of total theaflavins content in black tea using a portable electronic tongue system coupled to efficient variables selection algorithms. J Food Compost Anal 75:43-48 (2019).
Zhang L, Santos JS, Cruz TM, Marques MB, Do Carmo MAV, Azevedo L et al., Multivariate effects of Chinese keemun black tea grades (Camellia sinensis var. sinensis) on the phenolic composition, antioxidant, antihemolytic and cytotoxic/cytoprotection activities. Food Res Int 125:108516-108525 (2019).
Zhu J, Zhu F, Li L, Cheng L, Zhang L, Sun Y et al., Highly discriminant rate of Dianhong black tea grades based on fluorescent probes combined with chemometric methods. Food Chem 298:125046-125052 (2019).
Zhu H, Liu F, Ye Y, Chen L, Liu J, Gui A et al., Application of machine learning algorithms in quality assurance of fermentation process of black tea-based on electrical properties. J Food Eng 263:165-172 (2019).
Liang G, Dong C, Hu B, Zhu H, Yuan H, Jiang Y et al., Prediction of moisture content for Congou black tea withering leaves using image features and nonlinear method. Sci Rep 8:7854-7861 (2018).
Fang S, Ning J, Huang W-J, Zhang G, Deng W-W and Zhang Z, Identification of geographical origin of Keemun black tea based on its volatile composition coupled with multivariate statistical analyses. J Sci Food Agric 99:4344-4352 (2019).
Rocchi R, Mascini M, Faberi A, Sergi M, Compagnone D, Di Martino V et al., Comparison of IRMS, GC-MS and E-nose data for the discrimination of saffron samples with different origin, process and age. Food Control 106:106736 (2019).
Cortés V, Talens P, Barat JM and Lerma-García MJ, Potential of NIR spectroscopy to predict amygdalin content established by HPLC in intact almonds and classification based on almond bitterness. Food Control 91:68-75 (2018).
Wang C, Zhang C-X, Shao C-F, Li C-W, Liu S-H, Peng X-P et al., Chemical fingerprint analysis for the quality evaluation of deepure instant Pu-erh tea by HPLC combined with chemometrics. Food Anal Methods 9:3298-3309 (2016).
Qu F, Zhu X, Ai Z, Ai Y, Qiu F and Ni D, Effect of different drying methods on the sensory quality and chemical components of black tea. LWT - Food Sci Technol 99:112-118 (2019).
Das PR, Kim Y, Hong S-J and Eun J-B, Profiling of volatile and non-phenolic metabolites-amino acids, organic acids, and sugars of green tea extracts obtained by different extraction techniques. Food Chem 296:69-77 (2019).
Jiang H, Xu W and Chen Q, Evaluating aroma quality of black tea by an olfactory visualization system: selection of feature sensor using particle swarm optimization. Food Res Int 126:108605-108611 (2019).
Ikeda T, Kanaya S, Yonetani T, Kobayashi A and Fukusaki E, Prediction of Japanese green tea ranking by Fourier transform near-infrared reflectance spectroscopy. J Agric Food Chem 55:9908-9912 (2007).
Li Y, Sun J, Wu X, Lu B, Wu M and Dai C, Grade identification of Tieguanyin tea using fluorescence hyperspectra and different statistical algorithms. J Food Sci 84:2234-2241 (2019).
Paiva EM, Rohwedder JJR, Pasquini C and Pereira CF, Method for building a portable near infrared photometer based on LEDs and interference filters chosen by a spectral variable selection algorithm. Microchem J 146:842-849 (2019).
Chen H, Lin Z and Tan C, Classification of different animal fibers by near infrared spectroscopy and chemometric models. Microchem J 144:489-494 (2019).
Biancolillo A, Firmani P, Bucci R, Magrì A and Marini F, Determination of insect infestation on stored rice by near infrared (NIR) spectroscopy. Microchem J 145:252-258 (2019).
Dong C, Li J, Wang J, Liang G, Jiang Y, Yuan H et al., Rapid determination by near infrared spectroscopy of theaflavins-to-thearubigins ratio during Congou black tea fermentation process. Spectrochim Acta A Mol Biomol Spectrosc 205:227-234 (2018).
Wang J, Zareef M, He P, Sun H, Chen Q, Li H et al., Evaluation of matcha tea quality index using portable NIR spectroscopy coupled with chemometric algorithms. J Sci Food Agric 99:5019-5027 (2019).
Deng X, Liu Z, Zhan Y, Ni K, Zhang Y, Ma W et al., Predictive geographical authentication of green tea with protected designation of origin using a random forest model. Food Control 107:106807 (2020).
Firmani P, De Luca S, Bucci R, Marini F and Biancolillo A, Near infrared (NIR) spectroscopy-based classification for the authentication of Darjeeling black tea. Food Control 100:292-299 (2019).
Fu X, Xu L, Yu X, Ye Z and Cui H, Robust and automated internal quality grading of a Chinese green tea (Longjing) by near-infrared spectroscopy and chemometrics. J Spectrosc 2013:139347 (2013).
Liu P, Wen Y, Huang J, Xiong A, Wen J, Li H et al., A novel strategy of near-infrared spectroscopy dimensionality reduction for discrimination of grades, varieties and origins of green tea. Vib Spectrosc 105:102984-102991 (2019).
Jiang H, Xu W and Chen Q, Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations. Spectrochim Acta A Mol Biomol Spectrosc 214:366-371 (2019).
Teye E, Amuah CLY, McGrath T and Elliott C, Innovative and rapid analysis for rice authenticity using hand-held NIR spectrometry and chemometrics. Spectrochim Acta A Mol Biomol Spectrosc 217:147-154 (2019).
Jain S, Shukla S and Wadhvani R, Dynamic selection of normalization techniques using data complexity measures. Expert Syst Appl 106:252-262 (2018).
Ning J, Sheng M, Yi X, Wang Y, Hou Z, Zhang Z et al., Rapid evaluation of soil fertility in tea plantation based on near-infrared spectroscopy. Spectrosc Lett 51:463-471 (2018).
Zhu J, Ahmad W, Xu Y, Liu S, Chen Q, Hassan MM et al., Development of a novel wavelength selection method for the trace determination of chlorpyrifos on Au@Ag NPs substrate coupled surface-enhanced Raman spectroscopy. Analyst 144:1167-1177 (2019).
Xu Y, Kutsanedzie FYH, Sun H, Wang M, Chen Q, Guo Z et al., Rapid pseudomonas species identification from chicken by integrating colorimetric sensors with near-infrared spectroscopy. Food Anal Meth 11:1199-1208 (2018).
Kirkpatrick S, Optimization by simulated annealing: quantitative studies. J Stat Phys 34:975-986 (1984).
Ye D, Sun L, Tan W, Che W and Yang M, Detecting and classifying minor bruised potato based on hyperspectral imaging. Chemom Intell Lab Syst 177:129-139 (2018).
Wu Q and Peng C, A hybrid BAG-SA optimal approach to estimate energy demand of China. Energy 120:985-995 (2017).
Sodeifian G, Sajadian SA and Saadati Ardestani N, Experimental optimization and mathematical modeling of the supercritical fluid extraction of essential oil from Eryngium billardieri: application of simulated annealing (SA) algorithm. J Supercrit Fluid 127:146-157 (2017).
Pu H, Song T, Schonfeld P, Li W, Zhang H, Hu J et al., Mountain railway alignment optimization using stepwise & hybrid particle swarm optimization incorporating genetic operators. Appl Soft Comput 78:41-57 (2019).
Khulal U, Zhao J, Hu W and Chen Q, Comparison of different chemometric methods in quantifying total volatile basic-nitrogen (TVB-N) content in chicken meat using a fabricated colorimetric sensor array. RSC Adv 6:4663-4672 (2016).
Xia C, Yang S, Huang M, Zhu Q, Guo Y and Qin J, Maize seed classification using hyperspectral image coupled with multi-linear discriminant analysis. Infrared Phys Techn 103:103077 (2019).
Esteki M, Shahsavari Z and Simal-Gandara J, Use of spectroscopic methods in combination with linear discriminant analysis for authentication of food products. Food Control 91:100-112 (2018).
Li L, Xie S, Ning J, Chen Q and Zhang Z, Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems. J Sci Food Agric 99:1787-1794 (2019).
Sabanci K, Detection of sunn pest-damaged wheat grains using artificial bee colony optimization-based artificial intelligence techniques. J Sci Food Agric 100:817-824 (2020).
Xu W, Jiang H, Liu T, He Y and Chen Q, Qualitative discrimination of yeast fermentation stages based on an olfactory visualization sensor system integrated with a pattern recognition algorithm. Anal Methods 11:3294-3300 (2019).
Yan L, Liu C, Qu H, Liu W, Zhang Y, Yang J et al., Discrimination and measurements of three flavonols with similar structure using terahertz spectroscopy and chemometrics. J Infrared Millim Te 39:492-504 (2018).
Deng Z, Zhu X, Cheng D, Zong M and Zhang S, Efficient kNN classification algorithm for big data. Neurocomputing 195:143-148 (2016).
Singh SK, Vidyarthi SK and Tiwari R, Machine learnt image processing to predict weight and size of rice kernels. J Food Eng 274:109828 (2020).
Wang S, Liu S, Che X, Wang Z, Zhang J and Kong D, Recognition of polycyclic aromatic hydrocarbons using fluorescence spectrometry combined with bird swarm algorithm optimization support vector machine. Spectrochim Acta A Mol Biomol Spectrosc 224:117404 (2020).
Zhang J, Liu S and Wang Y, Gene association study with SVM MLP and cross-validation for the diagnosis of diseases. Prog Nat Sci 18:741-750 (2008).