A novel Kohonen one-class method for quality control of tea coupled with artificial lipid membrane taste sensors

The effective outlier detection method is an important technique in the process of product quality monitoring. In this work, a novel Kohonen one-class model coupled with artificial lipid membrane taste sensors was proposed for tea quality control. Firstly, the taste information of five different grades of Tieguanyin tea was obtained based on the artificial lipid membrane sensors. Secondly, an improved Kohonen model based on the average Hausdorff distance was proposed to enhance the matching degree and transform the multi-class model into a one-class model. Thirdly, a rejection rate was proposed to optimize the domain boundary, which affected the classification performance. Finally, the F1-score was introduced to evaluate the classification performance of the one-class model. The results indicated that the F1-scores for five different grades of Tieguanyin tea were 0.952, 0.947, 0.952, 1 and 0.947, respectively, and an average F1-score of 0.9596 was obtained. This study shows that the novel Kohonen one-class model coupled with the artificial lipid membrane taste sensors can be used as an effective outlier detection method for quality control of tea.

[1]  İbrahim Gülseren,et al.  Influence of phenolic profile on the RP-HPLC detection and anti-carcinogenic potential of cherry laurel extracts from Black Sea Region-Turkey , 2019, Microchemical Journal.

[2]  Zhongliang Jing,et al.  Study on an improved Hausdorff distance for multi-sensor image matching , 2012 .

[3]  Dejiang Ni,et al.  The new insight into the influence of fermentation temperature on quality and bioactivities of black tea , 2020 .

[4]  Xujun Zhu,et al.  Effects of geographic locations and topographical factors on secondary metabolites distribution in green tea at a regional scale , 2020 .

[5]  Huanhuan Li,et al.  Measurement of total free amino acids content in black tea using electronic tongue technology coupled with chemometrics , 2020 .

[6]  Bartosz Krawczyk,et al.  Diversity measures for one-class classifier ensembles , 2014, Neurocomputing.

[7]  Ker-I Ko.  On the complexity of computing the Hausdorff distance , 2013, J. Complex..

[8]  Yan Shi,et al.  Electronic nose sensors data feature mining: a synergetic strategy for the classification of beer , 2018 .

[9]  Mia Hubert,et al.  Robustness and Outlier Detection in Chemometrics , 2006 .

[10]  Hewei Meng,et al.  Rapid determination by near infrared spectroscopy of theaflavins-to-thearubigins ratio during Congou black tea fermentation process. , 2018, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[11]  Jun Wang,et al.  Rapid identification of tea quality by E-nose and computer vision combining with a synergetic data fusion strategy , 2019, Journal of Food Engineering.

[12]  Vural Gökmen,et al.  Investigation of free amino acids, bioactive and neuroactive compounds in different types of tea and effect of black tea processing , 2020 .

[13]  Nobuyuki Hayashi,et al.  Objective evaluation methods for the bitter and astringent taste intensities of black and oolong teas by a taste sensor , 2013 .

[14]  E R LALONDE,et al.  Number and distribution of taste buds on the epiglottis, pharynx, larynx, soft palate and uvula in a human newborn , 1961, The Anatomical record.

[15]  Katarzyna Radecka,et al.  Respiration Disorders Classification With Informative Features for m-Health Applications , 2016, IEEE Journal of Biomedical and Health Informatics.

[16]  Dezheng Zhang,et al.  A Framework for the Multi-Level Fusion of Electronic Nose and Electronic Tongue for Tea Quality Assessment , 2017, Sensors.

[17]  Lloyd R. Snyder,et al.  Dr. Joseph Jack Kirkland (1925–2016) , 2016, Chromatographia.

[18]  W. Cai,et al.  An improved boosting partial least squares method for near-infrared spectroscopic quantitative analysis. , 2010, Analytica chimica acta.

[19]  Shengzhi Shao,et al.  Predictive geographical authentication of green tea with protected designation of origin using a random forest model , 2020 .

[20]  Yong-xing Zhu,et al.  Original article A review of recent studies in China on the possible beneficial health effects of tea , 2006 .

[21]  Santanu Ghorai,et al.  Feature Fusion for Prediction of Theaflavin and Thearubigin in Tea Using Electronic Tongue , 2017, IEEE Transactions on Instrumentation and Measurement.

[22]  Jun Wang,et al.  The qualitative and quantitative assessment of tea quality based on E-nose, E-tongue and E-eye combined with chemometrics. , 2019, Food chemistry.

[23]  Luqing Li,et al.  Highly discriminant rate of Dianhong black tea grades based on fluorescent probes combined with chemometric methods. , 2019, Food chemistry.

[24]  Ping Zhong,et al.  A new one-class SVM based on hidden information , 2014, Knowl. Based Syst..

[25]  Dongyun Zheng,et al.  A novel needle trap device coupled with gas chromatography for determination of five fatty alcohols in tea samples , 2018 .

[26]  Ning Yang,et al.  Tea diseases detection based on fast infrared thermal image processing technology. , 2019, Journal of the science of food and agriculture.

[27]  Alessandra Biancolillo,et al.  Near infrared (NIR) spectroscopy-based classification for the authentication of Darjeeling black tea , 2019, Food Control.

[28]  Yan Shi,et al.  Fuzzy Evaluation Output of Taste Information for Liquor Using Electronic Tongue Based on Cloud Model , 2020, Sensors.

[29]  Bipan Tudu,et al.  Tea Quality Prediction by Sparse Modeling of Electronic Tongue Signals , 2019, IEEE Transactions on Instrumentation and Measurement.

[30]  Juan Peng,et al.  Development of an icELISA and Immunochromatographic Assay for Methyl-3-Quinoxaline-2-Carboxylic Acid Residues in Fish , 2017, Food Analytical Methods.

[31]  R. Bandyopadhyay,et al.  Estimation of theaflavin content in black tea using electronic tongue , 2012 .

[32]  Jingjing Xu,et al.  Geographical Origin Discrimination of Oolong Tea (TieGuanYin, Camellia sinensis (L.) O. Kuntze) Using Proton Nuclear Magnetic Resonance Spectroscopy and Near-Infrared Spectroscopy , 2017, Food Analytical Methods.

[33]  Xiangfei Song,et al.  Geographical origin traceability of tea based on multi-element spatial distribution and the relationship with soil in district scale , 2018, Food Control.

[34]  Jing Guo,et al.  Multi-Track Friction Stir Lap Welding of 2024 Aluminum Alloy: Processing, Microstructure and Mechanical Properties , 2016 .

[35]  Teuvo Kohonen,et al.  Self-organizing neural projections , 2006, Neural Networks.

[36]  Niranjan Panigrahi,et al.  Rapid assessment of black tea quality using diffuse reflectance spectroscopy , 2016 .

[37]  Hiromasa Kaneko.  Automatic outlier sample detection based on regression analysis and repeated ensemble learning , 2018 .

[38]  Shaveta Sood,et al.  Green Tea Catechins: Role in Oral Health and Disease. An Overview , 2015 .

[39]  Yuefeng Yao,et al.  Phytochemical comparison of different tea (Camellia sinensis) cultivars and its association with sensory quality of finished tea , 2020 .

[40]  Lan Du,et al.  Target Discrimination for SAR ATR Based on Scattering Center Feature and K-center One-Class Classification , 2018, IEEE Sensors Journal.

[41]  Solange Cadore,et al.  Arsenic species in herbal tea leaves and infusions determination by HPLC-ICP-MS , 2018, LWT.

[42]  Yan Shi,et al.  A deep feature mining method of electronic nose sensor data for identifying beer olfactory information , 2019 .

[43]  Jie-wen Zhao,et al.  Sensory quality evaluation for appearance of needle-shaped green tea based on computer vision and nonlinear tools , 2017, Journal of Zhejiang University-SCIENCE B.

[44]  Jieqing Li,et al.  Geographical traceability of wild Boletus edulis based on data fusion of FT-MIR and ICP-AES coupled with data mining methods (SVM). , 2017, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[45]  Xueguang Shao,et al.  Detecting influential observations by cluster analysis and Monte Carlo cross-validation. , 2010, The Analyst.