A Convolutional Neural Network Based Auto Features Extraction Method for Tea Classification with Electronic Tongue

Feature extraction is a key part of the electronic tongue system. Almost all of the existing features extraction methods are “hand-crafted”, which are difficult in features selection and poor in stability. The lack of automatic, efficient and accurate features extraction methods has limited the application and development of electronic tongue systems. In this work, a convolutional neural network-based auto features extraction strategy (CNN-AFE) in an electronic tongue (e-tongue) system for tea classification was proposed. First, the sensor response of the e-tongue was converted to time-frequency maps by short-time Fourier transform (STFT). Second, features were extracted by convolutional neural network (CNN) with time-frequency maps as input. Finally, the features extraction and classification results were carried out under a general shallow CNN architecture. To evaluate the performance of the proposed strategy, experiments were held on a tea database containing 5100 samples for five kinds of tea. Compared with other features extraction methods including features of raw response, peak-inflection point, discrete cosine transform (DCT), discrete wavelet transform (DWT) and singular value decomposition (SVD), the proposed model showed superior performance. Nearly 99.9% classification accuracy was obtained and the proposed method is an approximate end-to-end features extraction and pattern recognition model, which reduces manual operation and improves efficiency.

[1]  Jun Wang,et al.  The measurement principles, working parameters and configurations of voltammetric electronic tongues and its applications for foodstuff analysis , 2018 .

[2]  Julian W. Gardner,et al.  Effect of micro-electrode geometry on response of thin-film poly(pyrrole) and poly(aniline) chemoresistive sensors , 1999 .

[3]  Shie Mannor,et al.  A Tutorial on the Cross-Entropy Method , 2005, Ann. Oper. Res..

[4]  Christian Igel,et al.  A Unified View on Multi-class Support Vector Classification , 2016, J. Mach. Learn. Res..

[5]  Santanu Ghorai,et al.  Tea Quality Prediction by Autoregressive Modeling of Electronic Tongue Signals , 2016, IEEE Sensors Journal.

[6]  S. Lemos,et al.  A simple voltammetric electronic tongue for the analysis of coffee adulterations. , 2019, Food chemistry.

[7]  Y. Zuo,et al.  Simultaneous determination of catechins, caffeine and gallic acids in green, Oolong, black and pu-erh teas using HPLC with a photodiode array detector. , 2002, Talanta.

[8]  Ingemar Lundström,et al.  Drinking water monitoring with voltammetric sensors , 2011 .

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Ram Bilas Pachori,et al.  Cross-terms reduction in the Wigner-Ville distribution using tunable-Q wavelet transform , 2016, Signal Process..

[11]  A. K. Bag,et al.  Monitoring the Fermentation Process and Detection of Optimum Fermentation Time of Black Tea Using an Electronic Tongue , 2015, IEEE Sensors Journal.

[12]  Mehrtash Tafazzoli Harandi,et al.  Going deeper into action recognition: A survey , 2016, Image Vis. Comput..

[13]  Runu Banerjee Roy,et al.  Black tea classification employing feature fusion of E-Nose and E-Tongue responses , 2019, Journal of Food Engineering.

[14]  Ammar Zakaria,et al.  A Bio-Inspired Herbal Tea Flavour Assessment Technique , 2014, Sensors.

[15]  Jun Wang,et al.  Comparison of random forest, support vector machine and back propagation neural network for electronic tongue data classification: Application to the recognition of orange beverage and Chinese vinegar , 2013 .

[16]  A. G. González,et al.  Pattern recognition procedures for differentiation of Green, Black and Oolong teas according to their metal content from inductively coupled plasma atomic emission spectrometry. , 2001, Talanta.

[17]  C. Natale,et al.  Electronic tongue: new analytical tool for liquid analysis on the basis of non-specific sensors and methods of pattern recognition , 2000 .

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

[19]  Shaoping Deng,et al.  Multifrequency large amplitude pulse voltammetry: A novel electrochemical method for electronic tongue , 2007 .

[20]  Santanu Ghorai,et al.  A Novel Technique of Black Tea Quality Prediction Using Electronic Tongue Signals , 2014, IEEE Transactions on Instrumentation and Measurement.

[21]  Patrick Flandrin,et al.  On Phase-Magnitude Relationships in the Short-Time Fourier Transform , 2012, IEEE Signal Processing Letters.

[22]  Richard Hans Robert Hahnloser,et al.  correction: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[23]  C Di Natale,et al.  Direct and two-stage data analysis procedures based on PCA, PLS-DA and ANN for ISE-based electronic tongue-Effect of supervised feature extraction. , 2005, Talanta.

[24]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[25]  Davide Ballabio,et al.  Prediction of Italian red wine sensorial descriptors from electronic nose, electronic tongue and spectrophotometric measurements by means of Genetic Algorithm regression models , 2007 .

[26]  Jun Wang,et al.  The evaluation of sugar content and firmness of non-climacteric pears based on voltammetric electronic tongue , 2013 .

[27]  Jin Jiang,et al.  Time-frequency feature representation using energy concentration: An overview of recent advances , 2009, Digit. Signal Process..

[28]  Bipan Tudu,et al.  Artificial flavor perception of black tea using fusion of electronic nose and tongue response: A Bayesian statistical approach , 2014 .

[29]  Heiko Ulmer,et al.  Sensor arrays with only one or several transducer principles? The advantage of hybrid modular systems , 2000 .

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

[31]  I. Lundström,et al.  A hybrid electronic tongue. , 2000 .

[32]  Daniel Cozzolino,et al.  Instrumental methods (spectroscopy, electronic nose, and tongue) as tools to predict taste and aroma in beverages: advantages and limitations. , 2013, Chemical reviews.

[33]  Zhiwei Zhu,et al.  Classification of Rice by Combining Electronic Tongue and Nose , 2015, Food Analytical Methods.

[34]  Alisa Rudnitskaya,et al.  Cross-sensitivity of chalcogenide glass sensors in solutions of heavy metal ions , 1996 .

[35]  Zhonghua Tang,et al.  Gas chromatography mass spectrometry–based metabolite profiling of two sweet-clover vetches via multivariate data analyses , 2017 .