A Machine Learning Method for the Quality Detection of Base Liquor and Commercial Liquor Using Multidimensional Signals from an Electronic Nose

Chinese liquor is a world-famous beverage with a long history. Base liquor, a product of liquor brewing, significantly affects the flavor and quality of commercial liquor. In this study, a machine learning method consisting of a deep residual network (ResNet)18 backbone with a light gradient boosting machine (LightGBM) classifier (ResNet-GBM) is proposed for the quality identification of base liquor and commercial liquor using multidimensional signals from an electronic nose (E-Nose). Ablation experiments are conducted to analyze the contribution of the framework’s components. Five evaluation metrics (accuracy, sensitivity, precision, F1 score, and kappa score) are used to verify the performance of the proposed method, and six other frameworks (support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), multidimensional scaling-support vector machine (MDS-SVM), and back-propagation neural network (BPNN)) on three datasets (base liquor, commercial liquor, and mixed base and commercial liquor datasets). The experimental results demonstrate that the proposed ResNet-GBM model achieves the best performance for identifying base liquor and commercial liquors with different qualities. The proposed framework has the highest F1 score for the identification of commercial liquor in the mixed dataset due to the contribution of similar microconstituents from the base liquor. The proposed method can be used for the quality control of Chinese liquor and promotes the practical application of E-nose devices.

[1]  Lijiao Li,et al.  Chinese Baijiu: The Perfect Works of Microorganisms , 2022, Frontiers in Microbiology.

[2]  Lingchang Wang,et al.  Dynamic changes of volatile compounds and bacterial diversity during fourth to seventh rounds of Chinese soy sauce aroma liquor , 2021, Food science & nutrition.

[3]  Chi-Tang Ho,et al.  Rapid qualitative and quantitative analysis of strong aroma base liquor based on SPME-MS combined with chemometrics , 2021 .

[4]  Angus K. Y. Wong,et al.  Channel Attention Convolutional Neural Network for Chinese Baijiu Detection With E-Nose , 2021, IEEE Sensors Journal.

[5]  Tatsuro Yamane,et al.  Automatic detection method of cracks from concrete surface imagery using two‐step light gradient boosting machine , 2020, Comput. Aided Civ. Infrastructure Eng..

[6]  Qing Li,et al.  A Suppression Method of Concentration Background Noise by Transductive Transfer Learning for a Metal Oxide Semiconductor-Based Electronic Nose , 2020, Sensors.

[7]  Aili Wang,et al.  A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet , 2020, Sensors.

[8]  Lifeng Wu,et al.  Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data , 2019, Agricultural Water Management.

[9]  Xiaoran Wang,et al.  A Multitask Learning Framework for Multi-Property Detection of Wine , 2019, IEEE Access.

[10]  Yu Gu,et al.  Bionic Electronic Nose Based on MOS Sensors Array and Machine Learning Algorithms Used for Wine Properties Detection , 2018, Sensors.

[11]  Bing Tu,et al.  Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes , 2019, IEEE Access.

[12]  Baoqi Li,et al.  An Improved ResNet Based on the Adjustable Shortcut Connections , 2018, IEEE Access.

[13]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[14]  Wei Zhao,et al.  Stacked Sparse Auto-Encoders (SSAE) Based Electronic Nose for Chinese Liquors Classification , 2017, Sensors.

[15]  Jun Wang,et al.  The prediction of food additives in the fruit juice based on electronic nose with chemometrics. , 2017, Food chemistry.

[16]  Zhu Zhuowei,et al.  Year prediction of a mild aroma Chinese liquors based on fluorescence spectra and simulated annealing algorithm , 2017 .

[17]  Yu Gu,et al.  Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier , 2017, Sensors.

[18]  H. S. Ramaswamy,et al.  Characterization of Chinese liquor aroma components during aging process and liquor age discrimination using gas chromatography combined with multivariable statistics , 2017, Scientific Reports.

[19]  Yu Gu,et al.  A 3D CFD Simulation and Analysis of Flow-Induced Forces on Polymer Piezoelectric Sensors in a Chinese Liquors Identification E-Nose , 2016, Sensors.

[20]  Yu Zhou,et al.  A portable E-nose system for classification of Chinese liquor , 2015, 2015 IEEE SENSORS.

[21]  Wei Li,et al.  Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification. , 2014, The Review of scientific instruments.

[22]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[23]  Zhao Li,et al.  Application of Vis/NIR Spectroscopy for Chinese Liquor Discrimination , 2014, Food Analytical Methods.

[24]  T M Dymerski,et al.  Invited review article: an odor-sensing system--powerful technique for foodstuff studies. , 2011, The Review of scientific instruments.

[25]  H. Abdi,et al.  Principal component analysis , 2010 .

[26]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[27]  Markus Ringnér,et al.  What is principal component analysis? , 2008, Nature Biotechnology.