Classification and Concentration Prediction of VOC Gases Based on Sensor Array with Machine Learning Algorithms

Liu, Yingming1,2,3; Zhao, Changhui1,2,3; Lin, Junqi4; Gong, Huimin1,2,3; Wang, Fei1,2,3

10.1109/NEMS50311.2020.9265606

2020

IEEE 15th International Conference on Nano/Micro Engineered and Molecular System (NEMS)

2474-3747

2474-3755

978-1-7281-7231-6

2020 IEEE 15TH INTERNATIONAL CONFERENCE ON NANO/MICRO ENGINEERED AND MOLECULAR SYSTEM (IEEE NEMS 2020)

295-300

SEP 27-30, 2020

null,null,ELECTR NETWORK

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

In this work, a facile method is proposed to monitor the freshness of meat and fruits by combining a gas sensor array with machine learning algorithms, where the sensor array consists of four commercial metal oxide-based gas sensors. Back-propagation neural net cork (BPNN) is used for gas classification, and the average accuracy can reach 98.8%. To obtain more effective prediction of VOC gas concentration (ethanol, trimethylamine, and ammonia), four algorithms including BPNN, radial basis function neural network (RBFNN), support vector machine (SVM), and hybrid LDA-SVM, which is a combination of SVM and linear discriminant analysis (LDA) are implemented, which are trained with the same training set. By analyzing and comparing the prediction results of these four algorithm models, the RBFNN achieves the peak performance for the concentration predictions of ethanol and ammonia, and the average relative errors are less than 5% and 6.5%, respectively. For trimethylamine (TMA) concentration prediction, the average relative error of RBFNN is equal to 4.41%, which is better than 5.11% of SVM, while the mean absolute error of RBFNN is slightly inferior to SVM. Therefore, the classification accuracy of the gas type by BPNN and the prediction accuracy of gas concentration by RBFNN can meet the requirement of distinguishing the freshness of food.

Conferences

第一 ; 通讯

英语

EI ; CPCI-S

Shenzhen Science and Technology Innovation Conunittee[JCYJ120170412154,126330] ; Guangdong Natural Science Funds for Distinguished Young Scholar[2016A030306042] ; Department of Science and Technology of Guangdong Province[2018A050506001]

Engineering ; Science & Technology - Other Topics

Engineering, Electrical & Electronic ; Nanoscience & Nanotechnology

WOS:000722588100050

20210109712546

Ammonia ; Backpropagation ; Chemical sensors ; Discriminant analysis ; Errors ; Ethanol ; Forecasting ; Gas detectors ; Gases ; Learning systems ; Metals ; Nanosensors ; Predictive analytics ; Radial basis function networks

Computer Software, Data Handling and Applications:723 ; Artificial Intelligence:723.4 ; Nanotechnology:761 ; Chemistry:801 ; Organic Compounds:804.1 ; Inorganic Compounds:804.2 ; Accidents and Accident Prevention:914.1 ; Statistical Methods:922 ; Solid State Physics:933

Web of Science

1.Southern Univ Sci & Technol, Sch Microelect, Shenzhen 518055, Peoples R China
2.Southern Univ Sci & Technol, GaN Device Engn Technol Res Ctr Guangdong, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Engn Res Ctr Integrated Circuits Next Generat Com, Minist Educ, Shenzhen 518055, Peoples R China
4.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China

Liu, Yingming,Zhao, Changhui,Lin, Junqi,et al. Classification and Concentration Prediction of VOC Gases Based on Sensor Array with Machine Learning Algorithms[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2020:295-300.