Preview

Proceedings of the Voronezh State University of Engineering Technologies

Advanced search

Automation of recognition of chemicals using electronic sensor technology based on neural network data processing

https://doi.org/10.20914/2310-1202-2019-3-180-186

Abstract

The composition of the initial substance was determined using an electronic sensor “electronic nose”, consisting of 8 sensors, to which air was supplied with a syringe with alcohol vapor containing various kinds of impurities. The signal from the sensors was recorded with a sampling frequency of 1 s for 120 s. The output of the device was presented in two different interpretations - in the form of curves obtained from each sensor, or the areas under the curves. The purpose of the work is to build a recognition system for 11 impurities and water in the starting material. The composition of the initial substance was determined using an “electronic nose”, which allows one to obtain 120 values from each of 8 sensors in the form of curves or the values of the areas under the curves. A large number of classes (12), the dynamic presentation of the source data information make it advisable to build a pattern recognition system based on a neural network - a multilayer perceptron trained on the basis of the error back propagation algorithm. When training the network, existing samples are used, indicating which class they belong to. The properties of each analyte are represented as a vector of 120 values of 8 attributes defining one of 12 classes. To reduce the dimensionality of the input data of the neural network, the authors proposed the use of convolution of the available information without significant loss of information capacity of signs by constructing 8 polynomial regressions of the 19th order that describe the curves from each of the 8 sensors of the “electronic nose”. The input matrix obtained as a result of convolution consisted of 20 polynomial regression coefficients of each of 8 curves for 12 classes under consideration. A two-layer neural network with 43 neurons and a sigmoidal activation function in the hidden layer and 12 neurons and a linear activation function in the output layer was constructed. As a result of network training, 2 classification errors were obtained, which allows us to use the approach proposed by the authors to build a recognition system based on preliminary convolution of data dynamically obtained from the “electronic nose”

About the Authors

E. A. Balashova
Voronezh State University of Engineering Technologies
Russian Federation
Cand. Sci. (Engin.), associate professor, ,, Revolution Av., 19 Voronezh, 394036, Russia


V. V. Bityukova
Voronezh State Medical University named after N.N. Burdenko
Dr. Sci. (Med.), professor, obstetrics and gynecology IAPE, Zdoroviya lane, 2, Voronezh, 394024, Russia


A. A. Khvostov
Military Research Center of the Air Force “Air Force Academy named after prof. N.E. Zhukovsky and Yu.A. Gagarina”
Dr. Sci. (Engin.), professor, math department, Old Bolsheviks st., 54 A, Voronezh, 394064, Russia


References

1. Omatu S., Mitsuaki Y. E-nose system by using neural networks. Neurocomputing. 2016. vol. 172. pp. 394–398.

2. Nikitina S.Yu., Kuchmenko T.A., Rudakov O.B., Drozdova E.V. Application of the “electronic nose” technique to assess the quality of food ethanol. Bulletin of the Voronezh State University. Series: Chemistry. Biology. Pharmacy. 2015. no. 1. pp. 26–35. (in Russian).

3. Problems of analytical chemistry. Vol. 14. Chemical sensors: monograph; ed. Yu.G. Vlasov. Moscow, Nauka, 2011. 399 p. (in Russian).

4. Bolshakova L.V., Primakin A.I., Yakovleva A.N. The use of cluster and discriminant analyzes in the processing and interpretation of statistical data while ensuring economic and information security of an economic entity. Bulletin of the St. Petersburg University of the Ministry of Internal Affairs of Russia. 2014. no. 2 (62). pp. 148–156. (in Russian).

5. Al'-Khashedi A.A., Obadi A.A., Nuriev N.K. Development of mathematical and software for pattern recognition problems based on the perceptron. Bulletin of Kazan Technological University. 2017. vol. 20. no. 11. pp. 85–88. (in Russian).

6. Karpov A.S. Comparison of neural network training methods for image recognition. Bulletin of modern studies 2017. no. 6–1 (9). pp. 122–123. (in Russian).

7. Vijayaditya P., Povey D., Khudanpur S. A time delay neural network architecture for efficient modeling of long temporal contexts. Sixteenth Annual Conference of the International Speech Communication Association. 2015.

8. Dai W., Dai C., Qu S., Li J. et al. Very deep convolutional neural networks for raw waveforms. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017. doi: 10.1109/ICASSP.2017.7952190

9. Sainath T.N., Vinyals O., Senior A., Sak H. Convolutional, long short-term memory, fully connected deep neural networks. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2015. doi: 10.1109/ICASSP.2015.7178838

10. Szulczy?ski B. et al. Determination of odour interactions in gaseous mixtures using electronic nose methods with artificial neural networks. Sensors. 2018. vol. 18. no. 2. pp. 519. doi: 10.3390/s18020519

11. Jing Y.-Q., Meng Q.-H., Qi P.-F., Cao M.-L. et al. A bioinspired neural network for data processing in an electronic nose. IEEE Transactions on Instrumentation and Measurement 2016. vol. 65. no. 10. pp. 2369–2380. doi: 10.1109/TIM.2016.2578618


Review

For citations:


Balashova E.A., Bityukova V.V., Khvostov A.A. Automation of recognition of chemicals using electronic sensor technology based on neural network data processing. Proceedings of the Voronezh State University of Engineering Technologies. 2019;81(3):180-186. (In Russ.) https://doi.org/10.20914/2310-1202-2019-3-180-186

Views: 569


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2226-910X (Print)
ISSN 2310-1202 (Online)