PRACTICAL APPROACH TO DETERMINING SUFFICIENCY OF EXPERIMENTAL SAMPLE OF GAS ANALYTICAL MULTISENSOR MICRO-ARRAYS VECTOR SIGNALS FOR TRAINING ARTIFICIAL NEURAL NETWORK
https://doi.org/10.34822/1999-7604-2021-2-38-46
Abstract
An algorithm for finding a sufficient amount of a representative set of sample data for training artificial neural networks using the numerical parameters of the original sample set is proposed. The algorithm is carried out on the example of analyzing a vector signal generated by a gas analytical multisensor micro-arrays based on a thin SnO2 film when calibrated to the effect of CO, isopropanol, and ethanol in a mixture with air. As a result of the operation of the algorithm, the minimum required volume of the training sample of artificial neural networks was found, which allows achieving a high (more than 99 %) recognition quality. The results show the efficiency of the proposed algorithm.
About the Authors
V. S. Dykin
Yuri Gagarin State Technical University of Saratov, Saratov
Russian Federation
Russian Federation
V. Yu. Musatov
Yuri Gagarin State Technical University of Saratov, Saratov
Russian Federation
Russian Federation
E-mail: vmusatov@mail.ru
A. S. Varezhnikov
Yuri Gagarin State Technical University of Saratov, Saratov
Russian Federation
Russian Federation
V. V. Sysoev
Yuri Gagarin State Technical University of Saratov, Saratov
Russian Federation
Russian Federation
References
1. Kaltenecker C., Grebhahn A., Siegmund N., Apel S. The Interplay of Sampling and Machine Learning for Software Performance Prediction // IEEE Software. 2020. DOI 10.1109/MS.2020.2987024.
2. Ильясов Ф. Н. Репрезентативность результатов опроса в маркетинговом исследовании // Социологические исследования. 2011. № 3. С. 112–116.
3. Fernández A., García S., Herrera F. Addressing the Сlassification with Imbalanced Data: Open Problems and New Challenges on Class Distribution // Lecture Notes in Computer Science. 2011. Р. 1–10. DOI 10.1007/978-3-642-21219-2_1.
4. Мусатов В. Ю., Сысоев В. В. Обработка данных мультисенсорных систем «электронный нос» на основе методов искусственного интеллекта // Системы искусственного интеллекта в мехатронике / под ред. Большакова А. А., Бровковой М. Б., Глазкова В. П. и др. Саратов : Сарат. гос. тех. ун-т. 2015. С. 146–184.
5. Hierlemann A., Gutierrez-Osuna R. Higher-Order Chemical Sensing // Chem Rev. 2008. № 108. P. 563–613.
6. Kiselev I., Sysoev V., Kaikov I., Koronczi I., Tegin R. A. A., Smanalieva J., Sommer M., Ilicali C., Hauptmannl M. On Temporal Stability of Analyte Recognition with E-nose Based on Metal Oxide Sensor Array in Practical Applications // Sensors. 2018. Vol. 18, P. 22.
7. Зайцев Г. Н. Математическая статистика в экспериментальной ботанике. М. : Наука. 1984. 425 c.
8. Хайкин С. Нейронные сети / пер. с англ. М. : Вильямc, 2006. 1104 с.
9. Widrow В., Steams S. D. Adaptive Signal Processing. Englewood Cliffs, NJ : Prentice Hall, 1985. 475 р.
10. Шелухин О. Моделирование информационных систем. M. : Горячая линия – Телеком, 2011. X c.
11. Гайдышев И. Анализ и обработка данных : спец. справочник. СПб. : Питер, 2001. 750 с.
12. Vapnik V., Levin E., Cun Y. L. Measuring the VC-dimension of a Learning Machine // Neural Computation. 1994. Vol. 6. P. 851 –876.
13. Горшков М. К., Шереги Ф. Э. Прикладная социология: методология и методы. М. : Альфа ; ИНФРА-М, 2009. 416 с.
14. Sysoev V. V., Goschnick J., Schneider T., Strelcov E., Kolmakov A. A Gradient Microarray Electronic Nose Based on Percolating SnO2 Nanowire Sensing Elements // Nano Letters. 2007. Vol. 7, Iss. 10. P. 3182–3188. DOI 10.1021/nl071815+.
15. Sysoev V. V., Strelcov E., Kar S., Kolmakov A. The Electrical Characterization of a Multi-electrode Odor Detection Sensor Array Based on the Single SnO2 Nanowire // Thin Solid Films. 2011. Vol. 520. P. 898–903. DOI10.1016/j.tsf.2011.04.179.
16. Sysoev V. V., Strelcov E., Kolmakov A. Multisensor Micro-Arrays Based on Metal Oxide Nanowires for Electronic Nose Applications. Metal Oxide Nanomaterials for Chemical Sensors. Springer : New York, Heidelberg, Dordrecht, London, 2013. Chapter 15. Р. 465–502.
Review
For citations:
Dykin V.S., Musatov V.Yu., Varezhnikov A.S., Sysoev V.V. PRACTICAL APPROACH TO DETERMINING SUFFICIENCY OF EXPERIMENTAL SAMPLE OF GAS ANALYTICAL MULTISENSOR MICRO-ARRAYS VECTOR SIGNALS FOR TRAINING ARTIFICIAL NEURAL NETWORK. Proceedings in Cybernetics. 2021;(2 (42)):38-46. (In Russ.) https://doi.org/10.34822/1999-7604-2021-2-38-46
Views:
159
Email this article 