Article 2121

Title of the article

Multi-criteria neural network estimation of correlation coefficients for processing small samples of biometric data 

Authors

Aleksandr I. Ivanov, Doctor of engineering sciences, associate professor, scientific adviser, Penza Research Electrotechnical Institute (9 Sovetskaya street, Penza, Russia), E-mail: ivan@pniei.penza.ru
Yuliya I. Serikova, Postgraduate student, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: julia-ska@yandex.ru
Tat'yana A. Zolotareva, Senior lecturer of the sub-department of informatics, information technology and information security, Lipetsk State Pedagogical University named after P.P. Semyonov-Tyan-Shansky (42 Lenina street, Lipetsk, Russia), E-mail: zolotarevatatyana2016@yandex.ru
Svetlana A. Polkovnikova, Postgraduate student, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: 1996svetlanaserikova@gmail.com 

Index UDK

004.67: 519.7: 57.087.1 

DOI

10.21685/2072-3059-2021-1-2 

Abstract

Background. Over 120 years, Pearson’s criterion has been widely used to calculate correlation coefficients. Unfortunately, its use generates significant errors in calculating the correlation coefficients on small samples. The purpose of this research is to reduce these errors that occur with small samples by increasing the complexity of data processing.
Materials and methods. We consider the reduction of errors in calculating the correlation coefficients by using the large artificial neural networks, trained to predict the values of the correlation coefficients from the relative position of small sample points.
Results. The combined use of the classical Pearson’s formula and the neural network calculation of correlation coefficients can significantly increase the level of confidence in the neural network calculations.
Conclusions. It is noted that training samples of a neural network computer can be obtained from software random data generators and can be large. This allows us to hope for a significant increase in the accuracy of calculating the correlation coefficients. 

Key words

neural network computing, Pearson’s criterion, correlation coefficient, neural network analysis, data independence criteria, small samples 

Download PDF
References

1. Yazov Yu.K., Volchikhin V.I., Ivanov A.I., Funtikov V.A., Nazarov I.G. Neyrosetevaya zashchita personal'nykh biometricheskikh dannykh = Neural network protection of personal biometric data. Moscow: Radiotekhnika, 2012:157. (In Russ.)
2. GOST R 52633.5–2011. Zashchita informatsii. Tekhnika zashchity informatsii. Avtomaticheskoe obuchenie neyrosetevykh preobrazovateley biometriya-kod dostupa = Information security. Information security technology. Automatic training of neural network converters biometrics-access code. Moscow: Standartinform, 2012. (In Russ.)
3. Malygina E.A. Biometriko-neyrosetevaya autentifikatsiya: perspektivy primeneniya setey kvadratichnykh neyronov s mnogourovnevym kvantovaniem biometricheskikh dannykh: preprint = Biometrical neural network authentication: prospects for the application of quadratic neuron networks with multilevel quantization of biometric data: preprint. Penza: Izd-vo PGU, 2020:114. (In Russ.)
4. Ivanov A.I., Bezyaev A.V., Malygina E.A., Serikova Yu.I. The second national standard of Russia for fast automatic training of large artificial neural networks on small samples of biometric data. Bezopasnost' informatsionnykh tekhnologiy: sb. nauch. st. po materialam I Vseros. nauch.-tekhn. konf. (24 aprelya 2019 g.) = Information security: proceedings of the 1st All-Russian scientific and technical conference (April 24, 2019). Penza, 2019:174–177. (In Russ.)
5. Volchikhin V.I., Ivanov A.I., Malygina E.A., Serikova Yu.I. Comparison of the power of two types of artificial neurons enriching biometric data in linear and quadratic spaces. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2018;3:47–57. (In Russ.)
6. Ivanov A.I., Perfilov K.A., Lukin V.S. Neural network generalization of a family of statistical criteria for geometric mean and harmonic mean for precision analysis of small samples of biometric data. Informatsionno-upravlyayushchie telekommunikatsionnye sistemy, sredstva porazheniya i ikh tekhnicheskoe obespechenie: sb. nauch. st. po materialam Vseros. nauch.-tekhn. konf. = Information and control telecommunication systems, weapons and their technical support: proceedings of the All-Russian scientific and technical conference. Penza: AO «NPP "Rubin"», 2019:50–63. (In Russ.)
7. Ivanov A.I., Bannykh A.G., Kupriyanov E.N., Lukin V.S., Perfilov K.A., Savinov K.N. A collection of artificial neurons equivalent to statistical criteria for their combined use in testing the hypothesis of normality of small samples of biometric data technologies. Bezopasnost' informatsionnykh tekhnologiy: sb. nauch. st. po materialam I Vseros. nauch.-tekhn. konf. (24 aprelya 2019 g.) = Information security: proceedings of the 1st All-Russian scientific and technical conference (April 24, 2019). Penza: Izd-vo PGU, 2019:156–164. (In Russ.)
8. Ivanov A.I., Kupriyanov E.N. Zashchita iskusstvennogo intellekta: ortogonalizatsiya statistiko-neyrosetevogo analiza malykh vyborok biometricheskikh dannykh: preprint = Artificial intelligence protection: orthogonalization of statistics-neural network analysis for small samples of biometric data: preprint. Penza: Izd-vo PGU, 2020:72. (In Russ.)
9. Nikolenko S., Kudrin A., Arkhangel'skaya E. Glubokoe obuchenie. Pogruzhenie v mir neyronnykh setey = Deep Learning. Dive into the world of neural networks. Saint-Petersburg: Piter, 2018:480. (In Russ.)
10. Aggarval Charu. Neyronnye seti i glubokoe obuchenie = Neural networks and deep learning. Saint-Petersburg: Dialektika, 2020:756. (In Russ.)
11. Minskiy M.L., Paypert S. Perseptrony = Perceptrons. Moscow: Mir, 1971:242. (In Russ.)
12. Kolmogorov A.N. Representation of continuous functions of several variables by superpositions of continuous functions of fewer variables. Doklady Akademii nauk SSSR = Reports of the USSR Academy of Sciences. 1956;108(2):179–182. (In Russ.)
13. Khaykin S. Neyronnye seti: polnyy kurs = Neural networks: complete course. Moscow: Vil'yams, 2006:1104. (In Russ.)
14. Volchikhin V.I., Ivanov A.I., Akhmetov B.B., Serikova Yu.I. Fractal-correlation functional used when searching for pairs of weakly dependent biometric data in small samples. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2016;4:25–31. (In Russ.)
15. Volchikhin V.I., Ivanov A.I., Serikov A.V., Serikova Yu.I. Quantum superposition of a discrete spectrum of a mathematical molecule states of correlation for small samples of biometric data. Vestnik Mordovskogo universiteta = Bulletin of Mordovian University. 2017;27(2):230–243. (In Russ.)
16. Ivanov A.I., Lozhnikov P.S., Sulavko A.E., Serikova Yu.I. Reducing the requirements for the size of the test sample of biometric data in the transition to the use of multidimensional Bayesian correlation functionals. Infokommunikatsionnye tekhnologii = Infocommunication technologies. 2017;15(2):186–193.
17. Volchikhin V.I., Ivanov A.I., Serikov A.V., Serikova Yu.I. Testing of analog and quantum oracles of linear computational complexity, predicting the values of the correlation  coefficient on a small sample of 32 experiments. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2017;3:70–80. (In Russ.)
18. Ivanov A.I., Zolotareva T.A. Iskusstvennyy intellekt v zashchishchennom ispolnenii: sintez statistiko-neyrosetevykh avtomatov mnogokriterial'noy proverki gipotezy nezavisimosti malykh vyborok biometricheskikh dannykh: preprint = Artificial intelligence in protected design: synthesis of statistical neural network automata for multi-criteria testing of the hypothesis of independence of small samples of biometric data: preprint. Penza: Izd-vo PGU, 2020:105. (In Russ.)
19. Serikov A.V., Kachalin S.V. Correlation molecule with elliptic quantizers for computations on small training samples. Bezopasnost' informatsionnykh tekhnologiy: sb. nauch. st. po materialam I Vseros. nauch.-tekhn. konf. (24 aprelya 2019 g.) = Information technology security: proceedings of the 1st All-Russian scientific and technical conference (April 24, 2019). Penza: Izd-vo PGU, 2019:123–129. (In Russ.)
20. Bezyaev A.V. Biometriko-neyrosetevaya autentifikatsiya: obnaruzhenie i ispravlenie oshibok v dlinnykh kodakh bez nakladnykh raskhodov na izbytochnost': preprint = Biometrical neural network authentication: detecting and correcting errors in long codes without the overhead of redundancy: preprint. Penza: Izd-vo PGU, 2020:40. (In Russ.)
21. Ivanov A.I. Iskusstvennye matematicheskie molekuly: povyshenie tochnosti statisticheskikh otsenok na malykh vyborkakh (programmy na yazyke MathCAD): preprint = Artificial mathematical molecules: improving the accuracy of statistical estimates on small samples (programs in the MathCAD language): preprint. Penza: Izd-vo PGU, 2020:36. (In Russ.)

 

Дата создания: 14.05.2021 10:27
Дата обновления: 14.05.2021 10:41