Article 1117

Title of the article

THE PROSPECT OF CREATION OF A CYCLIC CONTINUAL-QUANTUM CHI-SQUARED MACHINE 
FOR CHECKING STATISTICAL HYPETHESES ON SMALL TEST SAMPLES
OF BIOETRIC AND OTHER TYPES OF DATA 

Authors

Volchikhin Vladimir Ivanovich, Doctor of engineering sciences, professor, President of Penza State University (40 Krasnaya street, Penza, Russia), president@pnzgu.ru
Ivanov Aleksandr Ivanovich, Doctor of engineering sciences, associate professor, head of the laboratory of biometric and neural network technologies, Penza Research Institute of Electrical Engineering (9 Sovetskaya street, Penza, Russia), ivan@pniei.penza.ru
Pashchenko Dmitriy Vladimirovich, Doctor of engineering sciences, professor,  head of sub-department of computer engineering, Penza State University (40 Krasnaya street, Penza, Russia), dmitry.pashchenko@gmail.com
Akhmetov Berik Bakhytzhanovich, Candidate of engineering sciences, professor, vice-president of Hodja Ahmet Yassawi International Kazakh-Turkish University (B. Sattarkhanova avenue, Turkestan, Kazakhstan), berik.akhmetov@ayu.edu.kz
Vjatchanin Sergej Evgenyevich, Associate professor, head of sub-department of radio and satellite communications, Faculty of Military Education, Penza State University (40 Krasnaya street, Penza, Russia), vyt5@list.ru

Index UDK

 004

DOI

 10.21685/2072-3059–2017-1-1

Abstract

Background. The article considers preconditions for reducing sized of test samples of the Pearson’s chi-squared test from 600 examples to 20 examples provided preservation of its capacity. The problem’s topicality is caused by the fact that during learning and testing of personality biometric identification means it is not possible to use ;arge volumes of learning and testing samples.
Materials and methods. The study formalizes the conditions, at which the chisquared test on small samples becomes a discerete distribution of values from a continuous distribution of values. For the normal and uniform law of values distribution the authors use histograms with uniform intervals having a precise binding of central intervals of a histogram to mathematical expectation, calculated on a test sample.
Results. It is offered to amplify the chi-squared test capacity 22 times by smoothing histograms with a digital filter with a slipping window of 9 readouts. The forecast is that the next chi-squared test capacity amplifier should be designed in the form of a cyclic continual-quantum converter that repeatedly solves the problem for smaller sub-samples. The article assesses an additional amplification of the chisquared test capacity by revealing and studying discrete conditions of its distribution (an output discerte spectrum of the chi-squared conversion).
Conclusions. It is shown that in 16 experiments the chi-squared test, synchronized by mathematical expectation and built on histograms with 6 uniform intervals, has a discrete spectrum of value probability consisting of 116 significant lines. The occurrence probability of each line depends on the input value distribution law. Recording of the discrete prectrum of chi-squared distribution can make it possible to improve the chi-squared test capacity by one or two orders.

Key words

continual-quantum chi-squared machine, Pearson’s chi-squared test, biometrics.

Download PDF
References

1. Kobzar' A. I. Prikladnaya matematicheskaya statistika dlya inzhenerov i nauchnykh rabotnikov [Applied mathematics and statistics for engineerings and researchers]. Moscow: Fizmatlit, 2006, 816 p.
2. R 50.1.037–2002 Rekomendatsii po standartizatsii. Prikladnaya statistika. Pravila proverki soglasiya opytnogo raspredeleniya s teoreticheskim. Ch. I. Kriterii tipa χ2. Gosstandart Rossii [Standardization recommendations. Applied statistics. Rules for checking accordance between experimental and theoretical distribution. Part 1. Criteria of χ2 type. State standard of Russia]. Moscow, 2001, 140 p.
3. Yazov Yu. K., Volchikhin V. I., Ivanov A. I., Funtikov V. A., Nazarov I. G. Neyrosetevaya zashchita personal'nykh biometricheskikh dannykh [Neural-network protection pf personal biometric data]. Moscow: Radiotekhnika, 2012, 157 p.
4. Boll R., Konnel Dzhonatan Kh., Pankanti Sharat, Ratkha Nalini K., Sen'or U. Endryu Rukovodstvo po biometrii: per. s angl. [Guide on biometrics: translation from English]. Moscow: Tekhnosfera, 2007, 368 p.
5. Akhmetov B. S., Volchikhin V. I., Ivanov A. I., Malygin A. Yu. Algoritmy testirovaniya biometriko-neyrosetevykh mekhanizmov zashchity informatsii [Algorithms of biometric- neural network data protection mechansism testing]. Kazakhstan, Almaty: KazNTU im. Satpaeva, 2013, 152 p. Available at: http:// portal.kazntu.kz/ files/ publicate/2014-01-04-11940.pdf
6. Akhmetov B. S., Ivanov A. I., Funtikov V. A., Bezyaev A. V., Malygin A. Yu. Tekhnologiya ispol'zovaniya bol'shikh neyronnykh setey dlya preobrazovaniya nechetkikh biometricheskikh dannykh v kod klyucha dostupa: monogr. [Application of large neural networks for fuzzy biometric data conversion into access key code: monograph]. Kazakhstan, Almaty: Izd-vo LEM, 2014, 144 p. Available at: http://portal. kazntu.kz/files/publicate /2014-06-27-11940.pdf)
7. Serikova N.I., Ivanov A.I., Kachalin S.V. Vestnik Sibirskogo gosudarstvennogo aerokosmicheskogo universiteta im. akademika M. F. Reshetneva [Bulletin fo Siberia State Aerospace University named after academician M.F. Reshetnev]. 2014, no. 3 (55), pp. 146–150.
8. Serikova N. I., Ivanov A. I., Serikova Yu. I. Voprosy radioelektroniki. Ser.: SOIU [Problems of radio electronics. Series: SOIU]. 2015, iss. 1, pp. 85–94.
9. Akhmetov B. S., Ivanov A. I., Serikova N. I., Funtikov V. A. Vestnik natsional'noy akademii nauk Respubliki Kazakhstan [Bulletin of the National Academy of Sciences of the republic of Kazakhstan]. 2014, no. 5, pp. 28–34.
10. Ivanov A. I. Zashchita informatsii. INSAID [Data protection: INSAID]. 2015, no. 2, pp. 29–32.
11. Akhmetov B. B., Ivanov A. I., Serikova N. I., Funtikov V. A. Vestnik Natsional'noy akademii nauk Respubliki Kazakhstan [Bulletin of the National Academy of Sciences of the republic of Kazakhstan]. Almaty, 2015, no. 1, pp. 17–25.
12. Volchikhin V. I., Pashchenko D. V., Trokoz D. A. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2010, no. 3, pp. 37–48.

 

Дата создания: 08.08.2017 15:42
Дата обновления: 10.08.2017 09:24