Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions
Background. Improving the reliability of statistical data processing on small samples. Materials and methods - it is proposed to use three artificial neurons, which are analogues of the chi-square test, the fourth statistical moment test and the Geary test. Additionally, the procedure for additio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penza State University Publishing House
2024-03-01
|
| Series: | Известия высших учебных заведений. Поволжский регион:Технические науки |
| Subjects: |
| _version_ | 1827330758017024000 |
|---|---|
| author | V.I. Volchikhin A.I. Ivanov A.V. Bezyaev I.A. Filipov |
| author_facet | V.I. Volchikhin A.I. Ivanov A.V. Bezyaev I.A. Filipov |
| author_sort | V.I. Volchikhin |
| collection | DOAJ |
| description | Background. Improving the reliability of statistical data processing on small
samples. Materials and methods - it is proposed to use three artificial neurons, which are
analogues of the chi-square test, the fourth statistical moment test and the Geary test. Additionally,
the procedure for additional training of output nonlinear functions of artificial neurons
was used to predict the confidence probabilities regarding decisions made by neurons.
Results. A significant increase in the number of detected and corrected errors during the
convolution of redundant codes of the neural network classifier is shown. Conclusions. It
has been confirmed that the use of several statistical criteria in parallel gives a more reliable
result in comparison with one criterion, and complex code designs capable of detecting and
correcting errors can be used to combine them. A numerical experiment confirmed that a
two-layer neural network can reduce the level of detected, but not correctable, errors to a
probability of 0.141. Linear extrapolation of the results of a numerical experiment allows us
to expect a confidence probability of 0.9 already when using 5 artificial neurons of the first
layer. Thus, there is a significant reduction in the cost of protecting applications due to the
use of SIM cards, RFID cards, microSD cards, USB BioTokens, FPGAs, DSP controllers in
a trusted computing environment. |
| first_indexed | 2024-03-07T16:22:00Z |
| format | Article |
| id | doaj.art-b9f43f28e890421bb1817b1ba5c97038 |
| institution | Directory Open Access Journal |
| issn | 2072-3059 |
| language | English |
| last_indexed | 2024-03-07T16:22:00Z |
| publishDate | 2024-03-01 |
| publisher | Penza State University Publishing House |
| record_format | Article |
| series | Известия высших учебных заведений. Поволжский регион:Технические науки |
| spelling | doaj.art-b9f43f28e890421bb1817b1ba5c970382024-03-04T06:17:51ZengPenza State University Publishing HouseИзвестия высших учебных заведений. Поволжский регион:Технические науки2072-30592024-03-01410.21685/2072-3059-2023-4-3Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisionsV.I. Volchikhin0A.I. Ivanov1A.V. Bezyaev2I.A. Filipov3Penza State UniversityPenza Scientific Research Electrotechnical InstitutePenza State UniversityPenza State UniversityBackground. Improving the reliability of statistical data processing on small samples. Materials and methods - it is proposed to use three artificial neurons, which are analogues of the chi-square test, the fourth statistical moment test and the Geary test. Additionally, the procedure for additional training of output nonlinear functions of artificial neurons was used to predict the confidence probabilities regarding decisions made by neurons. Results. A significant increase in the number of detected and corrected errors during the convolution of redundant codes of the neural network classifier is shown. Conclusions. It has been confirmed that the use of several statistical criteria in parallel gives a more reliable result in comparison with one criterion, and complex code designs capable of detecting and correcting errors can be used to combine them. A numerical experiment confirmed that a two-layer neural network can reduce the level of detected, but not correctable, errors to a probability of 0.141. Linear extrapolation of the results of a numerical experiment allows us to expect a confidence probability of 0.9 already when using 5 artificial neurons of the first layer. Thus, there is a significant reduction in the cost of protecting applications due to the use of SIM cards, RFID cards, microSD cards, USB BioTokens, FPGAs, DSP controllers in a trusted computing environment.chi-square testfourth statistical moment testgeary's testsmall samplestesting of the normality hypothesis |
| spellingShingle | V.I. Volchikhin A.I. Ivanov A.V. Bezyaev I.A. Filipov Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions Известия высших учебных заведений. Поволжский регион:Технические науки chi-square test fourth statistical moment test geary's test small samples testing of the normality hypothesis |
| title | Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| title_full | Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| title_fullStr | Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| title_full_unstemmed | Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| title_short | Recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| title_sort | recognition of small samples with a given data distribution using artificial neurons that predict the confidence probabilities of their own decisions |
| topic | chi-square test fourth statistical moment test geary's test small samples testing of the normality hypothesis |
| work_keys_str_mv | AT vivolchikhin recognitionofsmallsampleswithagivendatadistributionusingartificialneuronsthatpredicttheconfidenceprobabilitiesoftheirowndecisions AT aiivanov recognitionofsmallsampleswithagivendatadistributionusingartificialneuronsthatpredicttheconfidenceprobabilitiesoftheirowndecisions AT avbezyaev recognitionofsmallsampleswithagivendatadistributionusingartificialneuronsthatpredicttheconfidenceprobabilitiesoftheirowndecisions AT iafilipov recognitionofsmallsampleswithagivendatadistributionusingartificialneuronsthatpredicttheconfidenceprobabilitiesoftheirowndecisions |