| Authors |
Volchikhin Vladimir Ivanovich, doctor of technical sciences, professor, President of Penza State University (40 Krasnaya street, Penza, Russia), vvi@pnzgu.ru
Ivanov Aleksandr Ivanovich, doctor of technical sciences, associate professor, head of biometric and neuronal nets technology laboratory, Penza Scientific Research Electrotechnical Institute (9 Sovetskaya street, Penza, Russia), ivan@pniei.penza.ru
Serikov Andrey Vasil'evich, department director, Scientific production company «Rubin» (2 Baydukova street, Penza, Russia), julia-ska@yandex.ru
Serikova Julia Igorevna, master degree student, Penza State University (40 Krasnaya street, Penza, Russia), julia-ska@yandex.ru
|
| Abstract |
Background. The aim is to decrease the error calculating the standard deviation on small samples of biometric data as part of the normal distribution of values hypothesis.
Materials and methods. The method of estimation of the standard deviation regularization. It is shown that for this purpose need to use another (second) method of calculating the standard deviation. If the error of the second method is weakly correlated with the error of the classical method of calculating the correlation, there is a possibility of their mutual clarification. When implementing the second method used by one of the effects of quantum superposition occurring in the quantization of the continuum with the transition to the balanced histogram with adjustable width intervals.
Results. Proposed average result of the calculation of the standard deviation obtained by two different methods to improve the accuracy of estimates on small samples.
Conclusions. The resulting error in the calculation of the standard deviation of the two methods is reduced by about 30 %, equivalent to increasing the size of the test sample with 16 to 30 experiments. This is equivalent to improve the condition number of programs to calculate the standard deviation of about 2 times at roughly double the number of lines of software implementation for high-level languages.
|
