I.K. Belova - Ph. D. (Phys.-Math.), Kaluga branch of the Bauman MSTU E.O. Deryugina - Ph. D. (Eng.), Kaluga branch of the Bauman MSTU A.V. Ermolenko - Post-graduate Student, Kaluga branch of the Bauman MSTU. E-mail: syvorova_eo@mail.ru

Areas of work in which the author\'s identification when making management decisions, paperwork is very wide. While methods and models for decision support in the identification of the author of the handwritten documents today are virtually non-existent. The article shows that in the process of operational activities employees DOI are confronted with situations that require identification of the handwriting of the author. Existing methods of solving the problem is speculative, based on Visual analysis and do not contribute to the quality of our services. There are no formal decision-making algorithms for task identification. In this svâzai it is important to develop procedures of decision-making support for the task of identifying the author of a hand-written document using different intellectual methods. In particular can be a method of identification based on fuzzy logic and using neural networks. In the article questions of decision-making support for processing handwritten documents undepartmental security police units. The authors developed an original method of selection of the unique characteristics of handwriting based on string and char analysis. Applied methods for encoding characters using graph theory. Modified criterion informative and shows razdelimost′ priznakovoj base. Neural architecture is crucial devices modified using the theory of fuzzy sets. As a result, research has established a system of decision support, able to identify the author\'s handwriting. The analysis of descrip-tiveness of the results shows that the resulting feature set is separable sets. Analyzed and studied the properties of different identifying patterns in terms of the input feature set. Synthesized block model of decision-making. Taking into account the maximum efficiency in terms of the objectives chosen and implemented decisive model based on quasi-Newton BFGS-neural network training methodology based on back-propagation. The developed software is debugged and ready to work. Rospatent The certificate of official registration of the computer program for the number 2007612599. The introduction of this model of decision-making in the operation of the contractual and legal divisions of private security to improve the efficiency of service personnel, to strengthen the financial and economic and personnel discipline, reduce the distortion of statistical reporting.

 

1. Rekomendacii MVD Rossii ot 23.10.2013 P. 78.36.031 -2013 «O porjadke obsledovanija obektov, kvartir i MKHIG, prinimaemykh pod centralizovannuju okhranu».
2. Goroshko I.V. Matematicheskoe modelirovanie v upravlenii organami vnutrennikh del. M.: Akad. uprav. MVD Rossii. 2000.
3. Metody klassicheskojj i sovremennojj teorii avtomaticheskogo upravlenija: Uchebnik. V 5-ti tomakh. Izd. 2-e, pererab. i dop. T. 5.: Metody sovremennojj teorii avtomaticheskogo upravlenija / Pod red. K.A. Pupkova, N.D. Egupova. M.: Izd-vo MGTU im. N.EH. Baumana. 2004. 744 s.
4. Ermolenko A.V., Kozlichenkov A.A., Korljakova M.O. Vybor vkhodnogo nabora priznakov dlja nejjrosetevojj identifikacii pocherka // Nauchnaja sessija MIFI 2007. Sb. nauchnykh trudov IX Vseros. nauchno-tekhnich. konf. «Nejjroinformatika-2007»: V trekh chastjakh. CH. 1. M.: MIFI. 2007. S. 42−50.
5. Belova I.K., Derjugina E.O. Rekurrentnaja nejjronnaja set s upravljaemymi sinapsami dlja raspoznavanija rukopisnogo svjaznogo teksta // EHlektromagnitnye volny i ehlektronnye sistemy. 2013. T. 18. № 10. S. 36−39.
6. Ermolenko A.V. (a). Korljakova M.O., Filimonkov A.A. Formirovanie nejjrosetevojj modeli geoinformacionnogo datchika. Izvestija Instituta inzhenernojj fiziki. 2011. № 1(19). S. 25−30.
7. ZHuravlev JU.I. Ob algebraicheskom podkhode k resheniju zadach raspoznavanija ili klassifikacii // Problemy kibernetiki. 2005. № 33. S. 5−25.
8. Makarov I.M., Lokhin V.M., Manko S.V., Romanov M.P. Iskusstvennyjj intellekt i intellektualnye sistemyupravlenija. M.: Nauka. 2006. 333 s.
9. Ossovskijj S. Nejjronnye seti dlja obrabotki informacii / Per. s angl. I.D. Rudnickogo. M.: Finansy i statistika. 2002. 344 s.
10. Ajjzerman M.A., Braverman EH.M., Rozonoehr L.I. Metod potencialnykh funkcijj v teorii obuchenija mashin. M.: Nauka. 2004. 384 s.