350 rub
Journal Neurocomputers №10 for 2010 г.
Article in number:
Investigation of the reliability of analog neural networks using the Monte Carlo method
Authors:
A. I. Pereguda, A. A. Timashov
Abstract:
In article the utility model of the device for identification of the forged documents and the securities containing the hand-written text in Russian is described. Identification of forged hand-written documents in Russian in forensic handwriting expertise is a primary scope of the offered device. Also used forensic techniques, allows to identify the executor of the hand-written document, and to define his sex and age from handwriting are briefly described. In these forensic techniques neural network approach is used as a classification method. Examples of the known technical equipment connected with identification of various forged objects are listed. Also some known technical equipment, found in the ROSPATENT database, connected with neural networks and which can be used for the solving of practical problems is presented. The detailed description of known close analogues of the offered utility model is given. The formula of the offered utility model is described and differences from known close analogues are specified. The description of work of the offered utility model and an example of possible its industrial application is introduced.
Pages: 12-16
References
  1. Галушкин А.И. Теория нейронных сетей. Кн.1: Учеб. Пособие для вузов / Общая ред. А.И. Галушкина. М.: ИПРЖР. 2000. С. 356-357.
  2. Нечипоренко В.И. Структурный анализ и методы построения надежных систем. М.: Сов. радио. 1968. С. 220-232.
  3. Dugan J.B. Watterson J.W. Reliability analysis of artificial neural networks / Reliability and Maintainability Symposium. 1991. Proceedings. Annual. Р.598-603.
  4. Потапов В.И., Потапов И.В. Оптимизация функциональной надежности избыточной, восстанавливаемой после отказов, «стареющей» искусственной нейронной сети // Информационные технологии. 2004. № 12. С. 19-26.
  5. Derek B. I. Feltham, Wojciech Maly, Physically Realistic Fault Models for Analog CMOS Neural Networks // IEEE Journal of Solid-state Circuits. September 1991. V. 26. No. 9. Р. 1223-1229.
  6. Хайкин С. Нейронные сети: полный курс. Изд-е 2-е: пер. с. англ. М.: Издательский дом «Вильямс». 2006. С. 862-870.
  7. Круглов В.В., Борисов В.В. Искусственные нейронные сети. Теория и практика. Изд-е 2-е, стереотип. М.: Горячая линия-Телеком. 2002. С. 66-69.
  8. Pasha G.R., Muhammad Aslam, Atif Akbar, Sampling Algorithm of Order Statistics for Conditional Lifetime Distributions // Pakistan Journal of Statistics and Operation Research. 2005. V.1. Р. 1-6.
  9. Lawrence D. Brown Tony Cai T. and Anirban DasGupta Interval Estimation for a Binomial Proportion // Statistical Science 2001. V. 16. No. 2. Р.101-133.
  10. Боровков А.А. Математическая статистика. М.: Наука. 1984. С. 268-269.