On the Relationship between the Knowledge Model and the Problem of Pattern Recognition

Cover Page

Cite item

Full Text

Abstract

The article is devoted to the problem of pattern decomposition in solving the problem of pattern recognition. The problem of pattern decomposition is considered regardless of the recognition algorithms used. The only requirement is that the pattern recognition problem has a classical formulation. The article shows that without reference to the knowledge model, the decomposition of pattern cannot be performed within the framework of the recognition task itself, since it leads to a revision of the recognition task itself. In those cases, when the pattern recognition problem is preserved during decomposition, it may change in such a way that its solution in the decomposed form is not identical to the solution of the original pattern recognition problem.

Full Text

Restricted Access

About the authors

Oleg M. Polyakov

Saint-Petersburg State University of Aerospace Instrumentation

Author for correspondence.
Email: road.dust.spb@gmail.com

Candidate of technical sciences. Docent

Russian Federation, Saint-Petersburg

Sergey B. Rudnitskiy

Saint-Petersburg State University of Aerospace Instrumentation

Email: sbr@spiiras.ru

Doctor of Technical Sciences, Professor. Senior Researcher

Russian Federation, Saint-Petersburg

References

  1. The RapidMiner Platform // Electronic resource. URL: https://rapidminer.com/ (accessed 04.07.2023).
  2. Fomin Ya. A., Tarlovsky G.R. Statisticheskaya teoriya raspoznavaniya obrazov [Statistical theory of pattern recognition]. Moscow: Radio and Communication, 1986.
  3. Potapov A. A., Pakhomov A.A., S. Nikitin.A. Noveyshiye metody obrabotki izobrazheniy [The latest methods of image processing]. Moscow: Fizmatlit, 2008.
  4. Shapiro L., Stockman J. Komp'yuternoye zreniye. [Computer vision]. Moscow: Binom. Laboratory of Knowledge, 2006.
  5. Merkov A. B. Raspoznavaniye obrazov. Vvedeniye v metody statisticheskogo obucheniya [Pattern recognition. Introduction to methods of statistical training]. Moscow: Editorial URSS, 2011.
  6. Nicolas J. First Order Logic Formalization for Functional, Multivalued and Mutual Dependencies. ACM SIGMOD Conf, 1978. P. 40-46.
  7. Rissanen J. Independent Components of Relations. ACM TODS 2:4, December, 1977. P. 317-325.
  8. Fagin R. Multivalued Dependencies and a New Normal Form for Relational Databases. ACM TODS 2:3, September. 1977. P. 262-278.
  9. R-lingvistika [R-linguistics]. // Electronic resource. URL: https://roaddust.ru/?cat=36 / (accessed 22.04.2023).
  10. Polyakov O.М. Linguistic data model for natural languages and artificial intelligence. Part 1. Categorization // DISCOURSE. 2019. V. 5. No 4. P.102–114.
  11. Polyakov O. M. Linguistic Data Model for Natural Languages and Artificial Intelligence. Part 2. Identification. DISCOURSE. 2019. V. 5.No. 5. P. 99-113.
  12. Polyakov O. M. Linguistic Data Model for Natural Languages and Artificial Intelligence. Part 3. Recognition. DISCOURSE. 2019. V. 5. No. 6. P. 132-143.

Supplementary files

Supplementary Files
Action
1. JATS XML
2. Fig. 1. Training sample

Download (20KB)
3. Fig. 2. Two-parameter training sample

Download (2KB)

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).