This paper is devoted to the research, aimed at solving problems of recognition of dynamically changeable sequences, characterized by a set of parameters at each instance. The paper sets tasks of obtaining a mathematical model of separation of mixture sequences and their subsequent recognition as well as the problem of practical testing of the task solution. In the article as the accounting mechanism for the time history of signals' changes and subsequent recognition, in terms of recognition accuracy and computational efficiency, a method based on Markov chains is selected. The experimental part of the work is carried out in the case of clustering and recognition of pulses sequences mixture from different radar stations. Practical application can be extended to other various pattern recognition problems in which dynamic data sequences are used. In this regard, the proposed combined method of recognition, taking into account a large set of factors, characterized by affordability, ease of use, can be applied to a broad class of systems for processing of dynamically changing data, including image processing.
Mixed sequences clustering, dynamic sequences recognition, Markov chains, HMM, radar stations.
Alexeev, A. (2017). Methods of Clustering and Recognition of Dynamic Sequences with Use of Markov Chains Technique. Robotics and Technical Cybernetics, 2(15), pp.37-47.
- Gonorovskiy, I. (1986). Radiotekhnicheskie tsepi i signaly [Radiotechnical chains and signals]. 1st ed. Moscow, Russia: Radio i svyaz' Publ.
- Bashkov, E. and et al. (2010). Metody i sredstva identifikatsii istochnikov radioizlucheniya [Methods and tools of indentification of radiosources]. 1st ed. Donetsk: GVUZ «DonNTU» Publ.
- Tou, T. and Gonzalez, R. (1977). Pattern Recognition Principles. 2nd ed. Addison-Wesley.
- Bishop, C. (2006). Pattern recognition and machine learning. Information Science and Statistics. 1st ed. New York [u.a.]: Springer.
- Goryachkin, O. (2003). Metody slepoy obrabotki signalov i ikh prilozheniya v sistemakh radiotekhniki [Methods of signal blind processing and their application in radiotechnic systems]. 1st ed. Moscow, Russia: Radio i svyaz' Publ.
- Rabiner, L. (1989). A tutorial on hidden markov models and selected applications in speech recognition. 1st ed.
- Bilmes, J. (1999). Natural statistical models for automatic speech recognition. Doctor. Berkeley University of California.
- Hyvarinen, A., Karhunen, J. and Oja, E. (2001). Independent component analysis. 1st ed. New York: John Wiley & Sons.
- Ponomarev, V. (2010). Primenenie metoda slepogo razdeleniya istochnikov v elektrofiziologii dlya kartirovaniya funktsiy mozga [Application of blind source separation method in electrophysiology for brain function mapping]. In: Trudy IX mezhd. konf. «Prikladnaya optika-2010» [Proceedings of IX International Conference on Applied Optics - 2010]. pp.317-322.
- Gonzalez, R., Woods, R. and Eddins, S. (2003). Digital image processing using MATLAB. 1st ed. [United States]: Gatesmark Publishing.
- Bacher, J. (2002). Cluster Analysis. 1st ed. Nuremberg: University Erlangen.
- Wiley, R. (1985). Electronic intelligence, the interception of radar signals. 1st ed. Dedham, MA: Artech House.