Informatics and Applications
2025, Volume 19, Issue 4, pp 2-11
FILTERING OF SPECIAL MARKOV JUMP PROCESSES BY OBSERVATIONS WITH MULTIPLICATIVE NOISE
Abstract
The paper is devoted to the problem of optimal state filtering for a class of special Markov jump processes.
The system consists of two coupled components. The first component is a Markov jump process with a finite state space. The second component evolves synchronously with the first one and, given the trajectory of the first component, forms a sequence of independent random vectors. The observations are modeled by a diffusion process whose drift and diffusion coefficients depend on the underlying state to be estimated. The filtering problem is to determine the conditional distribution of the system state given the available observations. Through a suitable transformation, the original observations can be reduced to a diffusion process with unit diffusion accompanied by a function of the system state observed without noise. The conditional probability distribution of the state is absolutely continuous with respect to a specially constructed reference measure. Its conditional density is characterized by a system of recurrently connected stochastic integrodifferential equations - essentially, a variant of the Kushner-Stratonovich equation - augmented by integral transformations.
[+] References (25)
- Borisov, A., Yu. Kurinov, and R. Smeliansky. 2024. Veroyatnostnyy analiz klassa markovskikh skachkoobraznykh protsessov [Probabilistic analysis of a class of Markov jump processes]. Informatika i ee Primeneniya - Inform. Appl. 18(3):30-37. doi: 10.14357/19922264240304. EDN: XPVTGJ.
- Borisov, A., Yu. Kurinov, and R. Smeliansky. 2024. Fil'tratsiya sostoyaniy klassa markovskikh skachkoobraznykh protsessov po raznorodnym nablyudeniyam s additivnymi shumami [Filtering of a class of Markovjump processes by heterogeneous observations with additive noises]. Informatika i ee Primeneniya - Inform. Appl. 18(4):10-18. doi: 10.14357/19922264240402. EDN: FEMNQL.
- Bar-Shalom, Y., X.-R. Li, and T. Kirubarajan. 2002. Estimation with applications to tracking and navigation: Theory, algorithms and software. New York, NY: John Wiley & Sons. 592 p. doi: 10.1002/0471221279.
- Miller, B. M., K. E. Avrachenkov, K. V. Stepanyan, and G. B. Miller. 2005. Flow control as a stochastic optimal control problem with incomplete information. Probl. Inf. Transm. 41(2):150-170. doi: 10.1007/s11122-005- 0020-8. EDN: LJFPRR.
- Borisov, A. 2020. Robust filtering algorithm for Markov jump processes with high-frequency counting observations. Automat. Rem. Contr. 81(4):575-588. doi: 10.1134/S0005117920040013. EDN: DFNFFX.
- Smith, W. 1955. Regenerative stochastic processes. P. Roy. Soc. Lond. A Mat. 232(1188):6-31. doi: 10.1098/rspa.1955.0198.
- Ait-Sahalia, Y., and J. Jacod. 2014. High-frequency financial econometrics. Hoboken, Princeton, NJ: Princeton University Press. 688 p. doi: 10.1515/9781400850327.
- Elliott, R., and T. K. Siu. 2022. Hedging options in a hidden Markov-switching local-volatility model via stochastic flows and a Monte-Carlo method. J. Futures Markets 43(7):925-950. doi: 10.1002/fut.22422.
- Stoyanov, J. 1997. Counter examples in probability. Hoboken, NJ: Wiley. 352 p.
- Borisov, A., and I. Sokolov. 2020. Optimal filtering of Markov jump processes given observations with state-dependent noises: Exact solution and stable numerical schemes. Mathematics 8(4):506. 22 p. doi: 10.3390/math8040506.
- Liptser, R. Sh., and A. N. Shiryayev. 1989. Theory of martingales. New York, NY: Springer. 792 p. doi:10.1007/978- 94-009-2438-3.
- Kallianpur, G., and C. Striebel. 1969. Stochastic differential equations occurring in the estimation of continuous parameter stochastic processes. Theor. Probab. Appl. 14(4):567-594. doi: 10.1137/1114076.
- Wong, E., and B. Hajek. 1985. Stochastic processes in engineering systems. New York, NY: Springer. 361 p. doi: 10.1007/978-1-4612-5060-9.
- Takeuchi, Y., and H. Akashi. 1985. Least-squares state estimation of systems with state-dependent observation noise. Automatica 21(3):303-313. doi: 10.1016/0005- 1098(85)90063-9.
- Joannides, M., and F. LeGland. 1997. Nonlinear filtering with continuous time perfect observations and noninformative quadratic variation. 36th Conference on Decision and Control Proceedings. New York, NY: IEEE. 1645- 1650. doi: 10.1109/CDC.1997.657750.
- Crisan, D., M. Kouritzin, and J. Xiong. 2009. Nonlinear filtering with signal dependent observation noise. Electron. J. Probab. 14:1863-1883. doi: 10.1214/EJP.v14-687.
- Kushner, H., and P. Dupuis. 2001. Numerical methods for stochastic control problems in continuous time. 2nd ed. Stochastic modelling and applied probability ser. New York, NY: Springer. 476 p. doi: 10.1007/978-1-4613- 0007-6.
- Magnus, J., and H. Neudecker. 2019. Matrix differential calculus with applications in statistics and econometrics. New York, NY: J. Wiley & Sons. 504 p. doi:10.1002/9781119541219.
- Liptser, R. S., and A. N. Shiryaev. 1974. Statistika sluchaynykh protsessov (nelineynaya fil'tratsiya i smezhnye voprosy) [Statistics of random processes (nonlinear filtering and related problems)]. Moscow: Nauka. 696 p.
- Borisov, A. V. 2025. Fil'tratsiya sostoyaniy i parametrov spetsial'nykh markovskikh skachkoobraznykh protsessov po kosvennym nablyudeniyam bez shuma [Filtering of states and parameters of special Markov jump processes via indirect perfect observations]. Informatika i ee primeneniya - Inform. Appl. 19(1):25-32. doi: 10.14357/19922264250104. EDN: MZAJVZ.
- Cvitanic, J., R. Liptser, and B. Rozovskii. 2006. A filtering approach to tracking volatility from prices observed at random times. Ann. Appl. Probab. 16:1633-1652. doi: 10.1214/105051606000000222.
- Kloden, P. E., and E. Platen. 1992. Numerical solution of stochastic differential equations. Berlin-Heidelberg: Springer-Verlag. 636 p. doi: 10.1007/978-3-662-12616-5.
- Platen, E., and N. Bruti-Liberati. 2010. Numerical solution of stochastic differential equations with jumps in finance. Berlin: Springer. 856 p. doi: 10.1007/978-3-642-13694-8.
- Borisov, A., and D. Kazanchyan. 2021. Fil'tratsiya sostoyaniy markovskikh skachkoobraznykh protsessov po kompleksnym nablyudeniyam I: tochnoe reshenie zadachi [Filtering of Markov jump processes given composite observations I: Exact solution]. Informatika i ee primeneniya - Inform. Appl. 15(2):12-19. doi: 10.14357/19922264210202. EDN: NKCTNS.
- Borisov, A., and D. Kazanchyan. 2021. Fil'tratsiya sostoyaniy markovskikh skachkoobraznykh protsessov po kompleksnym nablyudeniyam II: Chislennyy algoritm [Filtering of Markov jump processes given composite observations II: Numerical algorithm]. Informatika i ee Primeneniya - Inform. Appl. 15(3):9-15. doi: 10.14357/19922264210302. EDN: WUJJEB.
[+] About this article
Title
FILTERING OF SPECIAL MARKOV JUMP PROCESSES BY OBSERVATIONS WITH MULTIPLICATIVE NOISE
Journal
Informatics and Applications
2025, Volume 19, Issue 4, pp 2-11
Cover Date
2025-30-12
DOI
10.14357/19922264250401
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
special Markov jump process; observations with multiplicative noise; conditional probability density function; Kushner-Stratonovich equation
Authors
A. V. Borisov
Author Affiliations
 Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|