UDC 681.5
1 Space Research Institute under NAS of Ukraine and State Space Agency of Ukraine, Kyiv, Ukraine
 v.f.gubarev@gmail.com
|
2 Educational and Research Institute for Applied System Analysis of the National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine
yuriy.milyavsky@gmail.com
|
FEATURES OF MODELING AND IDENTIFICATION
OF COGNITIVE MAPS UNDER UNCERTAINTY
Abstract. A process of complex systems identification is examined in this paper. It was established that it is impossible to create a universal identification method. Only for a well-identifiable system with a high signal-to-noise ratio for each individual system mode, a high-quality model can be reconstructed. In other cases, if modes with sufficiently small signal-to-noise ratio exist, only a surrogate model can be obtained. For cognitive maps, theoretical foundations are developed, which may be used in approaches to find a surrogate model and then to improve the result using different tuning and learning algorithms. Numerical simulation was used to analyze the identification process.
Keywords: cognitive map, system identification, subspace method, complex system, ill-conditioning, regularization.
full text
REFERENCES
- Miliavskyi Yu.L. Identification in cognitive maps in impulse process mode with incomplete measurement of nodes coordinates. Cybernetics and Computer Engineering Journal. 2019. Iss. 1 (195). P. 49–63. doi.org/10.15407/kvt195.01.049 .
- Roberts F.S. Discrete Mathematical Models: with Applications to Social, Biological, and Environmental Problems. Englewood Cliffs: Prentice-Hall, 1976. 559 p.
- Romanenko V.D., Milyavskiy Y.L. Stabilizing of impulse processes in cognitive maps based on state-space models. System Research & Information Technologies. 2014. N 1. P. 26–42 (in Russian).
- Ho B.L., Kalman R.E. Effective Construction of linear state variable models from input/output functions. Regelungstechnik. 1996. N 14. P. 545–548. https://doi.org/10.1524/auto.1966.14.112.545 .
- Katayama T. Subspace Methods for System Identification. Berlin: Springer, 2005. 408 p.
- Qin S.J. An overview of subspace identification. Computers & Chemical Engineering. 2006. Vol. 30, Iss. 10–12. P. 1502–1513. doi.org/10.1016/j.compchemeng.2006.05.045.
- Ljung L. System Identification: Theory for User. 2nd ed. Upper Saddle River: Prentice Hall PTR, 1999. 640 p.
- Ljung L., Chen T., Mu B. A shift in paradigm for system identification. International Journal of Control. 2020. Vol. 93, Iss. 2. P. 173–180. doi.org/10.1080/00207179.2019.1578407.
- Verhaegen M., Dewilde P. Subspace model identification. Part 1. The output-error state space model identification class of algorithms. International Journal of Control. 1992. Vol. 56, Iss. 5. P. 1187–1210. doi.org/10.1080/00207179208934363.
- Mao X., He J., Zhao C. An improved subspace identification method with variance minimization and input design. Proc. 2022 American Control Conference (ACC) (08–10 June 2022, Atlanta, GA, USA). Atlanta, 2022. P. 4820–4825. doi.org/10.23919/ACC53348.2022.9867157.
- Gubarev V.F. Modeling and Identification of Complex Systems. Kyiv: Naukova Dumka, 2019. 248 p. (in Ukrainian).
- Kailath T. Linear Systems. Englewood Cliffs: Prentice-Hall, Inc., 1980. 680 p.
- Golub G.H., Loan Ch.F. Matrix Computations. Baltimore: The John Hopkins University Press, 2013. 780 p.
- Leonov A.S. Justification of the choice of regularization parameter according to quasi-optimality and quotient criteria. USSR Computational Mathematics and Mathematical Physics. 1978. Vol. 18, Iss. 6. P. 1–
