(50-4) 19 * << * >> * Russian * English * Content * All Issues

Modeling and analysis of natural time series based on a combination of cognitive decision rules and KAN neural network
B.S. Mandrikova1,2, O.V. Mandrikova1

1 Institute of Cosmophysical Research and Radio Wave Propagation, Far Eastern Branch of the Russian Academy of Sciences, Mirnaya St. 7, Paratunka, 684034 Kamchatskiy Kray, Russia;
2 Saint Petersburg Electrotechnical University, Professora Popova str., 5, St. Petersburg, 197022, Russia

  Full text (PDF)

DOI: 10.18287/COJ1877

Article ID: 1877

Language: English

Abstract:
A method for modeling and analyzing natural time series based on a combination of cognitive decision rules with the Kolmogorov-Arnold neural network (KAN) is proposed. The problem of approximating the data time changes of the galactic cosmic ray flux variations is considered. Anomalous changes in the galactic cosmic ray flux indicate disturbances in the near-Earth space and are an important factor in space weather. The non-stationary structure of data of the cosmic ray flux variations, limited data samples, and a high proportion of incomplete a priori knowledge reduce the efficiency of existing data analysis methods, including the latest developments in machine learning and artificial intelligence. The cognitive rules developed by the authors are based on the synthesis of risk theory elements with adaptive threshold wavelet estimates. They allow suppressing interference (including correlated interference) and detecting an information signal at the rate of data receipt by the processing system. The obtained estimates showed that the combination of cognitive rules with the KAN neural network makes it possible to improve the qualitative characteristics of the KAN network. Application of the method allowed us to obtain an adequate model of the data time changes of cosmic ray variations (the MSE model values of the best network NN8_filt is 0.84633 and errors are white Gaussian noise), giving a forecast with a lead step of 10 counts. The example of the event on May 10, 2024 shows the prospects of using the developed method for the task of describing anomalous changes in the rate of cosmic ray arrival to the Earth based on the data from high-latitude neutron monitors. The efficiency and accuracy of the method were also confirmed by the estimates of the deviations in the L2 norm of the true (observed) values from the values obtained by the network (with the use of cognitive rules E~L2~=^2.0136, without cognitive rules E~L2~=^3.8538).

Keywords:
natural data analysis methods, correlated noise, neural network, adaptive filtering, wavelet transform.

Acknowledgements:
The work was supported by IKIR FEB RAS State Task (subject registration No. 124012300245-2).

Citation:
Mandrikova BS, Mandrikova OV. Modeling and analysis of natural time series based on a combination of cognitive decision rules and KAN neural network. Computer Optics 2026; 50(4): 1877. doi: 10.18287/COJ1877.

References:

  1. Gorodetskaya LA, Denisova AY, Kavelenova LM, Fedoseev VA. Rare plants detection using YOLO neural network. Computer Optics. 2024;48(3):397-405. doi:10.18287/2412-6179-CO-1405
  2. Ceribasi G, Ceyhunlu AI, Ahmed N. Innovative trend pivot analysis method (ITPAM): A case study for precipitation data of Susurluk Basin in Turkey. Acta Geophysica. 2021;69(4):1465-1480. doi:10.1007/s11600-021-00605-6
  3. Bychkov IV, Ruzhnikov GM, Fedorov RK, Popova AK, Avramenko YV. On classification of Sentinel-2 satellite images by a neural network ResNet-50. Computer Optics. 2023;47(3):474-481. doi:10.18287/2412-6179-CO-1216
  4. Fetisova NV. An algorithm for detecting intense anomalous changes in the time dependence of ionospheric parameters. Computer Optics. 2019;43(6):1064-1071. doi:10.18287/2412-6179-2019-43-6-1064-1071
  5. Belov AV, Gvishiani AD, Getmanov VG, et al. Recognition of geomagnetic storms based on neural network model estimates of Dst indices. Journal of Computer and Systems Sciences International. 2022;61(1):54-64. doi:10.1134/S106423072201004X
  6. Li X, Li Z, Huang J, et al. Research on the detection model of kernel anomalies in ionospheric space electric fields. Atmosphere. 2025;16(2):160. doi:10.3390/atmos16020160
  7. Xing F, Gao Y, Kang L, Zhang M, Qin C. KAN-Transformer model for ultra-short-term wind power prediction based on EWMA data processing. Applied Sciences. 2024;14(21):9630. doi:10.3390/app14219630
  8. Firsov N, Myasnikov E, Lobanov V, et al. HyperKAN: Kolmogorov-Arnold networks make hyperspectral image classifiers smarter. Sensors. 2024;24(23):7683. doi:10.3390/s24237683
  9. Mandrikova O, Mandrikova B. Hybrid model of natural time series with neural network component and adaptive nonlinear scheme: Application for anomaly detection. Mathematics. 2024;12(7):1079. doi:10.3390/math12071079
  10. Mandrikova BS. A method for analyzing complex structured data with elements of machine learning. Computer Optics. 2022;46(3):506-512. doi:10.18287/2412-6179-CO-1088
  11. Liu Z, Wang Y, Vaidya S, et al. KAN: Kolmogorov-Arnold networks. arXiv. Preprint posted online April 30, 2024. doi:10.48550/arXiv.2404.19756
  12. Mandrikova OV, Zalyaev TL, Geppener VV, Mandrikova BS. Analysis of neutron monitor data and isolation of sporadic effects based on neural networks and wavelet transform. In: Intellectualization of Information Processing: Abstracts of the 12th International Conference; 2018:90-91.
  13. Levin BR. Theoretical Foundations of Statistical Radio Engineering. 3rd ed. Radio i Svyaz; 1989. 656 p. [In Russian] ISBN: 5-256-00264-3.
  14. Donoho DL, Johnstone IM. Ideal spatial adaptation via wavelet shrinkage. Biometrika. 1994;81(3):425-455. doi:10.1093/biomet/81.3.425
  15. Zalyaev TL. Algorithm for anomaly detection in cosmic ray variations during heliospheric disturbances. Izvestiya Saint Petersburg Electrotechnical University "LETI." 2015;(10):25-32. [In Russian]
  16. Koundal P. Graph neural networks and application for cosmic-ray analysis. In: Proceedings of the 5th International Workshop on Deep Learning in Computational Physics; June 28-29, 2021; Moscow, Russia. doi:10.22323/1.410.0004
  17. Senkevich YuI. Search for signs of changes in the state of the near-surface lithosphere layer based on image analysis of the dynamics of geoacoustic-emission signal characteristics. Bulletin of KRASEC. Physical and Mathematical Sciences. 2024;47(2):58-74. [In Russian] doi:10.26117/2079-6641-2024-47-2-58-74

151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20