ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 5. Vol. 31. 2025

DOI: 10.17587/it.31.235-242

S. M. Salibekyan, Cand. Sc.,Assistant Professor,
National Research University Higher School of Economics, Moscow, 101000, Russian Federation

Simulation Modeling of the Clustering Problem Solution Using the Mean Shift Method

Received on October 02, 2024
Accepted on November 02, 2024

The article describes the implementation of the Mean Shift data clustering algorithm based on the data flow computing system, which provides maximum parallelization of calculations. The description of an algorithm adapted for execution on a dataflow computing system, an algorithm for generating a computational grid, is given. the architecture of the computer system, the implementation of its simulation model, the results of simulation modeling, evaluation of the main parameters of the computer system.
Keywords: computing system with data flow control, data clustering, Mean Shift algorithm, Delaunay triangulation, computational grid

P. 235-242

Full text on eLIBRARY

References

1. Milutinovic V., Salom J., Veljovic D., Korolija N., Markovic D., Petrovic L. DataFlow Supercomputing Essentials, Research, Development and Education, Springer, 2017, 150 p.
2. Milutinovic V., Trifunovic N., Salom J., Giorgi R. The guide to dataflow supercomputing, USA, Springer, 2015, available at: https://proxylibrary.hse.ru:2084/content/pdf/10.1007%2F978-3-319-16229-4.pdf.
3. Salibekyan S. M., Panfilov P. B. Issues in automata network modeling of dataflow computing systems, Informacionnye tekhnologii i vychislitel'nye sistemy, 2015, no. 1, pp. 3—9 (in Russian).
4. Panfilov P. B., Salibekyan S. M. A New Approach for Distributed Computing in Embedded Systems, Procedia Engineering, 2015, vol. 100, pp. 977—986. available at: http://www.sciencedirect.com/science/article/pii/S187770581500484.
5. Panfilov P. B., Salibekyan S. M. Modeling of a supercomputer computing system of object-attribute architecture with data flow control, Informacionnye tekhnologii i vychislitel'nye sistemy, 2013, no. 1, pp. 3—10 (in Russian).
6. Tyurin A. G., Zuyev I. O. Cluster analysis, methods and algorithms of the clustering, Vestnik MGTU MIREA, 2014, no. 2, pp. 86—97 (in Russian).
7. Comaniciu D., Meer P. Mean Shift: A Robust Approach Toward Feature Space Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, pp. 603—619.
8. Kim E., Wang W., Li H., Huang X. A parallel annealing methods for automatic color cervigram image segmentation, available at: http://edwardkim.net/publications/edkim_miccaigpu2009.pdf.
9. Klaus A., Sormann M., Karner K. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure, ICPR 2006, available at: http://old.vrvis.at/2d3d/technology/stereomatching/images/segment-based-stereomatching.pdf.
10. Wang Z., Zheng Z. A region based stereo matching algorithm using cooperative optimization, CVPR, 2008, available at: http://vision.middlebury.edu/stereo/eval/papers/CORegion.pdf.
11. Medvedev M. Y., Lazarev V. S. A path planning method for a moving object group using clustering in a two-dimensional environment, Nauchnyj vestnik Novosibirskogo gosudarstvennogo tekhnicheskogo universiteta, 2019, no. 4(77). pp. 45—54, doi 10.17212/1814-1196-2019-4-45-54, EDN FVNLJV (in Russian).
12. Skvorcov A. V. Delaunay triangulation and its application, Tomsk, Publishing house of Tomsk university, 2002, 128 p. (in Russian).
13. Levin B. A., Rosenberg I. N., Tsvetkov V. Y. Modeling of the basic relief based on Delaunay triangulation, Railway Science and Technology, 2018, vol. 2, no. 1 (5), pp. 3—15.
14. Zheleznyakova A. L., Surzhikov S. T. A Molecular dyญnamics-based triangulation of multiple nurbs-surfaces for complex products of the aviation and space-rocket industry, Fiziko-himiches-kaya kinetika v gazovoj dinamike, 2014, vol. 15, no 1, pp. 6, EDN UAHFHZ (in Russian).
15. Rebay S. Efficient Unstructured Mesh Generation by Means of Delaunay Triangulation and Bowyer-Watson Algorithm, Journal of Computational Physics, May 1993, vol. 106, iss. 1, p. 127.
16. Skvorcov A. V., Mirza N. S. Algorithms for constructing and analyzing triangulation, Tomsk, Publishing house of Tomsk university, 2006, 168 p., EDN SBVWBL (in Russian).
17. Batenkov A. A., Man'yakov Yu. A., Gasilov A. V., Yakov-lev O. A. Mathematical model of optimal triangulation, Informatika i ee primeneniya, 2018, vol. 12, no. 2, pp. 69—74, doi: 10.14357/19922264180210, EDN USPXIK (in Russian).
18. Salibekyan S. M., Panfilov P. B. Object-attribute architecture is a new approach to object systems developing, Informacionnye Tehnologii, 2012, no. 2, pp. 8—14 (in Russian).
19. Salibekyan S. M., Vishnekov A., Ivanova E. Methodology of Mean Shift Clustering Algorithm Implementation Based on Dataflow Computer, Proceedings of 2019 XVI International Symposium "Problems of Redundancy in Information and Control Systems" (REDUNDANCY)6 IEEE, 20196 pp. 177—180, doi: 10.1109/RE-DUNDANCY48165.2019.9003312.
20. Salibekyan S. M. High-level Language Translation Cotrolled by Dataflow, Informacionnye Tehnologii, 2024, vol. 30, no. 4, pp. 261—268 (in Russian).
21. Cormen T., Leiserson Ch., Rivest R., Klifford Sh. Introduction to Algorithms, Moscow, Sankt-Peterburg, Dialektika, 2019, 1323 p. (in Russian).

To the contents