C&SA | Contents

Volume 55 >>> № 2 MARCH — APRIL 2019

UDC 004.93

S.V. Mashtalir¹, M.I. Stolbovyi², S.V. Yakovlev³

¹ Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

sergii.mashtalir@nure.ua

² Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

st.mihail92@gmail.com

³ N. Ye. Zhukovskiy National Aerospace University “Kharkiv Aviation Institute,” Kharkiv, Ukraine

svsyak7@gmail.com

VIDEO SEQUENCES CLUSTERING BY THE k-HARMONIC MEANS

Abstract. The study is devoted to segmentation–clustering of video sequences by the analysis of multidimensional time sequences. An approach is proposed for using an iterative deepening time warping in conjunction with the matrix harmonic k-means. This segmentation-clustering procedure, unlike the traditional approach, is insensitive to the initial centroids selection, which is especially useful in the analysis of arbitrary mass data.

Keywords: segmentation, clustering, multidimensional sequences, video, dynamic warping.

FULL TEXT

REFERENCES

Gan G., Ma C., Wu J. Data clustering: Theory, algorithms and applications. Philadelphia: SIAM, 2007. 466 p.

Jain A.K., Dubes R.C. Algorithms for clustering data. Englewood Cliffs, N.J.: Prentice Hall, 1988. 320 p.

Olson D.L., Dursun D. Advanced data mining techniques. Berlin: Springer, 2008. 180 p.

Hulianytskyi L., Malyshko S. Big data in information analytical system “NEWSCAPE”. In: Data Stream Mining & Processing: Proc. IEEE First Int. Conf. on Data Stream Mining & Processing (23–27 August, 2016, Lviv, Ukraine) 2016. P. 382–386.

Hulianytskyi L., Riasna I. Formalization and classification of combinatorial optimization problems. Optimization Methods and Its Applications. 2017. Vol. 130. P. 239–250.

Hulianytskyi L., Riasna I. Automatic classification method based on a fuzzy similarity relation. Cybernetics and Systems Analysis. 2016. Vol. 52, N 1. P. 30–37.

Vedmid A.G., Mashtalir S.V. Sakalo E.S. Matrix self-learning Kohonen map in image processing problems. Systemy Upravlinnya, Navihatsiyi ta Zv'yazku. 2009. Issue. 1. P. 188–192.

Bodyanskiy Ye., Volkova V., Skuratov M. Matrix neuro-fuzzy self-organizing clustering network. Scientific Journal of Riga Technical University. Computer Science. Information Technology and Management Science. 2011. Vol. 49. P. 54–58.

Mashtalir V.P., Yakovlev S.V. Point-set methods of clusterization of standard information. Cybernetics and Systems Analysis. 2001. Vol. 37, N 3. P. 295–307.

Han J., Kamber M. Data mining: Concepts and techniques. San Francisco: Morgan Kaufmann, 2006. 26 p.

Xu R., Wunsch D. Survey of clustering algorithms. IEEE Transactions on Neural Networks. 2005. Vol. 16, N 3. P. 645–678.

Gngr Z., nler A. K-harmonic means data clustering with tabu-search method. Applied Mathematical Modelling. 2008. Vol. 32, N 6. P. 1115–1125.

Zhang B., Hsu M., Dayal V. K-harmonic means: A spatial clustering algorithm with boosting. First International Workshop on Temporal, Spatial and Spatio-Temporal Data Mining, 2000. P. 31–45.

Abonyi J., Feil B., Nemeth S., Arva P. Fuzzy clustering based segmentation of timeseries. Lecture Notes in Computer Science. 2003. Vol. 2810. P. 275–285.

Liao T.W. Clustering of time series data: A survey. Pattern Recognition. 2005. Vol. 38, N 11. P. 1857–1874.

Berndt D.J., Clifford J. Using dynamic time warping to find patterns in time series. In: Proc. 3rd International Conference on Knowledge Discovery and Data Mining. KDD Workshop. 1994. P. 359–370.

Setlak G., Bodyanskiy Y., Pliss I., Vynokurova O., Peleshko D., Kobylin I. Adaptive fuzzy clustering of multivariate short time series with unevenly distributed observations based on matrix neuro-fuzzy self-organizing network. Advances in Intelligent Systems and Computing. 2018. Vol. 643. P. 308–315.

Bodyanskiy Y., Kobylin I., Rashkevych Y., Vynokurova O., Peleshko D. Hybrid fuzzy clustering algorithm of unevenly and asynchronically spaced time series in computer engineering. In: Proc. 14th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (20–24 February 2018, Lviv–Slavske, Ukraine). P. 930–935.

Chu S., Keogh E., Hart D., Pazzani M. Iterative deepening dynamic time warping for time series. In: Proc. of the 2nd SIAM International Conference on Data Mining, 2002. P. 195–212.

Gerasin S.N., Shlyakhov V.V., Yakovlev S.V. Set coverings and tolerance relations. Cybernetics and Systems Analysis. 2008. Vol. 43, N 3. P. 333–340.

Stoyan Y.G., Yakovlev S.V. Configuration space of geometric objects. Cybernetics and Systems Analysis. 2018. Vol. 54, N 5. P. 716–726.

Yakovlev S.V. On some classes of spatial configurations of geometric objects and their formalization. Journal of Automation and Information Sciences. 2018. Vol. 50, N 9. P. 38–50.