USING DATA MINING TECHNIQUES FOR METEOROLOGICAL FIGURES ANALYSIS

Author:

Kazymyr Volodymyr, Chernihiv National University of Technology (95 Shevchenka Str., 14027 Chernihiv, Ukraine)

Нerasymenko Oksana, Chernihiv National University of Technology (95 Shevchenka Str., 14027 Chernihiv, Ukraine)

Language: ukrainian

Annotation:

This article describes several approaches to using Data Mining techniques for processing and analysis of the meteorological data. The Process of Knowledge Discovery in Databases (KDD) and some method of Data Mining (DM), one of the KDD’s step, are briefly described in the article. As an example of using Data Mining techniques for meteorological figures analysis a temperature forecasting by neural networks is performed in this article (as input data we used meteorological figures from Chernihiv weather station for 2013-2015 years).

Key words:

Knowledge Discovery in Databases, Data Mining, neural networks, multilayer perceptron, meteorological figures forecasting

References:

  1. Анализ данных и процессов : учеб. пособие / [А. А. Барсегян, М. С. Куприянов, И. И. Холод, М. Д. Тесс, С. И. Елизаров]. – [3-е изд., перераб. и доп.]. – СПб. : БХВ-Петербург, 2009. – 512 с.

  2. Bartok J. Data Mining for fog prediction and low clouds detection / J. Bartok, F. Babiˇc, P. Bedn´ar, J. Paraliˇc, J. Kov´aˇc, I. Bartokov´a, L. Hluch´y, M. Gera // Computing and Informatics. –2011. ‑ Vol. 30. – Р. 1441–1464.

  3. Bilgin T. A. data mining application on air temperature database / T. А. Bilgin, A. Çamurcu // Advances in Information Systems. ‑ Springer Berlin Heidelberg. – 2005. ‑ Р. 68–76.

  4. Fayyad U. From Data Mining to Knowledge Discovery in Databases / U. Fayyad, G. Piatetsky-Shapiro, P. Smyth // Al Magazine. – 1996. – № 17 (3): FALL. ‑ Р. 37–54.

  5. Fonte P. M. Wind speed prediction using artificial neural networks / P. M. Fonte, G. X. Silva, J. C. Quadrado // Proceedings of the 6th WSEAS Int. Conf. on neural networks, Lisbon, Portugal, June 16–18, 2005. – Р. 134–139.

  6. Han J. Data Mining: concepts and techniques / J. Han, M. Kamber, J. Pei. – 3rd ed. – Elsevier, 2011. – 744 p.

  7. Hand D. Principles of Data Mining / D. Hand, H. Mannila, P. Smyth. – Cambridge, Massachusetts : MIT Press, 2001. – 546 p.

  8. Hartigan J. A. A K-Means clustering algorithm / J. A. Hartigan, M. A. Wong // Journal of the Royal Statistical Society. Series C (Applied Statistics). – 1979. ‑ Vol. 28, No.1. ‑ Р. 100–108.

  9. Hayati M. Temperature forecasting based on neural network approach / M. Hayati, Z. Mohebi // World Applied Sciences Journal. – 2007. – Vol. 2, Num. 6. – Р. 613–620.

  10. Kotsiantis S. Using data mining techniques for estimating minimum, maximum and average daily temperature values / S. Kotsiantis, A. Kostoulas, S. Lykoudis, A. Argiriou, K. Menagias // International Journal of Mathematical, Physical and Engineering Sciences. – 2008. ‑ Vol. 1, Num. 1. ‑ Р. 16–20.

  11. Kumar V. The Top ten algorithms in Data Mining / V. Kumar, X. Wu. – Taylor&Francis Group, LLC, 2009. – 2008 p.

  12. Li X. Real-time storm detection and weather forecast activation through data mining and events processing / X. Li, B. Plale, N. Vijayakumar, R. Ramachandran, S. Graves, H. Conover // Earth Sci Inform. – 2008. – Vol. 1. – Р. 49–57.

  13. Maqsood I. An ensemble of neural networks for weather forecasting / I. Maqsood, M. R. Khan, A. Abraham // Neural Computing & Applications. 2004. – Vol. 1, Num. 2. – Р. 112–122.

  14. Mitra S. Data mining: multimedia, soft computing and bioinformatics / S. Mitra, T. Acharya. – John Wiley&Sons, Inc., 2003. – 424 p.

  15. Quinlan J. R. C4.5: Programs for machine learning. ‑ Morgan Kaufmann, Los Altos, 1993. – 303 p.

  16. Quinlan J. R. Induction of decision trees / J. R. Quinlan // Machine Learning 1, 1986. – Р. 81–106.

  17. Rokach L. Data Mining with decision trees: theory and applications / L. Rokach, O. Maimon. ‑ World Scientific Publishing, 2007. – Vol. 61. – 270 p. – (Series in Machine Perception and Artificial Intelligence).

  18. Shanmuganathan S. Data Mining methods to generate severe wind gust models / S. Shanmuganathan, Ph. Sallis // Atmosphere. – 2014. – Vol. 5. – Р. 60–80.

  19. Yang Y. CLOPE: A fast and effective clustering algorithm for transactional data / Y. Yang, H. Guan, J. You // Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2002. ‑ Р. 682–687.

  20. Zaki M. J. Data mining and analysis: fundamental concepts and algorithms / M. J. Zaki, M. J. Wagner. – NY : Cambridge University Press, 2014. – 593 p.

Download