A Rough Set Approach Aim to Space Weather and Solar Storms Prediction

  • Reza Mahini
  • Caro Lucas
  • Masoud Mirmomeni
  • Hassan Rezazadeh
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6782)


This paper illustrates using Rough set theory as a data mining method for modeling Alert systems. A data-driven approach is applied to design a reliable alert system for prediction of different situations and setting off of the alerts for various critical parts of human industry sections. In this system preprocessing and reduction of data with data mining methods is performed. Rough set learning method is used to attain the regular and reduced knowledge from the system behaviors. Finally, using the produced and reduced rules extracted from rough set reduction algorithms, the obtained knowledge is applied to reach this purpose. This method, as demonstrated with successful realistic applications, makes the present approach effective in handling real world problems. Our experiments indicate that the proposed model can handle different groups of uncertainties and impreciseness accuracy and get a suitable predictive performance when we have several certain features set for representing the knowledge.


Data Mining Rough Sets Data-Driven Modeling Solar Activities Alert Systems 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mitra, S., Pal, S.K., Mitra, P.: Data mining in Soft Computing Framework: A Survey. IEEE transactions on neural networks 13(1) (January 2002)Google Scholar
  2. 2.
    Lundstedt, H.: Neural networks and prediction of solar terrestrial effects. Planet Space Science 40, 457–464 (1992)CrossRefGoogle Scholar
  3. 3.
    Boberg, F., Wintoft, P., Lundstedt, H.: Real time Kp predictions from solar wind data using neural networks. Phys. Chem. Earth. 25(4), 275–280 (2000)Google Scholar
  4. 4.
    Gholipour, A., Abbaspour, A., Araabi, B.N., Lucas, C.: Enhancements in the prediction of solar activity by locally linear model tree. In: Proc. of MIC 2003: 22nd Int. Conf. on Modeling, Identification and Control, Innsbruck, Austria, pp. 158–161 (2003)Google Scholar
  5. 5.
    Gholipour, A., Lucas, C., Araabi, B.N., Mirmomeni, M., Shafiee, M.: Extracting the main patterns of natural time series for long-term neurofuzzy prediction. Neural Comput. & Applic. Springer, London (2006), doi:10.1007/s00521-006-0062-xGoogle Scholar
  6. 6.
    Attia, A.F., Hamed, R.A., Quassim, M.: Prediction of Solar Activity Based on Neuro-Fuzzy Modeling. Springer Solar Physics 227, 177–191 (2005)CrossRefGoogle Scholar
  7. 7.
    Gholipour, A., Araabi, B.N., Lucas, C.: Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study. Springer Neural Processing Letters 24, 217–239 (2006)CrossRefGoogle Scholar
  8. 8.
    Gholipour, A., Lucas, C., Araabi, B.N., Shafiee, M.: Solar activity forecast: Spectral analysis and neurofuzzy prediction. Elsevier Journal of Atmospheric and Solar-Terrestrial Physics 67, 595–603 (2005)CrossRefGoogle Scholar
  9. 9.
    Prestes, A., Rigozo, N.R., Echera, E., Vieira, L.E.A.: Spectral analysis of sunspot number and geomagnetic indices (1868–2001). Journal of Atmospheric and Solar-Terrestrial Physics 68, 182–190 (2006)CrossRefGoogle Scholar
  10. 10.
    Lucas, C., Abbaspour, A., Gholipour, A., Araabi, B.N., Fatourechi, M.: Enhancing the Performance of Neurofuzzy Predictors by Emotional Learning Algorithm. Informatica 27(2), 165–174 (2003)zbMATHGoogle Scholar
  11. 11.
    Babaie, T., Karimizandi, R., Lucas, C.: Prediction of solar conditions by emotional learning. Intelligent Data Analysis 9, 1–15 (2006)Google Scholar
  12. 12.
    Chen, Y.P., Wu, S.N., Wang, J.S.: A Hybrid Predictor for Time Series Prediction. IEEE, Los Alamitos (2004), 0-7803–8359Google Scholar
  13. 13.
    Mahini, R., Lucas, C., Mirmomeni, M.: Designing a New Alert System Based on KM in Fuzzy Expert System. In: 2nd Int. Conf. knowledge management. KMCM (2008)Google Scholar
  14. 14.
    Cloete, I., Zurada, J.M.: Knowledge-Based Neurocomputing. MIT Press, Cambridge (2000)Google Scholar
  15. 15.
    Li, R.F., Wang, X.Z.: Dimension reduction of process dynamic trends using independent component analysis. Computers and chemical engineering 26, 467–473 (2002)CrossRefGoogle Scholar
  16. 16.
    Chimphlee, S., Salim, N., Ngadiman, M.S.B., Chimphlee, W., Srinoy, S.: Independent component analysis and rough fuzzy based approach to web usage mining. In: Proceeding of 24th IASTED international Multi-Conference Artificial Intelligence and applications, February 13–16 (2006)Google Scholar
  17. 17.
    De Zeeuw, D.L., Gombosi, T.I., Groth, C.P., Powell, K.G., Stout, F.: An adaptive MHD method for global space weather simulations. IEEE Tran. on Plasma Science 28(6), 1956–1965 (2002)CrossRefGoogle Scholar
  18. 18.
    Horton, W., Doxas, I.: A low dimensional dynamical model for the solar wind driven geotail-ionosphere system. Journal of Geophysical Research 103, 4561–4572 (1998)CrossRefGoogle Scholar
  19. 19.
    Freeman, J., Nagai, A., Reiff, P., Denig, W., Gussenhoven, S.S., Heinermann, M., Rich, F., Hairston, M.: The use of neural networks to predict magnetospheric parameters for input to a magnetospheric forecast model. In: Joselyn, J., Lundstedt, H., Trollinger (eds.) Artificial Intelligence Applications in Solar Terrestrial Physics, Boulder, Colorado, vol. 167, Natl. Oceanic and Atmos. Admin, Boulder, Colorado (1994)Google Scholar
  20. 20.
    Gleisner, H., Lundstedt, H., Wintoft, P.: Predicting geomagnetic storms from solar wind data using time delay neural networks. Annales Geophysicae 14, 679–686 (1996)CrossRefGoogle Scholar
  21. 21.
    Gleisner, H.: Solar wind and Geomagnetic activity: predictions using neural networks. PhD thesis, Lund University, Lund, Sweden (2000)Google Scholar
  22. 22.
    Pawlak, Z.: Rough sets. International Journal of Computer and Information Sciences 11, 341–356 (1982)MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Pawlak, Z.: Rough Sets, Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Dordrecht (1991)zbMATHGoogle Scholar
  24. 24.
    Ziarko, W. (ed.): Rough Sets, Fuzzy Sets and Knowledge Discovery. Proceeding of the International Workshop on Rough Sets and Knowledge Discovery (RSKD 1993), Banff, Alberta, Canada, October 12–15. Springer, Heidelberg (1993)Google Scholar
  25. 25.
    Huynh, V., Ho, T., Nakamori, Y.: An Overview on the Approximation Quality Based on Rough-Fuzzy Hybrids. Studies in Fuzziness and Soft Computing (2008)Google Scholar
  26. 26.
    Shen, Q., Chouchoulas, A.: A rough-fuzzy approach for generating classification rules. Pattern Recognition Society, pp. 31–3203. Elsevier Science Ltd., Amsterdam (2002)zbMATHGoogle Scholar
  27. 27.
    Jensen, R., Shen, Q.: Fuzzy–rough attribute reduction with application to web categorization. Fuzzy Sets and Systems 141, 469–485 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    The Space Physics Interactive Data Resource,
  29. 29.
    NOAA’s National Geophysical Data Center,
  30. 30.
    Space Weather Alerts Archives,

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Reza Mahini
    • 2
  • Caro Lucas
    • 1
  • Masoud Mirmomeni
    • 1
    • 4
  • Hassan Rezazadeh
    • 3
  1. 1.Control and Intelligent Processing Center of Excellence, School of Electrical and Computer EngineeringUniversity of TehranIran
  2. 2.Electrical, Computer and IT Eng. DepartmentPayame Noor University of TabrizIran
  3. 3.Industrial Engineering DepartmentUniversity of TabrizIran
  4. 4.Departmentment of Computer Science and EngineeringMichigan State UniversityUSA

Personalised recommendations