Statistical Feature Ranking and Fuzzy Supervised Learning Approach in Modeling Regional Rainfall Prediction Systems

Mavuri SudhaKumarappan Subbu

DOI 10.7160/aol.2017.090210
No 2/2017, June
pp. 117-126

Sudha, M. and Subbu, K. (2017) “Statistical Feature Ranking and Fuzzy Supervised Learning Approach in Modeling Regional Rainfall Prediction Systems", AGRIS on-line Papers in Economics and Informatics, Vol. 9, No. 2, pp. 117 - 126. ISSN 1804-1930. DOI 10.7160/aol.2017.090210.

Abstract

Rainfall prediction is an essential and challenging task in hydro-meteorology. Most of the existing weather dataset used for prediction consists of observatory record of several atmospheric parameters. Identifying the signi cant parameters from irrelevant and redundant parameter set for weather prediction is important because irrelevant parameters may decrease the prediction accuracy. The main intent of this research is to identify the in uencing weather parameters for improving daily rainfall forecast ef ciency. A parameter selection module identi es the signi cant parameter based on information gain based feature ranking. Fuzzy supervised learning module evaluates the performance of fuzzy classi ers before and after parameter selection. In the evaluation phase, learning techniques was analyzed in terms of Accuracy Rate (AcR), Root Mean Squared Error (RMSE) and Misclassi cation Rate (McR). Experimental results revealed that, parameter subset selection has signi cantly improved the performance of the learning techniques. The investigation results identi ed minimum temperature, relative humidity and evapotranspiration as in uencing weather parameters for rainfall prediction. Empirical results revealed Fuzzy Unordered Rule Induction Algorithm (FURIA) as a suitable rainfall prediction approach. This fuzzy model achieved an enhanced accuracy rate of 84.10% after parameter selection with nominal misclassi cation rate of 0.1590%.

Keywords

Short-range rainfall prediction, statistical feature ranking, fuzzy rule induction and prediction accuracy.

References

  1. Abdul-Kader, H. M. (2009) “Neural networks training based on differential evolution algorithm compared with other architectures for weather forecasting”, International Journal of Computer Science and Network Security, Vol. 9, No.3, pp. 92-99. ISSN 1738-7906.
  2. Al-Matarneh, L., Sheta, A., Bani-Ahmad, S., Alshaer, J. and Al-oqily, I. (2014) “Development of temperature based weather forecasting models using neural networks and fuzzy logic”, International Journal of Multimedia and Ubiquitous Engineering, Vol. 9, No. 12, pp. 343-366. ISSN 1975-0080. DOI 10.14257/ijmue.2014.9.12.31.
  3. Bardossy, A., Duckstein, L. and Bogardi, I. (1995) “Fuzzy rule based classi cation of atmospheric circulation patterns”, International Journal of Climatology, Vol. 15, pp. 1087-1097. ISSN 1097-0088. DOI 10.1002/joc.3370151003.
  4. Blum, A. L. and Rivest, R. L. (1992) Training 3-node neural networks is NP-complete, Neural Networks, Vol. 05, pp. 117–127. ISSN 0893-6080.
  5. Dai, J. and Xu, Q. (2013) "Attribute selection based on information gain ratio in fuzzy rough set theory with application to tumour classi cation", Applied Soft Computing, Vol. 13, No. 1, pp. 211-221. ISSN 1568-4946. DOI 10.1016/j.asoc.2012.07.029.
  6. Hühn, J. and Hüllermeier, E. (2009) “FURIA: An algorithm for unordered fuzzy rule induction”, Data Mining and Knowledge Discovery, Vol. 19, No. 3, pp. 293-319. ISSN 1384-5810. DOI 10.1007/s10618-009-0131-8.
  7. Hühn, J. and Hüllermeier, E. (2009) “FURIA: An algorithm for unordered fuzzy rule induction”, Data Mining and Knowledge Discovery, Vol. 19, No. 3, pp. 293-319. ISSN 1384-5810. DOI 10.1007/s10618-009-0131-8.
  8. Ishibuchi, H. and Nakashima, T. (2001) “Effect of rule weights in fuzzy rule-based classi cation systems”, IEEE Transactions on Fuzzy Systems, Vol. 9, No. 4, pp. 506-515. ISSN 1063-6706.
  9. Kira, K. and Rendell, L. A. (1992) “The feature selection problem: Traditional methods and a new algorithm”, 10th National Conference on Arti cial Intelligence (AAAI-92), San Jose, California, pp. 122-126.
  10. Lee, J., Kim, J., Lee, J. H. I., Cho, I., Lee, J. W., Park, K. H. and Park, K. (2012) “Feature selection for heavy rain prediction using genetic algorithms”, International Symposium on Advanced Intelligent Systems, Kobe, Japan, pp. 830-833.
  11. Li, K. and Liu, Y. (2005) “A rough set based fuzzy neural network algorithm for weather prediction”, Proceedings of International Conference on Machine Learning and Cybernetics, Guangzhou, pp. 1888-1892. DOI 10.1109/91.940964.
  12. Liu, J. N. K., Li, B. N. L. and Dillon, T. S. (2001) “An improved Naive Bayesian classi er technique coupled with a novel input solution method”, IEEE Transactions on Systems, Man and Cybernetics, Vol. 31, No. 2, pp. 249-256. ISSN 2168-2216. DOI 10.1109/5326.941848.
  13. Maqsood, I., Khan, M. R. and Abraham, A. (2004) “An ensemble of neural networks for weather forecasting”, Neural Computing and Application, Vol. 13, No. 2, pp. 112-122. ISSN 1433-3058. DOI 10.1007/s00521-004-0413-4.
  14. McBratney, A. and Moore, A. (1985) “Application of fuzzy sets to climatic classi cation", Agricultural and Forest Meteorology, pp. 165-185. ISSN 0168-1923. DOI 10.1016/0168-1923(85)90082-6.
  15. Mitra, A., Meena, L. and Giri, R. (2006) “Forecasting of temperature-humidity index using fuzzy logic approach”, National Conference on Advances in Mechanical Engineering (AIME), January 2006.
  16. Nikam, V. B. and Meshram, B. B. (2013) “Modeling rainfall prediction using data mining method a bayesian approach”, 5th International Conference on Computational Intelligence, Modelling and Simulation, Seoul, Korea. pp. 132-136. DOI 10.1109/CIMSim.2013.29.
  17. Niksaz, P. and Latif, A. M. (2014) “Rainfall events evaluation using adaptive neural fuzzy inference system”, International Journal of Information Technology and Computer Science, Vol. 9, pp. 46-51. E-ISSN 2074-9015, ISSN 2074-9007. DOI 10.5815/ijitcs.2014.09.06.
  18. Novakovic, J. (2009) “Using information gain attribute evaluation to classify sonar targets”, 17th Telecommunications forum, Serbia, Belgrade. pp. 1351-1354.
  19. Seo, J. H., Lee, Y. H. and Kim, Y. H. (2014) "Feature selection for very short-term heavy rainfall prediction using evolutionary computation", Advances in Meteorology. Vol. 2014, 15 p. ISSN 1943-5584. DOI 10.1155/2014/203545.
  20. Seo, J. H. and Kim, Y. H. (2012) "Genetic feature selection for very short-term heavy rainfall prediction", Proceedings of the International Conference on Convergence and Hybrid Information Technology, Daejeon, Korea. pp. 312-322.
  21. Siedlecki, M. and J. Sklansky (1988) "On automatic feature selection", International Journal of Pattern Recognition and Arti cial Intelligence, Vol. 2, No. 2, pp. 197–220. ISSN 0218-0014. DOI 10.1142/S0218001488000145.
  22. Sudha, M. and Valarmathi, B. (2013) “Exploration on rough set based feature selection”, International Journal of Applied Engineering Research, Vol. 8, pp. 1555-1556. ISSN 0973-9769.
  23. Sudha, M. and Valarmathi, B. (2014) “Rainfall forecast analysis using rough set attribute reduction and data mining methods”, Agris on-line Papers in Economics and Informatics, Vol. 4, No. 4, pp. 145-154. ISSN 1804-1930.
  24. Sudha, M. and B. Valarmathi (2015) “Impact of hybrid intelligent computing in identifying constructive weather parameters for modeling effective rainfall prediction”, Agris on-line Papers in Economics and Informatics, Vol. 7, No. 4, pp. 151-160. ISSN 1804-1930.
  25. Sudha, M. and B. Valarmathi (2016) “Identi cation of effective features and classi ers for short term rainfall prediction using rough set based maximum frequency weighted feature reduction technique”, Journal of Computing and Information Technology, Vol. 24, No. 2, pp. 181-194. ISSN 1846-3908.
  26. Weka Software (2015) [Online]. http://www.cs.waikato.ac.nz/ml/weka/ [Assessed: August 20, 2015].
  27. Witten, I. H. and E. Frank (2005) “Data Mining: Practical Machine Learning Tools and Techniques”, Morgan Kaufmann, San Francisco, p. 525.
  28. Yu, L. (2005) “Toward integrating feature selection algorithms for classi cation clustering”, IEEE Transactions on Knowledge and Data Engineering, Vol. 17, No. 4.
  29. Zadeh, L.A. (1965) “Fuzzy Sets”, Information and Control, Vol. 8, pp. 338-353. DOI 10.1016/S0019-9958(65)90241-X.

Full paper

  Full paper (.pdf, 947.82 KB).