The Estimation of Wind Velocity Using Data Mining Techniques

Sattar Nabee Rasool; Ahmet Koca; Karwan Hussein Qader

doi:10.25212/lfu.qzj.2.2.44

Authors

Sattar Nabee Rasool Software Engineering, Technology Faculty, Firat University-Turkey
Ahmet Koca Mechatronics Engineering, Technology Faculty, Firat University-Turkey
Karwan Hussein Qader School of Computing, Faculty of Technology, University of Portsmouth- United Kingdom

DOI:

https://doi.org/10.25212/lfu.qzj.2.2.44

Keywords:

Climate parameter estimation, data mining, predictive modeling, clustering, classification

Abstract

Estimation of wind velocity in real time is very essential as it can provide valuable information to people of different domains such as agriculture, aviation and tourism to mention few. Since climate data is growing exponentially it is hard to analyze it manually. Therefore, machine-learning techniques such as unsupervised and supervised learning methods are used to mine voluminous data and discover valuable knowledge. Predictive modeling in data mining is required to estimate climate parameters. In this paper, we proposed a framework that exploits data mining techniques such as J48, KNN, Neural Networks, SVM and Linear Regression. The framework takes climate dataset as input, completes training phase and makes different models using data mining algorithms. Finally, it ends by exploiting linear regression, which models the relationship between a dependent variable and an exploratory variable. The framework results in estimating wind velocity and finding prediction error rate. A prototype application is built based on Weka, which is used to demonstrate proof of the concept. The empirical results applied on all data are obtained from the Turkish Government Meteorology Services for summer months of 2013. It revealed that the proposed framework is useful to have a predictive model with respect to estimation of climate parameters.

Downloads

Download data is not yet available.

References

Mohd Tajul Rizal Ab Aziz and Yuhanis Yusof , “Graduates Employment Classification using Data Mining Approach", ICAST, pp. 1-8, 2016.

Vanya Van Belle and Paulo Lisboa. “ Research directions in interpretable machine learning models”. ESANN, pp. 533-541, 2013.

Nguyen Dang Minh and Nguyen Thi Minh Hue , ”Equity valuation model of vietnamese companies in a foreign securities market a simulation approach, IEEE, vol. 66, pp. 1155- 11, 2012.

RoccoLangone , CarlosAlzate , BartDeKetelaere , JonasVlasselaer , WannesMeert and JohaA.K.Suykens,“LS-SVMbasedspectralclusteringandregressionforpredicting maintenanceofindustrialmachines”, Elsevier Ltd, vol. 37 , pp. 268-278, 2014.

Marc Claesen, Frank De Smet, Johan A. K. Suykens and Bart De Moor, “Arobust ensemble approach to learn from positive and unlabeled data using svm base models. neurocomputing, ”SI on Advances in Learning with Label Noise, pp. 1-34, 2014.

Emanuele Frandi, Ricardo Ñanculef and Johan A. K. Suykens, ”A partan-accelerated frank-wolfe algorithm for large-scale svm classification”, pp. 1-19, 2015.

Carlos M. Alaz, Micha•el Fanuel and Johan A. K. Suykens. “Robust classification of graph-based data” , pp. 1-8, 2016.

Hee-su Chae, Byung-oh Jo, Sang-Hyun Choi and Twae-kyung Park, “ Feature selection for intrusion detection using nsl-kdd”, isbn, pp. 184-187, 2013.

Min Chen ,” Shiwen Mao and Yunhao Liu. big data,” A Survey.Springer, vol. 19 , pp. 171-209, 2014.

Xiaolin Huang, Lei Shi, and Johan A. K. Suykens. “ Solution path for pin-svm classifiers with positive and negative values,” pp. 1-10, 2012.

Siamak Mehrkanoon and Johan A. K. Suykens. “Non-parallel semi-supervised classification based on kernel spectral clustering,” pp. 1-8, 2014.

Lucas Drumetz, Miguel Angel Veganzones, Ruben Marrero, Guillaume Tochon, Mauro Dalla Mura, Giorgio Licciardi, Christian Jutten and Jocelyn Chanussot, “Hyperspectral Local intrinsic dimensionality”, HAl, pp. 1-16. 2016.

Folorunsho Olaiya and Adesesan Barnabas Adeyemo . (2012). Application of Data Mining Techniques in Weather Prediction and Climate Change Studies . Information Engineering and Electronic Business, p51-59.

G.Vamsi Krishna (2015) A Review of Weather Forecasting Models-Based on Data Mining and Artificial Neural Networks 06 , p214-22.

Jurgen Schmidhuber,“Deep learning in neural networks: an overview”, pp. 1-88, 2014.

Corinna Cortes, Xavi Gonzalvo and Vitaly Kuznetsov, ” Adanet: adaptive structural learning of artificial neural networks”, pp. 1-20, 2016.

Mohammad Khubeb Siddiqui and Shams Naahid, ” Analysis of kdd cup 99 dataset using clustering based data mining”, International Journal of Database Theory and Application, vol. 6, (1-5), pp. 23-34, 2013.

Erich Schubert, Alexander Koos and Tobias Emrich ,” A framework for clustering uncertain data” , pp. 1976-1979, 2012.

Gaurav L. Agrawal and Hitesh Gupta, ” Optimization of c4.5 decision tree algorithm for data mining application” International Journal of Emerging Technology and Advanced Engineering, vol. 3, (1-3), pp. 341-345, 2013.

Thierry Denoeux, Orakanya Kanjanatarakul and Songsak Sriboonchitta, ” Ek-nnclus: A clustering procedure based on the evidential k-nearest neighbor rule,” pp. 1-39, 2016.

Dhaval Sanghavi, Hitarth Patel and Sindhu Nair, “Logistic regression in data mining and its application in identification ofdisease”, International Journal of Current Engineering and Technology , vol.4, (1-6), pp. 3837-3839, 2014.