Feature Selection with Support Vector Machines Applied on Tornado Detection

Budi Santosa


In this paper, a linear programming support vector machine which is based on L1-norm is applied to do feature selection in the tornado data set. The data is the ouputs of Weather Surveillance Radar 1998 Doppler (WSR-88D). The approach is evaluated based on the indices of probability of detection, false alarm rate, bias and Heidke skill. Tornado circulation attributes/variables derived largely from the National Severe Storms Laboratory Mesocyclone Detection Algorithm (MDA) have been investigated for their efficacy in distinguishing between mesocyclones that become tornadic from those which do not.


Classification; Detection; Feature Selection; Bayesian Neural Networks; Machine Learning; Linear Programming Support Vector Machines; Linear Discriminant Analysis; Performance Indices

Full Text:



Bishop, C.M. (1995), Neural Networks for Pattern Recognition, University Press, Oxford.

Bhattacharyya, C., Grate, L.R., Rizki, A., Radisky, D., Molina, F.J., Jordan, M.I., Bissell, M.J., and Mian, I.S. (2003), ‘Simultaneous Classification and Relevant Feature Identification in High-dimensional Spaces: Application to Molecular Profiling Data’, Signal Processing, Vol. 83, Issue 4, pp. 729-743.

Donoho, D. and Huo, X. (1999), ‘Uncertainty Principles and Ideal Atomic Decomposition’, Technical Report, Statistics Department, Stanford University, http://www-stat.stan ford.edu/~donoho/reports.html.

Doswell, C.A. III, Davies-Jones, R. and Keller, D. (1990), ‘On Summary Measures of Skill in Rare Event Forecasting Based on Contingency Tables’, Weather and Forecasting, Vol. 5, pp. 576-585.

Haykin, S. (1999), Neural Networks: A Comprehensive Foundation, 2nd Edition, Prentice-Hall, Upper Saddle River, NJ.

Heijden, F., Duin, R.P.W., Ridder, D. and Tax, D.M.J. (2004), Classification, Parameter Estimation and State Estimation: An Engineering Approach Using MATLAB, John Wiley and Sons Ltd., West Sussex, England.

Lakshmanan, V., Stumpf, G. and Witt, A. (2005), ‘Neural Network for Detecting and Diagnosing Tornadic Circulations using the Mesocyclone Detection and Near Storm Environment Algorithms’, 21st Int'l Conference on Information Processing Systems, Amer. Meteo. Soc., San Diego, CD-ROM, pp. J5.2.

MacKay, D. (1992a), ‘A Practical Bayesian Framework for Backpropagation Networks’, Neural Computation, Vol. 4, pp. 448-472.

MacKay, D. (1992b), ‘The Evidence Framework Applied to Classification Networks’, Neural Computation, Vol. 4, pp.720-736.

Marzban, C. and Stumpf, G. J. (1996), ‘A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes’, Journal of Applied Meteorology, Vol. 35, pp. 617-626.

Murtagh, B.A. and Saunders, M.A. (1998), MINOS 5.5 USER’S GUIDE, Technical Report SOL 83-20R, Revised July 1998, Systems Optimization Laboratory, Department of Operations Research, Stanford University, Stanford.

Sigurdsson, S. (2002), Binary Neural Classifier, Version1.0,http://mole.imm.dtu.dk/toolbox/ann/.

Theodore, B.T., Santosa, B. and Richman, M.B. (2004), ‘Bayesian Neural Networks for Tornado Detection’, WSEAS Transaction on Systems, Vol. 3, Issue 10, pp. 3211-3216.

Wilks, D.S. (1995), Statistical Methods in the Atmospheric Sciences, Academic Press, London.

DOI: http://dx.doi.org/10.12962/j20882033.v18i1.178


  • There are currently no refbacks.

Creative Commons License

IPTEK Journal of Science and Technology by Lembaga Penelitian dan Pengabdian kepada Masyarakat, ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at http://iptek.its.ac.id/index.php/jts.