The SFA-LSSVM as a Decision Support System for Mitigating Liquefaction Disasters

Julian Pratama Putra Thedja, Jui-Sheng Chou, Tri Joko Wahyu Adi

Abstract


Advanced data mining techniques are potential tools for solving civil engineering problems. This study proposes a novel classification system that integrates smart firefly algorithm (SFA) with least squares support vector machine (LSSVM). SFA is an optimization algorithm which combines firefly algorithm (FA) with smart components, namely chaotic logistic map, chaotic gauss/mouse map, adaptive inertia weight and Lévy flight to enhance optimization solutions. The least squares support vector machine (LSSVM) was adopted in this study for its superior performance of solving real-world problems. Based on the provided engineering data, the analytical results confirm that the SFA-LSSVM has 95.18% prediction accuracy

Keywords


Data mining; optimization; firefly algorithm; support vector machines; liquefaction

Full Text:

PDF

References


A. Kazem, E. Sharifi, F. K. Hussain, M. Saberi, and O. K. Hussain, "Support vector regression with chaos-based firefly algorithm for stock market price forecasting," Applied Soft Computing, vol. 13, pp. 947-958, 2// 2013.

C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, pp. 273-297, 1995.

J. A. Suykens, T. Van Gestel, J. De Brabanter, B. De Moor, and J. Vandewalle, Least squares support vector machines vol. 4: World Scientific, 2002.

J. A. K. Suykens, "Nonlinear modelling and support vector machines," in Instrumentation and Measurement Technology Conference, 2001. IMTC 2001. Proceedings of the 18th IEEE, 2001, pp. 287-294 vol.1.

X.-S. Yang, "Firefly algorithms for multimodal optimization," in Stochastic algorithms: foundations and applications, ed: Springer, 2009, pp. 169-178.

A. T. C. Goh and S. H. Goh, "Support vector machines: Their use in geotechnical engineering as illustrated using seismic liquefaction data," Computers and Geotechnics, vol. 34, pp. 410-421, 9// 2007.

A. Baykasoğlu, A. Çevik, L. Özbakır, and S. Kulluk, "Generating prediction rules for liquefaction through data mining," Expert Systems with Applications, vol. 36, pp. 12491-12499, 12// 2009.




DOI: http://dx.doi.org/10.12962/j23546026.y2015i1.1127

Refbacks

  • There are currently no refbacks.


View my Stat: Click Here

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.