Improved Support Vector Machine and its Application


Article Preview

According to the complex and uncertain relationships between indexes and grades of flood hazard evaluation, as well as the deficiency of measured samples, an improved support vector machine (SVM) model was established to improve accuracy and efficiency of calculation. The function that comprehensively evaluated indexes of multi-dimensional disaster situation in one-dimensional continuous space could be realized, and effectively solved the incompatible problems of different evaluation results with single index. The results showed that the model based on improved support vector machine had a better ability of generalization and calculation speed by reduce constraint conditions. It is considered to have a good application prospect in multi-index comprehensive evaluation.



Edited by:

Qi Luo






Z. W. Huang et al., "Improved Support Vector Machine and its Application", Applied Mechanics and Materials, Vols. 20-23, pp. 147-153, 2010

Online since:

January 2010




[1] J.B. Sui, X.W. Chen, & X. Wang: Design and application of the flood loss evaluation system based on GIS and RS. Geoscience and Remote Sensing Symposium, 2005. IGARSS '05. Proceeding 2005 IEEE international. Vol. 2, pp.1372-1375, (2005).

DOI: 10.1109/igarss.2005.1525377

[2] Y.M. Wei, J.L. Jin, C.J. Yang, Y. Fan, & Q. D Chen: Theory of risk management of flood disaster, Beijing: Science Press, (2002).

[3] L.M. Zhao, K. Wang & P.H. Qiu: Synthetic evaluation of disaster. Systems Engineering-Theory & Practice, Vol. 17, No. 3, pp.63-69, (1997).

[4] Q.D. Yu & R.F. Shen: A grading model and its application of the comprehensive situation of natural disaster, Journal of Catastrophology, Vol. 12, No. 3, pp.12-17, (1997).

[5] S.S. Yang: A method of dividing gradation of the condition of the natural disaster considering the regional economy difference and its application, Systems Engineering -Theory & Practice, Vol. 17, No. 12, pp.93-100, (1997).

[6] Q.D. Yu: The limitation and improvement of the method of disaster situation grade measurement, Journal of Natural Disaster, 1993, Vol. 2, No. 2, pp.8-11, (1993).

[7] H.H. Wu & Z.N. Li: Fuzzy comprehensive evaluation method of disaster loss assessment based on interval numbers of three parameters, Journal of Natural Disaster, Vol. 17, No. 5, pp.64-69, (2008).

[8] Y. Gao, Y.X. Chen, Y.S. Ding & B.Y. Tang: Immune genetic algorithm based on network model for flood disaster evaluation, Journal of Natural Disaster, Vol. 15, No. 1, pp.110-114, (2006).

[9] J.L. Jin, X.L. Zhang & J. Ding: Projection pursuit model for evaluation grade of flood disaster loss. Systems Engineering-Theory & Practice, Vol. 22, NO. 2, 140-144, (2002).

[10] X.H. Yang, Z.F. Yang, Z.Y. Shen, G.H. Lou & J.Q. Li: Interpolation model for evaluating loss of flood disaster based on genetic projection pursuit, Journal of Catastrophology, Vol. 19, No. 4, pp.1-6, (2004).

[11] V.N. Vapnik: The nature of statistical learning theory, New York: Springer-Verlag, (1995).

[12] D. Kim, H. Lee & S. Cho: Response modeling with support vector regression, Expert Systems with Applications, Vol. 34, pp.1102-1108, (2008).

DOI: 10.1016/j.eswa.2006.12.019

[13] S.X. Du & T.J. Wu: Support vector machines for regression, Journal of System Simulation, Vol. 15, No. 11, pp.1580-1585, (2003).

[14] S.T. Chen & P.S. Yu: Pruning of support vector networks on flood forecasting, Journal of Hydrology, Vol. 347, NO. 1-2, pp.67-78, (2007).

[15] L. Ding & L. Tao: Improved algorithm and application of SVM for regression, Computer Engineering and Applications, Vol. 44, No. 6, pp.96-97, (2008).

In order to see related information, you need to Login.