Seismic facies classification based on the improved transductive support vector machine

Article type: Research Article

Authors: Zhu, Yan-Wei

Affiliations: Department of Mathematics and Information Science, Tang Shan Normal University, Tang Shan, Hebei, China. E-mail: [email protected]

Abstract: In order to solve the problem of seismic facies classification, transductive support vector machine is improved. The improvement of transductive support vector machine model is proposed. Now the research of TSVM is only on the elementary stage, the optimization of TSVM is able to be solved theoretically, but it is quite difficult to find the exact solution. Therefore, we try to convert the optimization of TSVM into unconstraint problem, then we could able to construct smooth unconstraint problem with kernel, in order to create an optimized model which is easy to be solved by TSVM. The improvement of transductive support vector machine is applied to the seismic facies classification. This is a new method in the seismic facies classification never used. The experimental data show that the proposed algorithm can improve the seismic facies classification, economic benefit. The main positive feature of improved transductive support vector machine such as the less number of support vectors,there are the smaller training time and testing time and the higher correctly prediction.It has theoretical value and practical significance.

Keywords: Seismic facies, support vector machine, transductive support vector machine

DOI: 10.3233/JCM-150582

Journal: Journal of Computational Methods in Sciences and Engineering, vol. 15, no. 4, pp. 677-684, 2015