期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2010
卷号：4
期号：3
页码：308-315
出版社：Computer Science Journals
摘要：Efficient and successful seismic event detection is an important and challenging issue in many disciplines, especially in tectonics studies and geo-seismic sciences. In this paper, we propose a fast, efficient, and useful feature extraction technique for maximally separable class events. Support vector machine classifier algorithm with an adjustable learning rate has been utilized to adaptively and accurately estimate small level seismic events. The algorithm has been less computation, so that economic impact will be high. Experimental results demonstrate the strength and robustness of the method.
关键词：Feature extraction; Support Vector Machines; Kernels; Seismic signals; Wavelet decomposition Energy
