Title :
Prediction of earthquake in Yunnan region based on the AHC over sampling
Author :
Tan, Kai ; Cai, Xiushan
Author_Institution :
Coll. of Math., Phys. & Inf. Eng., Zhejiang Normal Univ., Jinhua, China
Abstract :
The data of earthquake of magnitude 3.5 or greater that happened during the 1970 and 2008 in Yunnan region (22 degrees and 28 degrees north, 98 degrees and 104 degrees east) were compiled and analyzed in this paper. After calculating the seismicity indicators and constructing the initial data set, AHC over sampling method was used on the imbalanced data. Then small earthquakes and large ones during the 1999 and 2008 were predicted and verified with the support vector machines (SVM) which contains different error cost. The result performs well, and it provides a new way for the earthquake prediction.
Keywords :
earthquakes; geophysical techniques; geophysics computing; pattern clustering; sampling methods; seismology; support vector machines; AHC over sampling method; agglomerative hierarchical clustering; earthquake prediction; seismicity indicators; support vector machines; Costs; Data engineering; Data mining; Earthquake engineering; History; Information analysis; Mathematics; Physics; Sampling methods; Support vector machines; Biased support vector machines; Earthquake prediction; Over sampling; Seismicity indicators;
Conference_Titel :
Control and Decision Conference (CCDC), 2010 Chinese
Conference_Location :
Xuzhou
Print_ISBN :
978-1-4244-5181-4
Electronic_ISBN :
978-1-4244-5182-1
DOI :
10.1109/CCDC.2010.5498782
