论文部分内容阅读
本文将云南省地震局多年来积累的关于中强震发生的地质构造、地貌、地球物理场、地形变等特征基础资料,用于Cora-3算法的模式识别,得出云南省潜在震源区的背景指标,结果是比较理想的。“投票”结果表明,80%的学习集D类对象仍被识别为D类,85%的学习集N类对象仍被识别为N类,控制试验的结果也表明识别结果是比较稳定和可靠的。
In this paper, the basic data about the geological structures, geomorphology, geophysical field and topography change that have been accumulated by the Seismological Bureau of Yunnan Province over the years are used for the pattern recognition of Cora-3 algorithm and the potential source regions in Yunnan Province are obtained Background indicators, the result is ideal. “Voting” results show that 80% of learning class D objects are still identified as class D, 85% of learning class N class objects are still identified as N class, the results of the control experiment also show that the recognition result is relatively stable and reliable .