摘要
结合粗糙集理论的属性约简与支持向量机的分类功能,建立了基于粗糙集与支持向量机的建筑物震害预测模型。该模型首先运用粗糙集理论,建立决策表,进行属性离散、属性重要性排序、属性约简和分类规则的提取,然后用所提取的关键成分训练支持向量机。该模型不但能有效降低建筑物震害影响因子数据维数及支持向量机的复杂程度,提高训练速度和分类精度,而且还能对各因子的影响程度进行排序。最后,通过实例验证了该模型的性能。
A model for seismic damage prediction of building is proposed based on two integrated intelligent algorithms ： attribute reduction algorithm of rough sets and support vector machines. At first, rough set theory is used to acquire the knowledge of classification, which includes decision table construction, attribute discretization, attribute importance ranking, attribute reduction and rule abstract. Then, the key components are extracted as the input of support vector machine. The method can reduce the dimensions of the data and the complexity, and raise the efficiency of training and the accuracy of prediction. The effect extent to the earthquake-resistance performance of these factors can be obtained in the model. Finally, it is validated applying the method to forecast seismic damage of mulfistory masonry buildings.
出处
《地震研究》
CSCD
北大核心
2008年第3期289-295,共7页
Journal of Seismological Research
基金
广东省自然科学基金(6021462)
广东省岩土工程重点学科基金资助
关键词
粗糙集
支持向量机
属性约简
震害预测
条件信息熵
rough set
support vector machine
attribute reduction
seismic damage prediction
conditional information entropy
