异构数据库下不完全信息优化检测仿真研究

Simulation Research of Incomplete Information Optimization Detection in Heterogeneous Database

对异构数据库下不完全信息的优化检测,能够有效提高数据库中数据质量。对不完全数据的检测,需要求得不完全信息的多准则权系数和分类中心,计算不完全信息方案集属于各类别的隶属度。传统方法利用偏好函数和不完全信息的准则权系数,定义两个方案的偏好优序指数,但忽略了计算信息类别隶属度,导致检测精度偏低。提出基于模糊聚类的异构数据库下不完全信息优化检测方法,在考虑对不完全信息训练集分类的基础上,结合计算获得的不完全信息的多准则权系数信息等建立模糊聚类模型;然后计算求得不完全信息的多准则权系数和分类中心,计算异构数据库下不完全信息方案集属于各类别的隶属度,从而完成对不完全信息的优化检测。仿真结果表明,所提方法操作简单,能够在经济管理中帮助决策者及时作出相应决策。

An optimization detection method for incomplete information in heterogeneous database is proposed based on fuzzy clustering. Firstly, combined with muhiple criteria weight coefficient information of incomplete infor- mation, a fuzzy clustering model is built on basis of considering classification of incomplete information training set, and then multiple criteria weight coefficients and classification center of incomplete information are calculated. Final- ly, the membership degree under heterogeneous database is calculated, and solution set of incomplete information be- longing to different categories is obtained. Thus, the optimal detection of incomplete information is completed. Simu- lation result shows that the proposed method is simple to operate. It can help decision-makers to make appropriate decisions in economic management.