分布式检测系统数据不相容情况下的融合方法

探讨基于粗糙集理论的分布式检测系统在数据不相容情况下的处理算法,包括上、下近似集和边界集的确定,然后根据下近似集和边界集确定出规则,删除冗余规则后得到融合中心的所有规则。文中通过实际数据说明具体处理过程,验证该算法正确性和有效性。

Fusion approach to inconsistent datum based on rough sets theory in a distributed measuring system

The inconsistent datum were disposed by the rough sets theory in the data fusion center of a distributed measuring system. The method includes three steps: the ascertainment of upper approximation, low approximation and boundary, the deduction of certain rules and possible rules from the low approximation and boundary, and the removing of the redundant rules, and the output rules were gotten. The certain rules removed are the rules with condition parts more specific than those of some other certain rules. The possible rules removed are the rules with condition parts more specific and plausibility measure equal to or smaller than those of some other possible rules and certain rules. The disposal process was described by factual datum, and the results illustrate the rationality and validity of the method.