In recent years,attribute reduction based on Bayesian decision cost minimization has attracted the attention of many scholars in the three-way decisions interval-valued systems.However,in the construction of loss function,few studies consider the influence of the difference between the compatible equivalence classes on the reduction result.To solve this problem,a attribute reduction method of decision cost minimization based on distance measure is proposed.By measuring the distance between decision class and compatible class,a comprehensive loss function is established to describe the difference information between objects.Then,according to the Bayesian decision rules and the pre-given initial cost function,the calculation method of adaptive threshold pairs is constructed.An attribute reduction algorithm for minimizing decision cost in interval-valued decision making systems is established.Finally,an example is given,and the results show that the proposed reduction algorithm can obtain the reduction result with less decision cost,and is more rational in theory.
维普
万方数据