基于二进制区分矩阵的不完备系统增量式属性约简算法

Incremental Attribute Reduction Algorithm Based on Binary Discernibility Matrix in Incomplete Information System

不完备信息系统下的增量式属性约简是动态数据挖掘技术的重要研究内容之一。求解增量式属性约简时首先需要求解容差类。当已有系统新增实例时,为了快速求解新的容差类,首先提出一种快速且稳定性较好的容差类静态求解方法,然后在此基础上提出容差类的增量式求解方法。根据增量式求得的新容差类,结合二进制区分矩阵直观及便于处理的优点,通过动态更新二进制区分矩阵方法,提出了不完备信息系统下基于二进制区分矩阵的增量式属性约简算法。通过实例及仿真实验验证了算法的有效性。

Incremental attribute reduction algorithm in incomplete information system is one of the important research contents in the area of data mining.For getting the attribute reduction incrementally,the tolerance class needs to be computed.For the purpose of speeding up the tolerance class calculation,an improved static algorithm with rapidity and stability is developed firstly,followed by a novel incremental algorithm,which can update the tolerance class rapidly when a new object is coming.On the basis of the obtained tolerance class and combined with the intuitive and easy of binary matrix,an incremental attribute reduction algorithm based on binary matrix in incomplete information system by updating the binary matrix was proposed.The validity of these algorithms was demonstrated by the simulation and experimental results.