一种不确定多变量决策树生成算法

imed at the problem of the inability for multivariate decision tree algorithm to effectively deal with noisy data, the paper extends the relative core of attributes in rough sets theory to variable precision rough set(VPRS), and uses it for selection of attributes in multivariate tests. Under the condition of majority inclusion relation the paper extends the concept of generalization of one equivalence relation with respect to another one, and uses it for construction of multivariate tests. Finally, we propose an algorithm for multivariate decision tree that can avoid disturbance of noisy data.