经典粗糙集方法的优点在于能够通过不可区分关系来获取知识,但其不足之处在于不能够处理定性属性、定量属性以及准则属性同时出现的定序分类问题.为此,本文对经典粗糙集进行扩展并提出了一个新的决策分析方法,该方法采用“不可区分-相似-优势”关系来代替经典粗糙集中的不可区分关系以获取知识的粗糙近似,从而不但能够解决上述定序分类问题,而且还能处理决策表中可能存在的不一致现象.实例验证了该方法的有效性与优越性.%The classic rough set theory can solve problems by means of indiscernibility relation,but it is powerless to resolve the sequencing classification problems that contain qualitative attributes and quantitative attributes as well as criterias. In view of this situation, thelassic rough set theory is firstly extended,and then,a decision analysis method based on the extended rough set theory is proposed. This method replaces the indiscernibility relation in the original rough set theory by the "indiscernibility-simi-larity-dominance" relation and obtains rough approximation of knowledge. The effectiveness and superiority of the method are demonstrated by a real example.
展开▼
