摘要
置信优势关系粗糙集是处理不完备有序信息的重要模型,上、下近似集的计算是核心内容之一.在实际应用中,属性集通常会发生变化.根据属性集的增加或减少,首先讨论置信优势类及劣势类变化情况,随之给出上、下近似集增量式的变化规律,提出相应的近似集动态更新方法.通过Matlab在UCI数据集上的实验结果表明,与非增量式方法相比,所提出的置信优势关系粗糙集下的上、下近似集的增量式更新方法可行、高效.
Confidential dominance relation based rough set is a model of incomplete ordered information processing,computation of approximations of which is a core issue. In real-life applications, the attribute set is dynamically changed.According to the variation of the attribute set, confidential dominance and dominated class are firstly calculated. Then the principles of incremental updating approximations are discussed when some attributes are added or deleted. Furthermore,incremental approaches and algorithms in the confidential dominance relation based on rough set are proposed. Finally, the experiments on UCI datasets developed on Matlab are designed to evaluate the performance of the proposed incremental updating method and non-incremental updating method. The results show that the proposed algorithms are effective and feasible under the variation of the attribute set.
出处
《控制与决策》
EI
CSCD
北大核心
2016年第6期1027-1031,共5页
Control and Decision
基金
国家科技重大项目(2014ZX07104-006)
中国科学院百人计划项目(Y21Z110A10)
国家自然科学基金项目(61073146
61173184)
关键词
置信优势关系
增量更新
近似集
粗糙集
confidential dominance relation
incremental updating
approximations
rough sets
