【作者】 令狐大智； 李陶深； 武新丽；

【Author】 Linghu Dazhi~(1,2),Li Taoshen~1,and Wu Xinli~3 1(School of Computer and Electronic Information,Guangxi University,Nanning 530004) 2(Department of Computer and Information Management,Guangxi Finance and Dconomics College,Nanning 530003) 3(Xingjian College of Arts and Science,Guangxi University,Nanning 530005)

【机构】 广西大学计算机与电子信息学院； 广西财经学院计算机与信息管理系； 广西大学行健文理学院；

【摘要】 依据物理学理论中的刚体最稳态结构,将数据集合看做物理实体,提出虚拟数字实体化观点和代表数据五元组、典型约束等概念,并在此基础上建立4点中心-边界算法(EFCBA)和基于相互约束的模糊数据归类算法(MRFCA).实验表明EFCBA算法提高了代表数据的集合代表性,缓解了图形不规则性对集合代表数据获取的影响;MRFCA算法有效利用了代表数据的特点,提高了归类准确率,并具有较好的自适应能力和未知新型数据归类能力.更多还原

【Abstract】 On the basis of most steady state structure of rigid bodies in physical theory,data set is regarded as physical object,and a dummy digital substantialization viewpoint and some conceptions such as representative data five element groups and model restraint.Then,the algorithm of elasticity based four-point center and borderline(EFCBA) and the algorithm based on mutual constraint fuzzy data classification(MRFCA) are presented.The experimental results show the EFCBA algorithm can enhance data representation and alleviate the graph irregularity’s influence;the MRFCA algorithm can utilize effectively the characteristic of representation data,enhance the classification rate of accuracy, and has good adaptive ability and unknown data classification ability.更多还原