一种增量更新算法在数据挖掘中的应用  

Application of an incremental updating algorithm in data mining

作　　者：曾小宁[1] 肖水晶[2] 

机构地区：[1]广东教育学院数学系,广东广州510303 [2]南昌大学理学院,江西南昌330031

出　　处：《计算机应用》2007年第6期1403-1406,1410,共5页journal of Computer Applications

基　　金：广东省自然科学基金资助项目(06023728)

摘　　要：引入扩展差别矩阵和扩展决策矩阵,提出了新的属性约简算法和增量更新算法,即基于扩展差别矩阵的属性约简算法和基于扩展决策矩阵的增量式规则提取算法,讨论了规则的增量更新算法。由于使用了增量更新算法和并行处理技术,从而提高了数据挖掘的效率,降低了时间复杂度。通过实验说明此算法是有效和可行的。The extended discernibility matrices and extended decision matrices have been introduced, new attribute reduction algorithm and incremental updating algorithm （namely, attribute reduction algorithm based on extended discernibility matrix and incremental rule acquisition algorithm based on extended decision matrix） have been presented, and incremental updating algorithm of rules has been discussed and researched. Incremental updating algorithm and parallel processing technology were used to raise the efficiency of data mining and reduce the time complexity. Our experimental results show that the algorithm is feasible and effective.

关 键 词：数据挖掘 粗糙集 增量更新算法 扩展差别矩阵 扩展决策矩阵 数据约简 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]