一种基于粗糙K均值的多靶点中心优化方法  

A multi-target center optimization approach based on rough K-means algorithm

作　　者：吴宏杰[1,2,3] 吕强[2,3] 叶红霞[4] 胡伏原[1] 付保川[1] 钱培德[2,3] 

机构地区：[1]苏州科技学院电子与信息工程学院,江苏苏州215011 [2]苏州大学计算机科学与技术学院,江苏苏州215006 [3]江苏省计算机信息处理技术重点实验室,江苏苏州215006 [4]苏州高等职业技术学校,江苏苏州215009

出　　处：《苏州科技学院学报（工程技术版）》2012年第3期76-80,共5页Journal of Suzhou University of Science and Technology （Engineering and Technology）

基　　金：住房与城乡建设部科技项目(2009-K5-10);苏州科技学院科研基金(2008Z1327)

摘　　要：结合粗糙集理论与K均值算法,提出一种粗糙K均值多靶点中心优化方法,通过噪声去除、多靶点区域识别、靶点中心计算三个步骤获取多个靶点中心的最优坐标。最后,在仿真桥梁上进行检验,结果显示其精度为74.5%,相关系数为0.290,说明该方法具有一定的准确性与鲁棒性。The center coordinates of the multi-target optimization approach is the key to improving the accuracy of the digital measurement system and intelligent image system. Combining the rough set theory and the K-means algorithm, this paper proposed a multi-target optimization approach with the rough set theory. The optimized co- ordinate with a multi-target center was obtained by the noise removal, muhi-target region recognition and the target center calculation. Finally, we validated the method＇s performance on a simulation bridge. The results showed that the accuracy was 74.5%, the correlated coefficient was 0.290, indicating that this method satisfacto- rily met the requirement of accuracy and robustness.

关 键 词：粗糙K均值 多靶点 靶点中心 桥梁监测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]