CAJ | 학술논문

提出基于模糊c均值聚类算法的两个新算法.设置每个数据隶属度的误差阈值,规定每个数据的隶属度误差不能超过给出的误差阈值.使用该类算法可以对有误差的数据进行模糊聚类.先利用隶属度矩阵的误差范围建立新的拉格朗日函数,再使用Kuhn-Tucker条件计算该函数,并通过一组实验来证明这类算法的正确性和有效性.
제출기우모호c균치취류산법적량개신산법.설치매개수거대속도적오차역치,규정매개수거적대속도오차불능초과급출적오차역치.사용해류산법가이대유오차적수거진행모호취류.선이용대속도구진적오차범위건립신적랍격랑일함수,재사용Kuhn-Tucker조건계산해함수,병통과일조실험래증명저류산법적정학성화유효성.
Two new clustering algorithms are proposed for the data with some errors.Set membership of each data error threshold,attached to each data error should not exceed the error threshold is given.These algorithms are based on the entropy regularized fuzzy cmeans.First,the tolerance which means the permissible range of the error is introduced into optimization problems which relate with clustering,and the tolerance is the upper bound of partition matrix.Next,the problems are solved using Kulm-Tucker conditions.Last,the algorithms are constructed based on the results of solving the problem.The correctness and effectiveness of algorithms is proved.