一种新的半监督熵模糊聚类算法
|
摘要
结合熵值和半监督模糊聚类两种概念,提出了半监督熵模糊聚类算法.该算法在目标函数中加入了反映划分矩阵的熵值项和已标记数据标签的监督项,使得聚类算法可以同时兼顾划分矩阵的模糊性和已知样本的类别信息.其迭代求解公式具有较为简洁的形式.将聚类方法应用于文本识别及其他真实数据库,实验结果表明,文章提出的半监督聚类算法和传统的聚类算法相比具有更好的聚类效果.
Combining the concepts of entropy and semi-supervised fuzzy clustering,a semi-supervised entropy fuzzy clustering algorithm is proposed in this paper.This algorithm adds the entropic term and the supervisory term in its objective function to reflect partition entropy and labeled data information so that the clustering algorithm can take into account both the ambiguity of partition matrix and the class information of labeled samples.Its iterative solution formula has a concise form.This clustering method is applied to text recognition and other real databases.The experimental results show that the semi-supervised clustering algorithm proposed in this paper has better clustering effect than the traditional clustering algorithms.
Combining the concepts of entropy and semi-supervised fuzzy clustering,a semi-supervised entropy fuzzy clustering algorithm is proposed in this paper.This algorithm adds the entropic term and the supervisory term in its objective function to reflect partition entropy and labeled data information so that the clustering algorithm can take into account both the ambiguity of partition matrix and the class information of labeled samples.Its iterative solution formula has a concise form.This clustering method is applied to text recognition and other real databases.The experimental results show that the semi-supervised clustering algorithm proposed in this paper has better clustering effect than the traditional clustering algorithms.
引文
[1] 杨昔阳,李志伟.半监督模糊Fisher降维分析[J].厦门大学学报(自然科学版),2015,54(6):869-875.
[2] 潘永平,黄道平,孙宗海.II型模糊控制综述[J].控制理论与应用,2011,28(1):13-23.
[3] 杨昔阳,周玉玲,李志伟.一种基于二型模糊集的模糊k-平面聚类算法[J].福建师范大学学报(自然科学版),2018,34(6):17-23.
[4] MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]// Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability,1967,1(14):281-297.
[5] BEZDEK J C.Pattern recognition with fuzzy objective function algorithms[M].Norwell:Kluwer Academic Publishers,1981.
[6] YANG Y,CHEN L.Semi-supervised fuzzy co-clustering algorithm for document categorization[J].Knowledge & Information Systems,2013,34(1):55-74.
[7] YAN R,ZHANG J,YANG J A.Hauptmann,a discriminative learning framework with pairwise constraints for video object classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):578-593.
[8] GAO C,WU X.A new semi-supervised clustering algorithm with pairwise constraints by competitive agglomeration[J].Applied Soft Computing,2011(11):5281-5291.
[9] PEDRYCZ W,AMATO A,LECCE V D,et al.Fuzzy clustering with partial supervision in organization and classification of digital images[J].IEEE Transactions on Fuzzy Systems,2008,16 (4):1008-1026.
[10] LI R P,MUKAIDONO M.A maximum-entropy approach to fuzzy clustering[C]//Proc of the 4th IEEE Int Conf on Fuzzy System.Piscataway,NJ:IEEE,1995:2227-2232.
[11] 陈晓,李亚安,蔚婧.基于最大熵模糊聚类的快速多目标跟踪算法研究[J].西北工业大学学报,2017(4):629-634.
[12] PAL N R,BEZDEK J C.On cluster validity for the fuzzy C-means model [J].IEEE Trans on Fuzzy Systems,1995,3(3):370-379.
[13] 张俊峰,景伟娜.基于L1度量的Type-2熵模糊聚类红外图像分割[J].微电子学与计算机,2010,27(1):49-52.
[14] 杨昔阳,李志伟.半监督模糊聚类及其应用[J].福建师范大学学报(自然科学版),2015(2):11-16.
[2] 潘永平,黄道平,孙宗海.II型模糊控制综述[J].控制理论与应用,2011,28(1):13-23.
[3] 杨昔阳,周玉玲,李志伟.一种基于二型模糊集的模糊k-平面聚类算法[J].福建师范大学学报(自然科学版),2018,34(6):17-23.
[4] MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]// Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability,1967,1(14):281-297.
[5] BEZDEK J C.Pattern recognition with fuzzy objective function algorithms[M].Norwell:Kluwer Academic Publishers,1981.
[6] YANG Y,CHEN L.Semi-supervised fuzzy co-clustering algorithm for document categorization[J].Knowledge & Information Systems,2013,34(1):55-74.
[7] YAN R,ZHANG J,YANG J A.Hauptmann,a discriminative learning framework with pairwise constraints for video object classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):578-593.
[8] GAO C,WU X.A new semi-supervised clustering algorithm with pairwise constraints by competitive agglomeration[J].Applied Soft Computing,2011(11):5281-5291.
[9] PEDRYCZ W,AMATO A,LECCE V D,et al.Fuzzy clustering with partial supervision in organization and classification of digital images[J].IEEE Transactions on Fuzzy Systems,2008,16 (4):1008-1026.
[10] LI R P,MUKAIDONO M.A maximum-entropy approach to fuzzy clustering[C]//Proc of the 4th IEEE Int Conf on Fuzzy System.Piscataway,NJ:IEEE,1995:2227-2232.
[11] 陈晓,李亚安,蔚婧.基于最大熵模糊聚类的快速多目标跟踪算法研究[J].西北工业大学学报,2017(4):629-634.
[12] PAL N R,BEZDEK J C.On cluster validity for the fuzzy C-means model [J].IEEE Trans on Fuzzy Systems,1995,3(3):370-379.
[13] 张俊峰,景伟娜.基于L1度量的Type-2熵模糊聚类红外图像分割[J].微电子学与计算机,2010,27(1):49-52.
[14] 杨昔阳,李志伟.半监督模糊聚类及其应用[J].福建师范大学学报(自然科学版),2015(2):11-16.