正在加载图片...
第11卷第2期 智能系统学报 Vol.11 No.2 2016年4月 CAAI Transactions on Intelligent Systems Apr.2016 D0I:10.11992/is.201507013 网络出版地址:http://www.cnki.net/kcms/detail/23.1538.TP.20160315.1239.014.html 适合大规模数据集的增量式模糊聚类算法 李滔,王士同 (江南大学数字媒体学院,江苏无锡214122) 摘要:FCPM算法已被成功地应用到模糊系统建模上,但其在某一类的聚类中心已知的大规模数据上的聚类性能 较差。为了避免这个缺点,参照单程模糊c均值(SPFCM)聚类算法、在线模糊c均值(OFCM)聚类算法,提出了适合 大规模数据集的增量式模糊聚类算法(Incremental fuzz四y(c+p)-means clustering,IFCM(c+p))。通过在每个数据块 中使用FCPM算法进行聚类,把每个数据块的聚类中心及其附近的一些样本点加入到下一个数据块参与聚类,同时 添加平衡因子以提高算法聚类性能。同SPFCM、OFCM以及rseFCM算法相比,IFCM(c+p)对初始聚类中心不敏感。 实验表明在没有花费很多运行时间的情况下,IFCM(c+p)算法的聚类性能比SPFCM算法和rseFCM算法更具优势, 因此该算法更适合处理某一类聚类中心已知的大规模数据集。 关键词:增量式模糊聚类;FCPM;IFCM(c+p);平衡因子;大规模数据集 中图分类号:TP391.4文献标志码:A文章编号:1673-4785(2016)02-0188-12 中文引用格式:李滔,王士同.适合大规模数据集的增量式模糊聚类算法[J].智能系统学报,2016,11(2):188-199. 英文引用格式:LITao,WANG Shitong.Incremental fuzzy(c+tp-means clustering for large data[J】.CAAI transactions on intelli- gent systems,2016,11(2):188-199. Incremental fuzzy (c+p)-means clustering for large data LI Tao,WANG Shitong (School of Digital Media,Jiangnan University,Wuxi 214122,China) Abstract:FCPM has been demonstrated to be successful in fuzzy system modeling,however,it will be ineffective for large data clustering tasks where the cluster centers of one class are known.In order to circumvent this draw- back,referring to single-pass fuzzy c-means (SPFCM)clustering algorithm and online fuzzy c-means (OFCM) clustering algorithm,the incremental fuzzy clustering algorithm for large data called IFCM(c+p)is proposed in this paper.FCPM algorithm is used to cluster for each data block at first,and then the clustering centers of data block and some of the sample points being near them are joined into the next block to be clustered,meanwhile the bal- ance factor is given to enhance the clustering performance.In contrast to SPFCM,OFCM and rseFCM,IFCM(c+ p)is not sensitive to the initial cluster centers.The experiments indicate the proposed clustering algorithm IFCM(c +p)is competitive to the clustering algorithms SPFCM and rseFCM in the clustering performance without the loss of running time a lot,hence it is especially suitable for large data clustering tasks where the cluster centers of one class are known. Keywords:incremental fuzzy clustering;FCPM;IFCM(c+p);balance factor;large data 聚类就是将物理或抽象的对象按照自己的某些 属性聚集成类的过程,并尽可能使得类(或者簇)之 间对象的差异程度最大,而类内(或者簇内)的相似 收稿日期:2015-07-06.网络出版日期:2016-03-15 基金项目:国家自然科学基金项目(61272210). 程度达到最大。聚类过程没有先验知识指导,仅凭 通信作者:李滔.E-mail:chasingdreaml19@163.com. 对象间的相似程度作为类属划分的准则,是无监督第 11 卷第 2 期 智 能 系 统 学 报 Vol.11 №.2 2016 年 4 月 CAAI Transactions on Intelligent Systems Apr. 2016 DOI:10.11992 / tis.201507013 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20160315.1239.014.html 适合大规模数据集的增量式模糊聚类算法 李滔,王士同 (江南大学 数字媒体学院,江苏 无锡 214122) 摘 要:FCPM 算法已被成功地应用到模糊系统建模上,但其在某一类的聚类中心已知的大规模数据上的聚类性能 较差。 为了避免这个缺点,参照单程模糊 c 均值(SPFCM)聚类算法、在线模糊 c 均值(OFCM)聚类算法,提出了适合 大规模数据集的增量式模糊聚类算法(Incremental fuzzy (c+p)⁃means clustering ,IFCM( c+p))。 通过在每个数据块 中使用 FCPM 算法进行聚类,把每个数据块的聚类中心及其附近的一些样本点加入到下一个数据块参与聚类,同时 添加平衡因子以提高算法聚类性能。 同 SPFCM、OFCM 以及 rseFCM 算法相比,IFCM( c+p)对初始聚类中心不敏感。 实验表明在没有花费很多运行时间的情况下,IFCM(c+p)算法的聚类性能比 SPFCM 算法和 rseFCM 算法更具优势, 因此该算法更适合处理某一类聚类中心已知的大规模数据集。 关键词:增量式模糊聚类;FCPM;IFCM(c+p);平衡因子;大规模数据集 中图分类号: TP391.4 文献标志码:A 文章编号:1673⁃4785(2016)02⁃0188⁃12 中文引用格式:李滔,王士同. 适合大规模数据集的增量式模糊聚类算法[J]. 智能系统学报, 2016, 11(2): 188⁃199. 英文引用格式:LI Tao, WANG Shitong. Incremental fuzzy (c+p)⁃means clustering for large data[J]. CAAI transactions on intelli⁃ gent systems, 2016, 11(2): 188⁃199. Incremental fuzzy ( c+p) ⁃means clustering for large data LI Tao, WANG Shitong (School of Digital Media, Jiangnan University, Wuxi 214122, China) Abstract:FCPM has been demonstrated to be successful in fuzzy system modeling, however, it will be ineffective for large data clustering tasks where the cluster centers of one class are known. In order to circumvent this draw⁃ back, referring to single⁃pass fuzzy c⁃means ( SPFCM) clustering algorithm and online fuzzy c⁃means (OFCM) clustering algorithm, the incremental fuzzy clustering algorithm for large data called IFCM(c+p) is proposed in this paper. FCPM algorithm is used to cluster for each data block at first, and then the clustering centers of data block and some of the sample points being near them are joined into the next block to be clustered, meanwhile the bal⁃ ance factor is given to enhance the clustering performance. In contrast to SPFCM, OFCM and rseFCM, IFCM(c+ p) is not sensitive to the initial cluster centers. The experiments indicate the proposed clustering algorithm IFCM(c +p) is competitive to the clustering algorithms SPFCM and rseFCM in the clustering performance without the loss of running time a lot, hence it is especially suitable for large data clustering tasks where the cluster centers of one class are known. Keywords: incremental fuzzy clustering; FCPM; IFCM(c+p); balance factor; large data 收稿日期:2015⁃07⁃06. 网络出版日期:2016⁃03⁃15. 基金项目:国家自然科学基金项目(61272210). 通信作者:李滔. E⁃mail:chasingdream119@ 163.com. 聚类就是将物理或抽象的对象按照自己的某些 属性聚集成类的过程,并尽可能使得类(或者簇)之 间对象的差异程度最大,而类内(或者簇内)的相似 程度达到最大。 聚类过程没有先验知识指导,仅凭 对象间的相似程度作为类属划分的准则,是无监督
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有