语义减法聚类研究

计算机工程与科学

语义减法聚类研究

马慧1,赵捧未1,王婷婷2

(1.西安电子科技大学经济与管理学院,陕西西安 710126;
2.鲁东大学信息与电气工程学院,山东烟台 264000）

收稿日期:2015-05-25 修回日期:2015-09-30 出版日期:2016-09-25 发布日期:2016-09-25

A semantic driven subtractive clustering method

MA Hui1，ZHAO Peng-wei1，WANG Ting-ting2

（1.School of Economics and Management,Xidian University,Xi’an 710071;
2.School of Information and Electrical Engineering,Ludong University,Yantai 264000,China）

Received:2015-05-25 Revised:2015-09-30 Online:2016-09-25 Published:2016-09-25

摘要/Abstract

摘要：

针对传统减法聚类算法需要人工输入参数τ1和τ2的不足，对算法进行改进。引入AFS理论，通过隶属度矩阵自动确定密度半径τ1、半自动确定权重参数τ2，提出了改进的语义减法聚类算法SDSCM，并在Iris和Wine数据集上将其与FCM、KMEANS算法进行比较实验。实验结果表明，SDSCM在评价指标语义强度期望上高于FCM、KMEANS 1%~5%。SDSCM的SPT指标低于FCM、KMEANS，算法的类间分离度有待提高。SDSCM较好地解决了传统减法聚类人工输入参数τ1和τ2带来的弊端，并给出了更贴近用户给定语义的聚类。

关键词: 减法聚类, AFS理论, 隶属度矩阵, 语义强度期望

Abstract:

Aiming at the unnecessary need of manual input of parametersτ1 andτ2, we propose a sementic driven subtractive clustering mehtod (SDSCM) to improve the traditional subtractive clustering algorithms by introducing the axiomatic fuzzy sets (AFS) thoery. The density radius τ1 is automatically determined and weight τ2 is semi-automatically determined based on the membership matrix. We compare the SDSCM with the FCM and the KMEANS on the Iris and Wine data sets. Experimental results show that the SDSCM is 1% to 5% higher than the FCM and the KMEANS in terms of evaluation index (semantic strength expectation), while the SPT is lower than the other two methods, where it still needs to be improved. The SDSCM can effectively solve the disadvantages caused by manual input of parameters τ1 and τ2, and find the clusters which are closer to the user semantics.

Key words: subtractive clustering, AFS, membership matrix, semantic strength expectation

马慧1,赵捧未1,王婷婷2. 语义减法聚类研究[J]. 计算机工程与科学.

MA Hui1，ZHAO Peng-wei1，WANG Ting-ting2. A semantic driven subtractive clustering method [J]. Computer Engineering & Science.

参考文献

［1］Sun Ji-gui， Liu Jie， Zhao Lian-yu. Clustering algorithms research ［J］.Journal of Software,2008，19（1）:48-61．(in Chinese)
［2］Han Jia-wei.Data mining concepts and techniques ［M］.Beijing: Higher Education Press,2006:363-369．
［3］Kim Dae-Won,Lee Ki-Young, Lee Doheon, et al.A kernel-based subtractive clustering method［J］.Pattern Recognition Letters, 2005,26(7):879-891．
［4］Pan Tian-hong, Xue Zhen-kuang, Li Shao-yuan. An online multi-model identification algorithm based on subtractive clustering ［J］.Acta Automatica Sinica,2009,35（2）:220-224．(in Chinese)
［5］Duan Qun-jie， Zhang Ming-jun. Design of motion planner based on subtractive clustering and adaptive fuzzy neural network ［J］.Acta Armamentarii，2007,28（12）:1533-1536．(in Chinese)
［6］Yuan Xu，Chen Zhi-kui，Zhao Liang，et al.An improved subtractive clustering algorithm based on Hadoop［J］.Microelectronics and Computer，2015,32（3）:151-155．(in Chinese)
［7］Sun Zhi-hai,Kong Wan-zeng.Density value approximation for subtractive clustering based on Nystrom method［J］.Journal of Image and Graphics，2013，18（7）:790-798．(in Chinese)
［8］Zhang Xun,Zhan Cheng-wei,Deng Hui-wen,et al.Approximate clustering via the quick subtractive clustering method［J］.Journal of Southwest China Normal University（Natural Science），2006,31（3）:126-129．(in Chinese)
［9］Yu Di，Li Yi-jie.Research on fuzzy clustering based on subtractive clustering and improved fuzzy C-means algorithm［J］.Microcomputer and Its Applications,2010，29（16）:14-20．(in Chinese)
［10］Bataineh K M， Naji M， Saqer M. A comparison study between various fuzzy clustering algorithms［J］.Jordan Journal of Mechanical and Industrial Engineering，2011，5（4）:335-343．
［11］Gu Lei, Wu Hui-zhong. A subtractive clustering method based on genetic algorithms［J］.PR & AI,2008，21（6）:758-762．(in Chinese)
［12］Sun Z H,Zhou W H,Li E T,et al.Study on subtractive clustering video moving object locating method with introduction of eigengap［C］∥Proc of the 9th International Conference on Fuzzy Systems and Knowledge Discovery，2012:626-629.
［13］Ren Yan. Fuzzy clustering approaches based on AFS fuzzy logic［D］.Dalian:Dalian Maritime University，2007．(in Chinese)
［14］Liu Xiao-dong, Pedrycz W. Axiomatic fuzzy set theory and its applications［M］∥Studies in Fuzziness and Soft Computing.Berlin:Springer Publishing Company,2009:111-166．
［15］Liu Xiao-dong,Wang Wei,Chai Tian-you.The fuzzy clustering analysis based on AFS theory［J］.IEEE Transactions on Systems,Man，and Cybernetics, part B: Cybernetics,2005,35（5）: 1013-1027．
［16］Zhang Xun,Tian Yan-shan. A method to detect the upper limit of the number of cluster based on subtractive clustering［J］.Journal of Guyuan Teachers College,2006,27（3）:42-44．(in Chinese)
［17］Xiao Chun-jing， Zhang Min. Research on fuzzy clustering based on subtractive clustering and fuzzy C-means［J］.Computer Engineering，2005，31(5):135-137．(in Chinese)
［18］UCI machine learning repository［ER/OL］.［2014-04-25］.http:∥archive.ics.uci.edu/ml/．(in Chinese)
［19］Li Long-bo,Li Ren-pu,Zhang Zhi-wang，et al.Optimized semantic conditioned fuzzy C-Means［J］.Computer Science，2013，40（10）:243-247.(in Chinese)
附中文参考文献：
［1］孙吉贵,刘杰,赵连宇.聚类算法研究［J］.软件学报,2008，19（1）:48-61．
［4］潘天红，薛振框，李少远.基于减法聚类的多模型在线辨识算法［J］.自动学报，2009,35（2）:220-224．
［5］段群杰,张铭钧.基于减法聚类和自适应模糊神经网络方法的运动规划器设计［J］.兵工学报,2007,28（12）:1533-1536．
［6］原旭,陈志奎，赵亮,等.一种基于Hadoop的改进减法聚类算法［J］.微电子学与计算机,2015,32（3）:151-155．
［7］孙志海,孔万增.基于Nystrom密度值逼近的减法聚类［J］.中国图像图形学报，2013，18（7）:790-798．
［8］张栒,湛成伟，邓辉文,等.一种快速减法聚类算法［J］.西南师范大学学报（自然科学版）,2006,31（3）:126-129．
［9］于迪，李义杰.基于减法聚类改进的模糊C-均值算法的模糊聚类研究［J］.微型机与应用,2010，29（16）:14-20．
［11］顾磊,吴慧中.一种基于遗传算法的减法聚类方法［J］.模式识别与人工智能,2008，21（6）:758-762．
［13］任艳.基于AFS模糊逻辑的聚类分析方法研究［D］.大连:大连海事大学,2007．
［16］张栒，田彦山.基于减法聚类的聚类上限确定方法［J］.固原师专学报,2006,27（3）:42-44．
［17］肖春景，张敏.基于减法聚类与模糊C-均值的模糊聚类研究［J］.计算机工程，2005，31(5):135-137．
［18］UCI机器学习知识库［ER/OL］.［2014-04-25］.http:∥archive.ics.uci.edu/ml/．
［19］李洪波，李仁璞，张志旺,等.一种优化的语义条件模糊聚类［J］.计算机科学，2013，40（10）:243-247．