期刊文献+

一种基于元启发式策略的迭代自学习K-Means算法 被引量:2

Metaheuristic Strategy Based K-Means with the Iterative Self-Learning Framework
下载PDF
导出
摘要 类内误差平方和最小化的聚类准则求解是NP难问题,K-Means采用的迭代重定位方法本质上是一种局部搜索的爬山算法,因此聚类结果对初始代表点的选择非常敏感,只能保证局部最优。为此,引入元启发式策略,通过建立评估函数对K-Means初始代表点和目标函数之间的依赖关系进行近似,然后利用近似评估函数指导新的初始代表点的选择,构成一种迭代自学习框架下的K-Means算法。实验表明算法可以很好地克服K-Means对初始代表点的依赖性,获得较高质量的聚类结果。 The clustering problems based on minimizing the sum of intra-cluster squared-error are known to be NP- hard. The iterative re-locating method using by K-Means is essentially a kind of local hill-climbing algorithm, which will find a locally minimal solution eventually and cause much sensitivity to initial representatives. The meta-heuristic strategy was introduced to minimize the squared-error criterion globally. Firstly, an evaluation function was built to approxi- mate the dependency between a series of initial representatives of K-Means and the local minimal of objective criterion, and then the selection of initial representatives was done under the supervision of the evaluation function for the next K- Means. This iterative and self-learning process is called Meta-KMeans algorithm. The experimental demonstrations show that Meta-KMeans can overcome the sensitivity to initial representatives of K-Means to a great extent.
出处 《计算机科学》 CSCD 北大核心 2009年第7期175-178,共4页 Computer Science
基金 中国矿业大学科技基金(OD080313) 国家863高技术研究发展计划(2006AA12Z217)资助
关键词 聚类问题K-Means算法 元启发式策略 迭代自学习框架 K-Means algorithm, Metaheuristic, Iterative self-learning framework
  • 相关文献

参考文献7

  • 1Sebastiani F.A tutorial on automatic text categorization[].Procof the st ArgentineanSymposium on Artificial Intelligence.1999
  • 2Boyan J A,,Moore A W.Learning Evaluation Functions forGlobal Optimization and Boolean Satisfiability[].Procof the thNational Conference onArtificial Intelligence.1998
  • 3Han J,Kamber M.Data mining:concepts and techniques[]..2001
  • 4Kirkpatrick S,Gelatt CD Jr,Vecchi MP.Optimization by simulated annealing[].Science.1983
  • 5Glover,F.Tabu search: part I[].ORSA Journal on Computing.1989
  • 6Glover F.Tabu search: part Ⅱ[].ORSA Journal on Computing.1990
  • 7Dorigo M,Blum C.Ant colony optimization theory: A survey[].Theoretical Computer Science.2005

同被引文献25

  • 1易纲.中国金融资产结构分析及政策含义[J].经济研究,1996,31(12):26-33. 被引量:278
  • 2HANJia-wei,Micheline Kanber著.数据挖掘概念与技术[M].北京:机械工业出版社,2007
  • 3CORMEN T H. , LEISERSON C E, RONSLD L. 算法导论[M].北京:机械工业出版社,2006:1-8.
  • 4HAN Jia-wei, KAMBER M. Data mining: concepts and techniques [ M ]. San Francisco : Morgan Kaufmann Publishers,2011 : 223- 250.
  • 5SHI Na, LIU Xu-min. Research on K-means clustering algorithm:an improved K-means clustering algorithm [ C]//Pmc of the 3rd Interna- tional Symposium on Intelligent Information Technology and Security Informatics. 2010 : 1-3.
  • 6LIU Hong. Internet public opinion hotspot detection and analysis based on K-means and SVM algorithm [ C ]//Proc of International Conference on Information Science and Management Engineering. 2010:257-261.
  • 7MOSHE S, HERTZ D. On computing DFT of real N-point vector and IDFT of DFT-transformed real N-point vector via single DFT [ J ]. IEEE Signal Processing Letters, 1999,6 (6) : 141.
  • 8Wang J,Su X.An improved K-Means clustering algorithm[C]// Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on. IEEE, 2011: 44-46.
  • 9Guha S,Rastogi R,Shim K.CURE: an efficient clustering alg- orithm for large databases[C]//ACM SIGMOD Record. ACM, 1998, 27(2): 73-84.
  • 10Trikha P,Vijendra S. Fast density based clustering algorithm [J].International Journal of Machine Learning and Computing, 2013, 3(1): 10-12.

引证文献2

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部