期刊文献+

基于ACF非线性趋势特征的时间序列聚类 被引量:1

Cluster Time-Series Based on the Non-Linear Trend Character of ACF
下载PDF
导出
摘要 在时间序列挖掘工作中,比如聚类和分类,需要计算距离来衡量时间序列样本之间的相似性,有许多研究都致力于时间序列相似性度量的研究.充分利用非线性趋势特征来进行时间序列挖掘.首先计算时间序列的ACF,进而构造ACF的非线性趋势特征,利用该特征作为时间序列相似性度量来进行聚类,它给时间序列平稳性的判定提供了一种新的途径.列举了一个模拟数据和一个实际数据来进行实例验证,实验结果表明,ACF非线性趋势特征作为一种新的相似性度量,相对已有的一些相似性度量而言,ACF非线性趋势特征通常只需计算少量的若干特征值就能更合理地刻画时间序列的平稳性特征.借助K-means进行聚类实验.
出处 《计算机研究与发展》 EI CSCD 北大核心 2007年第z2期111-116,共6页 Journal of Computer Research and Development
基金 国家"九八五"工程二期基金项目(0000-X07204)
  • 相关文献

参考文献11

  • 1陈佐,谢赤,陈晖.基于小波聚类方法的股票收益率序列时间模式挖掘[J].系统工程,2005,23(11):102-107. 被引量:5
  • 2汤胤.时间序列相似性分析方法研究[J].计算机工程与应用,2006,42(1):68-71. 被引量:17
  • 3周明磊.非参数估计与小波分析在股市趋势线中的应用[J].数理统计与管理,2005,24(4):70-75. 被引量:3
  • 4[4]E Keogh,S Kasetty.On the need for time series data mining benchmarks:A survey and empirical demonstration.The 8th ACM SIGKDD Int'lConf on Knowledge Discovery and Data Mining,Edmonton,Alberta,Canada,2002
  • 5[5]D Piccolo.A distance measure for classifying ARIMA models.Journal of Time Series Analysis,1999,11:152-164
  • 6[6]C Jorge,C Nuno,P Daniel.A periodogram-based metric for time series classification.Computational Statistics & Data Analysis,2006,50(10):2668-2684
  • 7[7]P Galeano,D Pe.Multivariate analysis in vector time series.Journal of the Institute of Mathematics and Statistics of the University of Sao Paolo,Resenhas,2000,4:383-404
  • 8[8]W S Cleveland.The inverse autocorrelations of a time series and their applications.Technometrics,1972,14(2):277-293
  • 9[9]C Chatfield.Inverse autocorrelations.Journal of Royal Statistical Society,A,1979,142:363-377
  • 10[10]M Gavrilov,D Anguelov,P Indyk,et al.Mining the stock market:Which measure is best? The 6th ACM Int'lConf on KDD,Boston,2000

二级参考文献46

  • 1N Crato,B K Ray.Model selection and forecasting for long-range dependent processes[J].Journal of Forecasting, 1996 ; ( 15 ) : 107-125.
  • 2Christos Faloutsos,M Ranganathan,Yannis Manolopoulos.Fast Subsequence Matching in Time-Series Database[C].In:Proceedings 1994;ACM SIGMOD Conference,Minneapolis,1994.
  • 3Davtmd Rafiei ,Alberto O Mendelson. Querying Time Series Data Based on Similarity[C].In:IEEE TRANS ON KNOWLEDGE AND DATA ENG,2000- 12(5 ).
  • 4Chang-Shing Perng,Hai-un Wang,Sylvia R Zhang et al.Landmarks- A New Model for Similarity-Based Pattern Querying in Time Series Databases[C].In: 16th International Conference on Data Engineering ICDE'2000,2000 - 33 -42.
  • 5Ge,Smyth.Deformable Markov model templates for time-series pattern matching[J].KDD,2000 : 81-90.
  • 6Altrock yon Constantin.Fuzzy Logic and Neuro Fuzzy Applications Explained[M].Prentice Hall, Englewood Cliffs, 1995.
  • 7Tsoukalas H Leftefi,Uhrig E Robert.Fuzzy and Neural Approaches in Engineering[M].New York :John Wiley, 1997.
  • 8Zadeh A Lotfi,Fu King-Sun,Tanaka Kokichi et al.Fuzzy Sets and their Applications to Cognitive and Decision Processes[M].New York: Academic Press, 1975.
  • 9Antonin Guttman.R-Trees:A Dynamic Index Structure for Spatial Searching[C].In:SIGMOD Conference, 1984:47-57.
  • 10Eamonn J Keogh,Michael J Pazzani.Scaling up Dynamic Time Warping for Datamining Applications.Knowledge Discovery and Data Mining,in ACM, 2000 : 1 -58.

共引文献22

同被引文献5

  • 1Jorge C, Nuno C, Daniel P. A periodograrn - based metric for time series classification[ R]. Computational Statistics &Data Analysis 50,2006:2668 - 2684.
  • 2Galeano, P, Pe, D, Multivariate analysis in vector time series[J]. Resenhas 4,2000:383 - 404.
  • 3Cleveland,WS. The inverse autocorrelations of a time series and their applications [ J ]. Technometrics 14,1972 : 277 - 293.
  • 4Chatfield, C. Inverse autocorrelations[J]. J. Roy. Statist. Soc. Ser. A 142, 1979:363 - 377.
  • 5Guan HS, Jiang QS, Hong ZL, A New Metric for Classification of Multivariate Time Series[ Z]. The 4th International Conference on Fuzzy Systems and Knowledge Discovery, Hainan, China,2007:453-457.

引证文献1

二级引证文献4

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