带正则化项的时间序列聚类算法及其应用
|
摘要
为了更加准确地对时间序列数据进行聚类分析,运用了带正则化项的时间序列聚类方法,并实现了该聚类方法的算法.将该方法应用于云南地区水准形变数据的实际研究中,以寻找类之间状态转移与地震的关系.数值结果同时表明了带正则化项的时间序列聚类方法比标准的K-means方法更有效,更有优势.
In order to have a better clustering result of the time series data,a new time series clustering method with regularization is introduced.Applying this method into studying the horizontal deformation data of Yunnan province,the relationship between the transition of the states and the eruption of the earthquakes could be figured out.The numerical results show that,comparing with the standard K-means method,this approach manifests its efficiency.
In order to have a better clustering result of the time series data,a new time series clustering method with regularization is introduced.Applying this method into studying the horizontal deformation data of Yunnan province,the relationship between the transition of the states and the eruption of the earthquakes could be figured out.The numerical results show that,comparing with the standard K-means method,this approach manifests its efficiency.
引文
[1]Bezdek J C.Pattern recognition with fuzzy objective function algorithms[M].New York:PlenumPress,1981.
[2]Bezdek J C,Hathaway R H,Sabin M J,et al.Convergence theory for fuzzy C-means:Counterexamplesand repairs[J].IEEE Trans,1987,17:873-877.
[3]Hpner F,Klawonn F,Kruse R,et al.Fuzzy cluster analysis[M].New York:Wiley Press,1999.
[4]Hathaway R H,Bezdek J C.Switching regression models and fuzzy clustering[J].IEEE Transactions onFuzzy Systems,1993,1(3):195-204.
[5]Horenko I.On clustering of non-stationary meteorological time series[J].Dynamics of Atmosphere andOceans,2010,49(2-3):164-187.
[6]Horenko I.On simultaneous data-based dimension reduction and hidden phase identification[J].Journalof the Atmospheric Sciences,2008,6:1941-1954.
[7]Engl H W,Hanke M,Neubauer A.Regularization of inverse problems[M].Dordrecht:Kluwer,1996.
[8]Tikhonov A.On the stability of inverse problems[J].Dokl Akad Nauk SSSR,1943,39(5):195-198.
[9]苏有锦,李忠华,刘祖荫,等.20世纪云南地区Ms≥5.0级地震活动的基本特征[J].地震研究,2001,21(1):1-9.
[10]张四新,江在森,王双绪.南北地震带及青藏块体东部垂直形变与地震活动研究[J].西北地震学报,2003,25(2):143-148.
[11]郭良迁,马青,杜雪松,等.华北地区断层形变与地震的关系[J].大地测量与地球动力学,2008,28(3):14-20.
[12]吴宗敏.散乱数据拟合的模型、方法和理论[M].北京:科学出版社,2007.
[13]Loader C.Local regressions and likelihood[M].New York:Springer,1999.
[2]Bezdek J C,Hathaway R H,Sabin M J,et al.Convergence theory for fuzzy C-means:Counterexamplesand repairs[J].IEEE Trans,1987,17:873-877.
[3]Hpner F,Klawonn F,Kruse R,et al.Fuzzy cluster analysis[M].New York:Wiley Press,1999.
[4]Hathaway R H,Bezdek J C.Switching regression models and fuzzy clustering[J].IEEE Transactions onFuzzy Systems,1993,1(3):195-204.
[5]Horenko I.On clustering of non-stationary meteorological time series[J].Dynamics of Atmosphere andOceans,2010,49(2-3):164-187.
[6]Horenko I.On simultaneous data-based dimension reduction and hidden phase identification[J].Journalof the Atmospheric Sciences,2008,6:1941-1954.
[7]Engl H W,Hanke M,Neubauer A.Regularization of inverse problems[M].Dordrecht:Kluwer,1996.
[8]Tikhonov A.On the stability of inverse problems[J].Dokl Akad Nauk SSSR,1943,39(5):195-198.
[9]苏有锦,李忠华,刘祖荫,等.20世纪云南地区Ms≥5.0级地震活动的基本特征[J].地震研究,2001,21(1):1-9.
[10]张四新,江在森,王双绪.南北地震带及青藏块体东部垂直形变与地震活动研究[J].西北地震学报,2003,25(2):143-148.
[11]郭良迁,马青,杜雪松,等.华北地区断层形变与地震的关系[J].大地测量与地球动力学,2008,28(3):14-20.
[12]吴宗敏.散乱数据拟合的模型、方法和理论[M].北京:科学出版社,2007.
[13]Loader C.Local regressions and likelihood[M].New York:Springer,1999.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心