全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

时间序列的符号化方法研究

, PP. 154-161

Keywords: 符号化,有限统计复杂性,动态法

Full-Text   Cite this paper   Add to My Lib

Abstract:

符号化是一种重要的时间序列分析方法,但是如何选择合适的符号化策略却是一个难题.有限统计复杂性表达符号序列中包含的信息量,它可以作为符号化处理的评价标准.本文首先分析现有的符号化方法,如:静态法、动态法、小波空间法等.然后选用8组时间序列为例,用不同符号化方法处理它们,计算并比较符号序列的有限统计复杂性.因为8组时间序列分别来自不同领域,且都是非线性和非平稳的,因此分析结果会导出一些有意义的经验结论.综合评价认为:动态法是符号化方法的首选,其次是综合法和小波空间法,最常用的静态法效果反而最差.

References

[1]  Crutchfield J P, Young K. Inferring Statistical Complexity. Physical Review Letters, 1989, 63(2): 105108
[2]  Perry N, Binder P M. Finite Statistical Complexity for Sofic Systems. Physical Review E, 1999, 60(1): 459463
[3]  Hyndman R J. Time Series Data Library [DB/OL]. [20060406]. http://wwwpersonal.buseco.monash.edu.au/~hyndman/TSDL
[4]  Weigend A. The Santa Fe Time Series Competition Data [DB/OL]. [20060406]. http://wwwpsych.stanford.edu/~andreas/TimeSeries/SantaFe.html
[5]  Andrzejak G, Lehnertz K, Rieke C, et al. EEG Time Series Download Page [DB/OL]. [20060406]. http://www.meb.unibonn.de/epileptologie/science/physik/eegdata.html
[6]  Daw C S, Finney C E A, Tracy E R. A Review of Symbolic Analysis of Experimental Data. Review of Scientific Instruments, 2003, 74(2): 915930
[7]  Kurths J, Schwarz U, Witt A,et al. Measures of Complexity in Signal Analysis // Proc of the AIP Conference on Chaotic, Fractal, and Nonlinear Signal Processing. Woodbury, USA, 1996: 3354
[8]  Shi Hong, Shen Yi, Liu Zhiyan, et al. Research on Main Issues in Rough Sets and Its Application. Computer Engineering, 2003, 29(3): 13 (in Chinese) (石 红, 沈 毅, 刘志言,等.关于粗糙集理论及应用问题的研究.计算机工程, 2003, 29(3): 13)
[9]  Tang X Z, Tracy E R, Boozer A D, et al. Symbol Sequence Statistics in Noisy Chaotic Signal Reconstruction. Physical Review E, 1995, 51(5): 38713889
[10]  Shalizi C R, Crutchfield J P. Computational Mechanics: Pattern and Prediction, Structure and Simplicity. Journal of Statistical Physics, 2001, 104(3/4): 817879
[11]  Lin J, Keogh E, Loncell S, et al. A Symbolic Representation of Time Series, with Implications for Streaming Algorithms // Proc of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery. San Diego, USA, 2003: 211
[12]  Ray A. Symbolic Dynamic Analysis of Complex Systems for Anomaly Detection. Signal Processing, 2004, 84(7): 11151130
[13]  Chin S C. Real Time Anomaly Detection in Complex Dynamic Systems. Ph.D Dissertation. Park, USA: The Pennsylvania State University. Depatment of Electrical Engineering, 2004
[14]  Crutchfield J P. The Calculi of Emergence: Computation, Dynamics and Induction. Physica D, 1994, 75(1/2/3): 1154

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133