计算机科学 ›› 2017, Vol. 44 ›› Issue (1): 247-252.doi: 10.11896/j.issn.1002-137X.2017.01.046
张建辉,王会青,孙宏伟,郭芷榕,白莹莹
ZHANG Jian-hui, WANG Hui-qing, SUN Hong-wei, GUO Zhi-rong and BAI Ying-ying
摘要: 时序降维是解决时间序列高维问题的关键技术。符号聚集近似表示(SAX表示法)作为一种时序降维技术,具有良好的维度约简能力与性能稳定的下界距离算法,但算法中分段数的选取需根据当前时序数据的特征而人为设定。针对这一问题,引入了滑动窗口算法与统计学方法,提出了基于二分迭代SAX的时序相似性度量算法。实验结果表明,该算法不仅解决了分段数设定困难的问题,而且降低了时序降维表示的复杂度,提高了SAX算法在多种时序数据上的分类准确性。
[1] LI Hai-lin,Yang Li-bin.Method of dimensionality reduction and feature representation for time series [J].Contorl and Decision,2013 (11):1718-1722.(in Chinese) 李海林,杨丽彬.时间序列数据降维和特征表示方法[J].控制与决策,2013 (11):1718-1722. [2] DAW C S,FINNEY C E A,TRACY E R.A review of symbolic analysis of experimental data[J].Review of Scientific Instruments,2003,74(2):915-930. [4] LIN J,KEOGH E,WEI L,et al.Experiencing SAX:a novelsymbolic representation of time series[J].Data Mining & Knowledge Discovery,2007,15(2):107-144. [5] SHIEH J,KEOGH E.i SAX:indexing and mining Terabytesized time series[C]∥Proceedings of the14th ACM SIGKDD international Conference on Knowledge Discovery and Data Mi-ning.ACM,2008:623-631. [6] CAMERRA A,PALPANAS T,SHIEH J,et al.iSAX 2.0:Indexing and Mining One Billion Time Series[C]∥2013 IEEE 13th International Conference on Data Mining.IEEE,2010:58-67. [8] LKHAGVA B,SUZUKI Y,KAWAGOE K.Extended SAX:Ex-tension of symbolic aggregate approximation for financialtime series data representation[C]∥DEWS 2006.2006. [9] HE X,SHAO C,XIONG Y.A non-parametric symbolic approximate representation for long time series[J].Formal Pattern Analysis & Applications,2016,19(1):111-127. [10] SUN Y,LI J,LIU J,et al.An improvement of symbolic aggregate approximation distance measure for time series[J].Neurocomputing,2014,8(11):189-198. [11] FUAD M M M,MARTEAU P F.Towards a faster symbolic aggregate approximation method[C]∥ICSOFT 2010.2010. [13] BARNAGHI P,GANZ F,HENSON C,et al.Computing perception from sensor data[C]∥Sensors,2012 IEEE.IEEE,2012:1-4. [15] BURANASING A,PRAYOTE A.Storm intensity estimation using symbolic aggregate approximation and artificial neural network[C]∥International Computer Science and Engineering Conference.2014. [16] KEOGH E,ZHU Q,HU B,et al.Ratanamahatana,The UCR time seriesclassification/clustering homepage.http://www.cs.ucr.edu/~eamonn/timeseries_data/. |
No related articles found! |
|