期刊文献+

动态时间弯曲距离精确计算的Dijkstra方法

The Directed Graph Method for Dynamic Time Warping
下载PDF
导出
摘要 将动态时间弯曲距离(DTW)的差异矩阵一一对应于点阵,按DTW定义的行走规则对该点阵连线定向,使所对应点阵成为一个有向图,然后使用一个加权技巧对该有向图的边加权后得到一个加权有向图,于是把求DTW的精确计算问题等价地转化为求一个有向图起点到终点的最短路长,从而使图论中求两点间最短路径的方法如目前公认的经典Dijkstra算法均可用于求DTW,因此间接地找到了精确计算DTW的一个新方法. Map the difference matrix of dynamic time warping(DTW) to a corresponding point matrix,and connect those points according to the walking rout in the definition of DTW to obtain a directed graph.Then weight the edges by using some trick,a appropriate directed and weighted graph is given out.As a result,to find DTW is equally to find the shortest distance path,therefore all those algorithms that used to find shortest distance path such as Dijkstra's algorithm well known as the best one until now can be used to find DTW,which improves solving the problem of calculating DTW.
作者 李兴芳
机构地区 重庆财政学校
出处 《四川职业技术学院学报》 2011年第6期101-103,共3页 Journal of Sichuan Vocational and Technical College
关键词 动态时间弯曲距离(DTW) 有向加权图 最短路径 DIJKSTRA算法 时间序列 Dynamic Time Warping Directed Graph Shortest Path Dijkstra's Algorithm Time Series Data mining Cluster Analysis Euclidean Distance.
  • 相关文献

参考文献11

  • 1Rabiner, L. &Juang, B.. Fundamentals of speechrecognition [M]. EnglewoodCliffs, N. J, PrenticeHall. 1993.
  • 2Sakoe, H. &Chiba, S. Dynamic programming algorithm optimization for spoken word recognition [C]. IEEE Trans. Acoustics, Speech, and Signal Processing. 1978, Volume 26, pp143- 165.
  • 3Berndt, D. & Clifford. J. Using dynamic time warping to find patterns in time series[C]. AAAI-94 Work shop on Knowledge Discovery in Databases, pages 229-248. Seattle, Washington, 1994.
  • 4Keogh, E. & Pazzani, M. Scaling up Dynamic Time Warping for Datamining Applications [C]. Proceedings of the 6th International Conference onKnowledge Discovery andDataMining, pp. 285-289. 2000, Boston, USA.
  • 5D. Rafiei and A. Mendelzon. "Similarity-based Queries for TimeSeriesData" [C]. Proc. ACMSIGMOD, Tucson, AZ, 1997.
  • 6C.F.B. Yi, H.V. Jagadish. Efficient retrieval of similar sequences undertimewarping[C]. IEEEICDE, pages201 - 208, 1998.
  • 7Xiao Hui,Feng Xiaofei, Hu Yunfu. A New Segmented Time Warping Distance for Data Mining in Time Series Database [C]. Proceedings of the Third Intecnational Conference on Machine Learning and Cybernetics, Shanghai, 26-29August 2004.
  • 8Chu, S., E. Keogh, D. Hart & Michael Pazzani. Iterative Deepening Dynamic Time Warping for Time Series[C]. In Proc. of the Second SIAM Intl. Conf. on Data Mining. Arlington, Virginia, 2002.
  • 9Teddy Siu Fung Wong, Man Hon Wong. Efficient Subsequence Matching for Sequences Databases under Time Warping [C].Proceedings of the Seventh International Database Engineering and Applications Symposium (IDEAS'03). 2003 IEEE.
  • 10钱颂迪.运筹学(修订版)[M].北京:清华大学出版社,2003.

共引文献2

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