基于斜率偏离的时间序列相似性搜索方法研究

Study of distance-measuring method and application for time series similarity search based on slope departure

针对数据挖掘领域中时间序列的相似性度量问题,提出了基于斜率偏离度量的浮动索引相似性搜索算法。在斜率偏离度量的基础上建立分箱标志,通过浮动索引方法有效实现高维多元时间序列的准确索引,用实际的飞行数据进行仿真验证获得好的效果,证明这种方法的有效性和可靠性。

Aiming at the measuring method of similarity search in time series, this paper proposed a similarity measuring method based on slope departure. To dispose the time series data with high dimension, used a similarity measuring method to caculate the slope departure based on curve-in bin solving the localization of slope distance measurement in SFFS. In fact, the physical concept of this method proved more clearly and nicely with real fight data. The maturity, validity and the continuity of slope departure was proved.