时间序列相似性分析中滑动窗口宽度的确定

How to Get Effective Slide-window Size in Time Series Similarity Search

时间序列相似性查找作为一种非平凡问题,大多数有效的求解方法都涉及到对原数据维度的简约。在有效地保持原序列中信息量的前提下,尽可能降低计算复杂度是算法的关键所在。通过讨论滑动窗口在时间序列相似性降维算法中的实际应用情况,从中发现一种自适应确定滑动窗口宽度的新方法。通过对时序特征值分布函数挖掘,发现时间序列中的有效特征点,进而确定一组合适的滑动窗口宽度;最后根据序列的变化情况来决定最优的滑动窗口宽度,对原数据维度进行简约。

As a non-trivial problem, most promising solutions of similarity search in time series databases involve performing dimensionality reduction on the original data. The key to this question is how to effectively keep original time series information while reduc slide-window practical application in this area, ing and computational complexity at the best effort. It discusses the then concludes how to get an effective slide-window size in similarity of time series research. To find some useful eigenvalue in time series by mining the distributing values of original series, and deduce a collection of candidate slide-window size, find the optimal slide window size by adapting to the series eigenvalue variable motion movement.