Dissimilarity measures for time trajectories
Dissimilarity measures for time trajectories
复制标题
DOI：
10.1007/bf03178958
复制
发表时间：
2000
影响因子：
1
通讯作者：
P. D’Urso
中科院分区：
文献类型：
--
作者：
P. D’Urso
本文通过考虑时间序列在对象空间(单元空间)中的一种可能的几何表示，分析了单元的多变量时间轨迹之间的不同差异度量，这些单元按照不同的方法被系统地分类，并考虑到它们的特点。特别地，我们定义了三类相异度：‘几何’类，其中根据轨迹的几何特征(瞬时位置、时间段(速度)的斜率、每对时间段(加速度)、多边形线(形状)、每对轨迹之间的面积部分)的凹凸性来建立相异度；“结构”类，包含考虑轨迹的结构方面的不同，例如线性或多项式趋势以及每个单变量分量的季节性。文中还进行了实证比较。
In this paper, by considering one of the possible geometric representations of time arrays in the ‘object space’ (space of the units), we analyze different dissimilarity measures between multivariate time trajectories of the units, which are classified, systematically, in various approaches, by taking into account their features. In particular, we define three classes of dissimilarities: the ‘geometric’ class, in which dissimilarities are built according to the geometrical features of the trajectories (instantaneous position, slope of the inter-temporal segments (velocity), concavity and convexity of each pair of inter-temporal segments (acceleration), polygonal line (shape), portion of area between each pair of trajectories); the ‘correlative’ class, in which dissimilarity measures that analyze the autocorrelation and cross-correlation functions of the univariate components of each multivariate trajectory are classified; the ‘structural’ class, containing dissimilarities which consider the structural aspects of the trajectories, such as the linear or polynomial trends and the seasonality of each univariate component. An empirical comparison is also included.