一种基于关键点的时间序列线性表示方法

Linear Representation Method Based on Key Points for Time Series

时间序列数据具有规模大、维度高等特点,直接在原始序列上进行数据挖掘,其计算复杂度高且易受噪声影响,因此对原始时间序列进行预处理是必不可少的,而常用的线性表示方法大多存在对分段点的筛选准确度不高的问题。基于时间序列的变化特征,提出了一种基于时间序列关键点的线性表示方法。该方法综合考虑了时间跨度和振幅变化,能高效提取时间序列中的关键点,并防止过度除噪,实现简单。实验表明,该方法对不同领域的数据具有良好的普适性。

Time series data has the features of large scale and high latitude.It has high computational complexity and is susceptible to noise if doing data mining on the raw sequence directly,so the original time series pretreatment is essential,and most methods of commonly used linear representation have low accuracy in selection piecewise points.Based on the time series variation,we proposed a linear representation method based on key points for time series.The method takes into account the time span and amplitude changes and can efficiently extract key points in the time series,which can prevent excessive noise removal and is implemened simply.Experiments show that the method has good universality for data from different areas.