摘要
在时间序列分段线性表示基础上,提出一种新的基于趋势转折点的时间序列模式表示方法。该方法在充分利用时间序列时变特征的基础上,可以有效地提取时间序列中的趋势及压缩原始数据。仿真实验证明,该方法具有高效、实现简便、效果直观的优点,对于油田测井领域的数据适应性良好。
Based on PLR (piecewise linear representation) of time series,a new representation method of time-series based on trend turning point is proposed.The method takes full advantage of time-varying characteristics of time-series,and can effectively extract the trend of the time series and compress the primary data.The simulation results show that the method is efficient,simple and intuitive,and the method has good adaptability to oil well logging data.
出处
《科学技术与工程》
2010年第13期3254-3257,共4页
Science Technology and Engineering
基金
中国博士后科学基金(20080440923)
黑龙江省自然科学基金(F2007-11)
黑龙江省教育厅科研课题(11521005)资助