Detecting long-range correlations of traffic time series with multifractal detrended fluctuation analysis
Detecting long-range correlations of traffic time series with multifractal detrended fluctuation analysis
复制标题
DOI：
10.1016/j.chaos.2006.06.019
复制
发表时间：
2008-04-01
影响因子：
7.8
通讯作者：
Kamae, Santi
中科院分区：
文献类型：
--
作者：
Shang, Pengjian;Lu, Yongbo;Kamae, Santi
交通时间序列中的多重分形行为通常与小波动和大波动的不同长程（时间）相关性或（和）时间序列值的宽概率密度函数有关。采用多触消趋势波动分析方法（MFDFA）研究交通流速度波动。研究表明，北京玉泉营高速公路上40个月左右的车速时间序列存在一个交叉时间尺度s（x），其中信号在时间尺度s > s（x）和s < s（x）上具有不同的相关指数。最后，通过比较原始序列的MFDFA结果与通过MFDFA获得的混洗序列的结果，验证了长程相关性是占主导地位的。(C)2006爱思唯尔有限公司版权所有。
Multifractal behavior in traffic time series usually connected with different long-range (time-) correlations of the small and large fluctuations or (and) a broad probability density function for the values of the time series. Multiftactal detrended fluctuation analysis (MFDFA) is used to study the traffic speed fluctuations. It is demonstrated that the speed time series, observed on the Beijing Yuquanying highway over a period of about 40 months, has a crossover time scale s(x), where the signal has different correlation exponents in time scales s > s(x) and s < s(x). Finally, the long-range correlation was validated to be dominant by the method of comparing the MFDFA results for original series to those obtained via the MFDFA for shuffled series. (C) 2006 Elsevier Ltd. All rights reserved.