基于时空相关性的交通流故障数据修复方法

发布时间：2018-10-13 11:23

【摘要】：为及时对高速公路交通流故障数据进行有效修复,综合考虑交通流数据的时空特性,提出基于3D形函数的时空插值修复方法.以时间间隔、距离和时滞参数作为相关数据的提取依据,以高速公路实际数据对所提出方法进行验证;将实验结果与采用时间序列法、空间插值法、基于灰色残差GM模型以及基于统计相关分析的方法得到的结果进行对比.结果表明,该方法的修复结果优于时间序列法和空间插值法,并且修复误差低于其他方法.其中,与基于灰色残差GM模型和基于统计相关分析的方法相比,该方法的修复结果的均绝对误差分别降低了21.33%和43.54%,均方根误差分别降低了12.87%和35.08%.该方法的修复结果的平均绝对值误差率比基于统计相关分析的方法降低了40%.这表明研究中所提方法的修复精度更高,是一种有效的数据修复方法.
[Abstract]:In order to repair the freeway traffic flow fault data in time, considering the space-time characteristics of the traffic flow data, a 3D shape function based spatio-temporal interpolation method is proposed. Taking the time interval, distance and time delay parameters as the basis for extracting the relevant data, the proposed method is verified by the actual data of the highway, and the experimental results are compared with the time series method, the spatial interpolation method, the time series method and the spatial interpolation method. The results based on grey residual GM model and statistical correlation analysis are compared. The results show that the proposed method is superior to the time series method and the spatial interpolation method, and the repair error is lower than that of other methods. Compared with the method based on grey residual GM model and statistical correlation analysis, the mean absolute error and root mean square error of the proposed method are reduced by 21.33% and 43.54%, respectively, and the root mean square error by 12.87% and 35.08%, respectively. The average absolute error rate of this method is 40% lower than that based on statistical correlation analysis. This indicates that the proposed method is more accurate and is an effective data restoration method.
【作者单位】：吉林大学交通学院;吉林大学吉林省道路交通重点实验室;山东省交通规划设计院;
【基金】：国家科技支撑计划资助项目(2014BAG03B03) 国家留学基金资助项目
【分类号】：U491

【相似文献】