A Study on the Method for Cleaning and Repairing the Probe Vehicle Data

• Published in: IEEE transactions on intelligent transportation systems Vol. 14; no. 1; pp. 419 - 427
• Main Authors: Zhang, Zhaosheng, Yang, Diange, Zhang, Tao, He, Qiaochu, Lian, Xiaomin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2013; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Automobile dealers; Cleaning; Correlation; Data cleaning; data repair; Maintenance engineering; Missing data; multithreshold control repair method (MTCRM); normalization transform; probe vehicle data; Probes; reconstruction of principal components; Repair; Roads; Rule based; Studies; Telematics; Traffic engineering; Traffic flow; Vectors; Vehicles
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2012.2217378

Probe vehicle data are being increasingly applied in urban dynamic traffic data collection. However, the mobility and scale limit of probe vehicles may lead to incomplete or inaccurate data and thus influence the measurement of the state of traffic. At present, probe vehicle data are usually repaired by linear interpolation or a historical average method, but the repair accuracy is relatively low. To address the given problems, the multi-threshold control repair method (MTCRM) was proposed to clean and repair the probe vehicle data. The MTCRM adopts threshold control and a rule based on the approximate normalization transform to clean abnormal traffic data and to fill in the missing data by a weighted average method and an exponential smoothing method. In this approach, we combine topological road network characteristics to fill in the missing data from data for neighboring road sections and repair noisy data by reconstructing the principal components. This paper mainly focuses on analyzing the component of the recurring pattern of probe vehicle data, which can provide guidelines for the subsequent traffic forecasts. The findings of data repair for different grades of road in Beijing, China, demonstrate that the mean repair error may meet the requirements of traffic-state measurement, demonstrating that MTCRM can effectively clean probe vehicle data.