Traffic Missing Data Completion With Spatial-temporal Correlations

The missing data problem remains as a difficulty in transportation information system, which seriously restricted the application of intelligent transportation system, e,g. traffic control and traffic flow prediction. To solve this problem, numerous imputation methods had been proposed in the last decade. However, few existing studies had fully used the spatial correlation for traffic data imputation. In this paper, tensor based imputing method, which had been proven to be an effective imputation method, is applied to multi-detector missing data imputation for freeway corridor by constructing the traffic data into a 4-way spatial tensor. The authors make three main contributions in this paper: (a) Various tensor patterns are explored to model the traffic data, and take the multi-detectors into account. (b) Various tensor completion methods are explored and evaluated for missing traffic data imputation. Experiments show HaLRTC is more robust for missing traffic data than TDI. (c) The coefficient of the number of loop detectors used for missing traffic volume and speed data imputation is studied. Experiment results show the number of locations related to the spatial-temporal correlation of traffic data.