Estimation of Missing Data in Intelligent Transportation System
This work provides a significant improvement in the accuracy of traffic data estimation for transportation authorities and planners, enabling more reliable ITS applications.
This paper addresses missing traffic speed and travel time data in Intelligent Transportation Systems (ITS) caused by sensor and communication errors. The authors applied a Multi-Directional Recurrent Neural Network (M-RNN) and found it reduced Root Mean Square Error (RMSE) by up to 58% compared to existing methods like spline interpolation and matrix completion on a TomTom dataset from the Greater Toronto Area.
Missing data is a challenge in many applications, including intelligent transportation systems (ITS). In this paper, we study traffic speed and travel time estimations in ITS, where portions of the collected data are missing due to sensor instability and communication errors at collection points. These practical issues can be remediated by missing data analysis, which are mainly categorized as either statistical or machine learning(ML)-based approaches. Statistical methods require the prior probability distribution of the data which is unknown in our application. Therefore, we focus on an ML-based approach, Multi-Directional Recurrent Neural Network (M-RNN). M-RNN utilizes both temporal and spatial characteristics of the data. We evaluate the effectiveness of this approach on a TomTom dataset containing spatio-temporal measurements of average vehicle speed and travel time in the Greater Toronto Area (GTA). We evaluate the method under various conditions, where the results demonstrate that M-RNN outperforms existing solutions,e.g., spline interpolation and matrix completion, by up to 58% decreases in Root Mean Square Error (RMSE).