01658946

Component

Despite the constant innovations of modern traffic counting devices, missing data is still a major concern for most of continuous traffic monitoring programs. In this work, it is proposed an algorithm for imputation of missing data obtained from continuous traffic counting devices using Gaussian Processes techniques for Machine Learning applied to time-series data. The authors present some applications of the method for the treatment of data from the Brazilian National Traffic Counting Plan (PNCT), under the responsibility of the Brazilian National Department of Transport Infrastructure (DNIT). The tests show that the PNCT data reconstructions obtained with the algorithm proposed in this work are robust and accurate. The method is flexible enough to consistently model widely varying traffic patterns, without loss of interpretability. Another important characteristic of the proposed method is the ability of generating confidence intervals for every imputed data. In the end of the work, the authors also discuss some possible future extensions for predicting traffic volumes, and to learn joint traffic patterns for different sensors.

This paper was sponsored by TRB committee ABJ70 Standing Committee on Artificial Intelligence and Advanced Computing Applications.

18-04912

English

15p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

Figures; References; Tables

Algorithms; Information processing; Machine learning; Time series; Traffic counts; Traffic volume

Brazil

Data and Information Technology; Highways; Planning and Forecasting

Transportation Research Board Annual Meeting 2018 Paper #18-04912

TRIS, TRB, ATRI

Jan 8 2018 11:13AM