Short-term travel time estimation and prediction for long freeway corridor using NN and regression

Travel time information is a fundamental component in Advanced Traveler Information System. In this paper, we propose a short-term travel time estimation and prediction framework for long freeway corridor, considering measurements from vehicle detectors (VD) and floating car data (FCD). The modeling approach is based on a modified Nearest-Neighborhood (NN) model with threshold and a regression model capturing the within day variations. The advantages are that our approach allows for missing data without the need of data imputation in real-time, and is suitable for travel time prediction of long corridors. The validation analysis using an 88 km long section of freeway shows satisfactory results.