No abstract

This article addresses the problem of the accuracy of short-term traffic flow forecasting in the complex case of urban signalized arterial networks. A new, artificial intelligence (AI)-based approach is suggested for improving the accuracy of traffic predictions through suitably combining the forecasts derived from a set of individual predictors. This approach employs a fuzzy rulebased system (FRBS), which is augmented with an appropriate metaheuristic (direct search) technique to automate the tuning of the system parameters within an online adaptive rolling horizon framework. The proposed hybrid FRBS is used to nonlinearly combine traffic flow forecasts resulting from an online adaptive Kalman filter (KF) and an artificial neural network (ANN) model. The empirical results obtained from the model implementation into a real-world urban signalized arterial demonstrate the ability of the proposed approach to considerably overperform the given individual traffic predictors.

No abstract

Variations in traffic flow patterns can be very useful in helping intelligent transportation systems (ITS) provide drivers with useful and accurate route and travel-time information, in examining the potential benefits of flexible work hours, and in assessing the environmental effects of traffic congestion. Much of the work done toward examining temporal and spatial variations in traffic flow has concentrated on freeways, largely ignoring urban areas, where ITS strategies can have the most important effects. Addressed are the issues of temporal and spatial distributions and variations in real-time traffic flow by using data from 140 loop detectors from the greater Athens, Greece, urban area. The results indicate that the temporal distributions of traffic flows are nonnormal, and they vary by direction (toward, in, or away from the central business district) and time of day. This result has important implications in correctly calibrating the real-time simulation models used for volume and travel-time predictions. The results also indicate that traffic in Athens exhibits low seasonality, with lower traffic during the summer months, although traffic conditions are very similar for all weekdays but vary relative to the weekends and by time of day.

No abstract