01155564

Component

https://doi.org/10.3141/2165-08

http://scholar.google.com...Chen&publication_year=2010

The accurate modeling and forecasting of traffic flow data such as volume and travel time are critical to intelligent transportation systems. Many forecasting models have been developed for this purpose since the 1970s. Recently kernel-based machine learning methods such as support vector machines (SVMs) have gained special attention in traffic flow modeling and other time series analyses because of their outstanding generalization capability and superior nonlinear approximation. In this study, a novel kernel-based machine learning method, the Gaussian processes (GPs) model, was proposed to perform short-term traffic flow forecasting. This GP model was evaluated and compared with SVMs and autoregressive integrated moving average (ARIMA) models based on four sets of traffic volume data collected from three interstate highways in Seattle, Washington. The comparative results showed that the GP and SVM models consistently outperformed the ARIMA model. This study also showed that because the GP model is formulated in a full Bayesian framework, it can allow for explicit probabilistic interpretation of forecasting outputs. This capacity gives the GP an advantage over SVMs to model and forecast traffic flow.

01220491

10-0752

English

pp 69-78

2010

Transportation Research Record: Journal of the Transportation Research Board

9780309142977

Print

Figures (8) ; References (27) ; Tables (3)

Interstate highways; Traffic flow; Traffic forecasting; Traffic models; Traffic volume

Autoregressive integrated moving average models; Bayesian approach; Gaussian processes; Support vector machines

Seattle (Washington)

Data and Information Technology; Highways; Planning and Forecasting; I71: Traffic Theory

TRIS, TRB, ATRI

Jan 25 2010 10:21AM

• Combined Effect of Traffic and Geometrics on Rear-End Collision Risk: Driving Simulator Study
• Empirical Investigation of Continuous Logit for Departure Time Choice with Bayesian Methods
• Examination of Methods to Estimate Crash Counts by Collision Type
• Getis–Ord Spatial Statistics to Identify Hot Spots by Using Incident Management Data
• Integration of Traffic Simulation into Design Visualization: Case Study
• Investigating Regression to the Mean in Before-and-After Speed Data Analysis
• Leverage of Spiral Graph for Transportation System Data Visualization
• Modeling Injury Severity of Multiple Occupants of Vehicles: Copula-Based Multivariate Approach
• Multiple Applications of Multivariate Adaptive Regression Splines Technique to Predict Rear-End Crashes at Unsignalized Intersections
• Spatial Correlation in Multilevel Crash Frequency Models: Effects of Different Neighboring Structures