01475390

Component

https://doi.org/10.3141/2334-09

http://scholar.google.com...ftis&publication_year=2013

Univariate and multivariate neural network (NN) and autoregressive time series models are compared with regard to application to the short-term forecasting of freeway speeds. Statistical tests are used to evaluate the developed models with respect to temporal data resolution, prediction accuracy, and quality of fit. The results indicate that, by and large, NNs provide more accurate predictions than do classical statistical approaches, particularly for finer data resolutions. Evaluation of model fit indicated that, in contrast to vector autoregressive models, NNs may also provide unbiased predictions. Overall, the findings clearly suggest the need to jointly consider statistical and NN models to develop more efficient prediction models.

01517323

13-1367

English

pp 9–22

2013

Transportation Research Record: Journal of the Transportation Research Board

9780309294843

Print

Figures (10) ; References (49) ; Tables (5)

Choice models; Drivers; Learning; Personality; Psychological aspects; Route choice; Travel behavior

Highways; Planning and Forecasting; I72: Traffic and Transport Planning

TRIS, TRB, ATRI

Feb 5 2013 12:21PM

• ASSIST-ME: Postprocessing Tool for Transportation Planning Model Output
• Data Density Requirements as Functions of Design Speed: Controlling Accuracy of Representation of Horizontal and Vertical Curves in Surface Models for Automated Machine Guidance
• Feasibility and Advantages of Estimating Local Road Vehicle Miles Traveled on Basis of Global Positioning System Travel Data
• Handling Uncertainty in Transit Project Evaluation and Rating Process: Comparison Between the Existing FTA Approach and a Fuzzy Inference Approach
• Large-Scale Agent-Based Transport Simulation in Shanghai, China
• Prediction of Individual Travel Mode with Evidential Neural Network Model
• Spatial Approach for Assessing Energy-Related Impacts on Transportation Systems
• Spatiotemporal Data Warehouse for Vehicle Supervision: Grid Time–Indexed Cube Approach
• Stochastic Network Design Problem with Fuzzy Goals
• Systems Thinking for Knowledge Transfer in Organic and Mechanistic Organizations: State Government Transportation Research Organizations
• Translating Transportation Data Between Linear Referencing Systems of Dissimilar Resolution