Freeway traffic data prediction using neural networks

Author

Taylor, Cynthia ; Meldrum, D.

Author_Institution

Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

fYear

1995

fDate

30 Jul-2Aug 1995

Firstpage

225

Lastpage

230

Abstract

A multi-layer perceptron type of artificial neural network predicts congested freeway data while demonstrating robustness to faulty loop detector data. Test results on historical data from the I-5 freeway in Seattle, Washington demonstrate that a neural network can successfully predict volume and occupancy one minute in advance, as well as fill in the gaps for missing data with an appropriate prediction. The volume and occupancy predictions are used as inputs to a fuzzy logic ramp metering algorithm currently under testing

Keywords

fuzzy logic; multilayer perceptrons; road traffic; traffic control; I-5 freeway; Seattle; Washington; artificial neural network; congested freeway data prediction; faulty loop detector data robustness; freeway traffic data prediction; fuzzy logic ramp metering algorithm; multi-layer perceptron; neural networks; occupancy prediction; traffic volume; Artificial neural networks; Detectors; Fault detection; Fuzzy logic; Multilayer perceptrons; Neural networks; Robustness; Telecommunication traffic; Testing; Traffic control;

fLanguage

English

Publisher

ieee

Conference_Titel

Vehicle Navigation and Information Systems Conference, 1995. Proceedings. In conjunction with the Pacific Rim TransTech Conference. 6th International VNIS. 'A Ride into the Future'

Conference_Location

Seattle, WA

Print_ISBN

0-7803-2587-7

Type

conf

DOI

10.1109/VNIS.1995.518843

Filename

518843