Traffic speed prediction with neural networks

Çakmak, Umut Can and Apaydın, Serkan Mehmet and Çatay, Bülent (2018) Traffic speed prediction with neural networks. In: Annual International Conference of the German Operations Research Society (GOR), Berlin, Germany

[thumbnail of 2018_OR_Traffic_Speed_Prediction_with_Neural_Networks.pdf] PDF
2018_OR_Traffic_Speed_Prediction_with_Neural_Networks.pdf
Restricted to Repository staff only

Download (364kB) | Request a copy

Abstract

With the increasing interest in creating Smart Cities, traffic speed prediction has attracted more attention in contemporary transportation research. Neural networks have been utilized in many studies to address this problem; yet, they have mainly focused on the short-term prediction while longer forecast horizons are needed for more reliable mobility and route planning. In this work we tackle the medium-term prediction as well as the short-term. We employ feedforward neural networks that combine time series forecasting techniques where the predicted speed values are fed into the network. We train our networks and select the hyper-parameters to minimize the mean absolute error. To test the performance of our method, we consider two multi-segment routes in Istanbul. The speed data are collected from floating cars for every minute over a 5-month horizon. Our computational results showed that accurate predictions can be achieved in medium-term horizon.
Item Type: Papers in Conference Proceedings
Subjects: T Technology > T Technology (General)
Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Industrial Engineering
Faculty of Engineering and Natural Sciences
Faculty of Engineering and Natural Sciences > Academic programs > Manufacturing Systems Eng.
Depositing User: Bülent Çatay
Date Deposited: 01 Aug 2018 10:26
Last Modified: 26 Apr 2022 09:29
URI: https://research.sabanciuniv.edu/id/eprint/34866

Actions (login required)

View Item
View Item