Degree Type
Dissertation
Date of Award
2018
Degree Name
Doctor of Philosophy
Department
Civil, Construction, and Environmental Engineering
Major
Civil Engineering
First Advisor
Anuj Sharma
Second Advisor
Soumik Sarkar
Abstract
The objective of the proposed study is to predict traffic speeds at a route level so that the traffic management has a chance to operate proactively. A distributed file system and parallel computing platform is used to store the big data sets of state-wide traffic and weather data in a fault-tolerant way and process the big data in a timely manner. Traffic speed prediction problem is studies at two levels and two deep networks are proposed accordingly: a fully convolutional deep network for long-term speed prediction and a hybrid LSTM network for short-term speed prediction. The fully convolutional deep network utilizes both weather information and historical traffic speeds to make long-term traffic speed prediction and a trained model can be transferred to predict traffic speed at any spatial-temporal scale. The hybrid LSTM network utilizes the previous traffic speeds on the current day as well as historical traffic speeds to make short-term speed prediction and a trained model can be used to predict speeds at any timestamps ahead in a streaming fashion. The proposed long-term and short-term traffic speed prediction models can be combined as a multi-layer decision supporting system to provide traffic management an opportunity to operate proactively.
Copyright Owner
Shuo Wang
Copyright Date
2018-05
Language
en
File Format
application/pdf
File Size
108 pages
Recommended Citation
Wang, Shuo, "Traffic speed prediction using big data enabled deep learning" (2018). Graduate Theses and Dissertations. 16753.
https://lib.dr.iastate.edu/etd/16753