File(s) under permanent embargo
Empirical evaluation of deep learning-based travel time prediction
conference contribution
posted on 2023-05-23, 14:32 authored by Wang, M, Li, W, Kong, Y, Quan BaiQuan BaiTravel time prediction is critical in the urban traffic management system. Accurate travel time prediction can assist better city planning and reduce carbon footprints. In this paper, we conducted an empirical work on deep learning-based travel time prediction. The objective of this study is to compare the prediction performance of different machine learning methods. Meanwhile, through the comparison, a neural network module with high prediction accuracy can be offered for alleviating traffic congestion. In addition, to eliminate the influence of nonlinear external factors, a variety of extrinsic data with abrupt properties will be acquired in real time and become part of the research considerations.
History
Publication title
PKAW 2019 Conference ProceedingsEditors
K Ohara and Q BaiPagination
54-65ISSN
0302-9743Department/School
School of Information and Communication TechnologyPublisher
Springer NaturePlace of publication
SwitzerlandEvent title
2019 Pacific Rim Knowledge Acquisition Workshop (PKAW 2019)Event Venue
Cuvu, FijiDate of Event (Start Date)
2019-08-26Date of Event (End Date)
2019-08-27Rights statement
Copyright 2019 Springer Nature Switzerland AGRepository Status
- Restricted