期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 62, 期 -, 页码 284-292出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2016.06.032
关键词
Grey system theory-based models; GM(1,1); Grey Verhulst model; Fourier series; Traffic parameter prediction
类别
资金
- National Science Foundation [1238705]
- NSF [1436222]
- Direct For Education and Human Resources
- Division Of Human Resource Development [1436222] Funding Source: National Science Foundation
- Division Of Human Resource Development
- Direct For Education and Human Resources [1238705] Funding Source: National Science Foundation
Intelligent transportation systems applications require accurate and robust prediction of traffic parameters such as speed, travel time, and flow. However, traffic exhibits sudden shifts due to various factors such as weather, accidents, driving characteristics, and demand surges, which adversely affect the performance of the prediction models. This paper studies possible applications and accuracy levels of three Grey System theory models for short-term traffic speed and travel time predictions: first order single variable Grey model (GM(1,1)), GM(1,1) with Fourier error corrections (EFGM), and the Grey Verhulst model with Fourier error corrections (EFGVM). Grey models are tested on datasets from California and Virginia. They are compared to nonlinear time series models. Grey models are found to be simple, adaptive, able to deal better with abrupt parameter changes, and not requiring many data points for prediction updates. Based on the sample data used, Grey models consistently demonstrate lower prediction errors over all the time series improving the accuracy on average about 50% in Root Mean Squared Errors and Mean Absolute Percent Errors. (C) 2016 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据