Fuzzy modeling approach for combined forecasting of urban traffic flow

Stathopoulos, A; Dimitriou, L; Tsekeris, T

dc.contributor.author	Stathopoulos, A	en
dc.contributor.author	Dimitriou, L	en
dc.contributor.author	Tsekeris, T	en
dc.date.accessioned	2014-03-01T01:28:29Z
dc.date.available	2014-03-01T01:28:29Z
dc.date.issued	2008	en
dc.identifier.issn	1093-9687	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/18855
dc.subject	Combining Forecast	en
dc.subject	Fuzzy Model	en
dc.subject	Traffic Flow	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Construction & Building Technology	en
dc.subject.classification	Engineering, Civil	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Backpropagation	en
dc.subject.other	Chlorine compounds	en
dc.subject.other	Control theory	en
dc.subject.other	Heuristic programming	en
dc.subject.other	Neural networks	en
dc.subject.other	Traffic control	en
dc.subject.other	Traffic surveys	en
dc.subject.other	Adaptive Kalman filtering	en
dc.subject.other	Arterial networks	en
dc.subject.other	Artificial neural network models	en
dc.subject.other	Combined forecasting	en
dc.subject.other	Direct search	en
dc.subject.other	Empirical results	en
dc.subject.other	Fuzzy modeling	en
dc.subject.other	Fuzzy rule-based systems	en
dc.subject.other	Individual traffic	en
dc.subject.other	Meta heuristic	en
dc.subject.other	Model implementation	en
dc.subject.other	Real-world	en
dc.subject.other	Rolling horizons	en
dc.subject.other	Short-term traffic flow forecasting	en
dc.subject.other	System parameters	en
dc.subject.other	Traffic flowing	en
dc.subject.other	Urban traffic	en
dc.subject.other	Forecasting	en
dc.subject.other	artificial neural network	en
dc.subject.other	forecasting method	en
dc.subject.other	fuzzy mathematics	en
dc.subject.other	Kalman filter	en
dc.subject.other	knowledge based system	en
dc.subject.other	modeling	en
dc.subject.other	traffic management	en
dc.subject.other	urban transport	en
dc.title	Fuzzy modeling approach for combined forecasting of urban traffic flow	en
heal.type	journalArticle	en
heal.identifier.primary	10.1111/j.1467-8667.2008.00558.x	en
heal.identifier.secondary	http://dx.doi.org/10.1111/j.1467-8667.2008.00558.x	en
heal.language	English	en
heal.publicationDate	2008	en
heal.abstract	This article addresses the problem of the accuracy of short-term traffic flow forecasting in the complex case of urban signalized arterial networks. A new, artificial intelligence (AI)-based approach is suggested for improving the accuracy of traffic predictions through suitably combining the forecasts derived from a set of individual predictors. This approach employs a fuzzy rule-based system (FRBS), which is augmented with an appropriate metaheuristic (direct search) technique to automate the tuning of the system parameters within an online adaptive rolling horizon framework. The proposed hybrid FRBS is used to nonlinearly combine traffic flow forecasts resulting from an online adaptive Kalman filter (KF) and an artificial neural network (ANN) model. The empirical results obtained from the model implementation into a real-world urban signalized arterial demonstrate the ability of the proposed approach to considerably overperform the given individual traffic predictors. © 2008 Computer-Aided Civil and Infrastructure Engineering.	en
heal.publisher	BLACKWELL PUBLISHING	en
heal.journalName	Computer-Aided Civil and Infrastructure Engineering	en
dc.identifier.doi	10.1111/j.1467-8667.2008.00558.x	en
dc.identifier.isi	ISI:000258597400004	en
dc.identifier.volume	23	en
dc.identifier.issue	7	en
dc.identifier.spage	521	en
dc.identifier.epage	535	en