An efficient non-linear Kalman filtering algorithm using simultaneous perturbation and applications in traffic estimation and prediction

Antoniou, C; Koutsopoulos, HN; Yannis, G

dc.contributor.author	Antoniou, C	en
dc.contributor.author	Koutsopoulos, HN	en
dc.contributor.author	Yannis, G	en
dc.date.accessioned	2014-03-01T02:44:25Z
dc.date.available	2014-03-01T02:44:25Z
dc.date.issued	2007	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31824
dc.subject	Dynamic Model	en
dc.subject	extended kalman filter	en
dc.subject	Finite Difference	en
dc.subject	Simultaneous Perturbation	en
dc.subject	kalman filter	en
dc.subject.other	Empirical results	en
dc.subject.other	Finite difference	en
dc.subject.other	Gradient approximation	en
dc.subject.other	Intelligent transportation systems	en
dc.subject.other	Kalman Filtering algorithms	en
dc.subject.other	Non-linear	en
dc.subject.other	Numerical derivatives	en
dc.subject.other	On-line calibrations	en
dc.subject.other	Simultaneous perturbation	en
dc.subject.other	Traffic dynamics	en
dc.subject.other	Traffic estimation	en
dc.subject.other	Approximation theory	en
dc.subject.other	Cellular radio systems	en
dc.subject.other	Control theory	en
dc.subject.other	Finite difference method	en
dc.subject.other	Gradient methods	en
dc.subject.other	Intelligent vehicle highway systems	en
dc.subject.other	Kalman filters	en
dc.subject.other	Numerical analysis	en
dc.subject.other	Perturbation techniques	en
dc.subject.other	Polynomial approximation	en
dc.subject.other	Vehicle locating systems	en
dc.subject.other	Wave filters	en
dc.subject.other	Intelligent systems	en
dc.title	An efficient non-linear Kalman filtering algorithm using simultaneous perturbation and applications in traffic estimation and prediction	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ITSC.2007.4357813	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ITSC.2007.4357813	en
heal.identifier.secondary	4357813	en
heal.publicationDate	2007	en
heal.abstract	The Extended Kalman Filter, a well-established and straightforward extension of the Kalman filter, requires a computationally intensive linearization step. In this paper, the use of the simultaneous perturbation is proposed for the computation of the gradient in a far more efficient way than the usual numerical derivatives. The resulting algorithm is applied to the problem of on-line calibration of traffic dynamics models and empirical results are presented. The use of the simultaneous perturbation gradient approximation provides significant improvement over the base case, and comparable results to those obtained by the more computationally intensive finite difference gradient approximation. © 2007 IEEE.	en
heal.journalName	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC	en
dc.identifier.doi	10.1109/ITSC.2007.4357813	en
dc.identifier.spage	217	en
dc.identifier.epage	222	en