Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/9164

Title: A non-Gaussian Kalman Filter with application to the estimation of vehicular speed
Authors: Li, Baibing
Keywords: Dynamic generalized linear model
Non-Gaussian Kalman filter
Reciprocal inverse Gaussian distribution
State space model
Issue Date: 2009
Publisher: © American Society for Quality
Citation: LI, B., 2009. A non-Gaussian Kalman Filter with application to the estimation of vehicular speed. Technometrics,51 (2), pp. 162-172
Abstract: Single Inductance Loop Detectors (ILDs) which provide online measurements of traffic volume and occupancy are widely used devices in road systems. Due to the nature of traffic flow, fast estimation and forecasting of vehicular speed using the data collected by an ILD are crucial to online road traffic management. In this paper statistical inference for vehicular speed is formulated as a dynamic generalized linear model with a reciprocal inverse Gaussian observational distribution. The formulation motivates us to extend the Gaussian Kalman filter to this non-Gaussian scenario. This results in a set of simple recursive formulae where the current estimate of the parameter of interest is updated as a weighted harmonic average of the previous estimate and the current observation. By applying the developed non-Gaussian Kalman filter to analyze traffic data collected by an ILD, we provide a competitive alternative to estimate vehicular speed at a minimum computational cost.
Description: This article is closed access, it was published in the journal Technometrics [© American Statistical Association]. The definitive version is available from: http://pubs.amstat.org/loi/tech
Version: Accepted for publication
DOI: 10.1198/TECH.2009.0017
URI: https://dspace.lboro.ac.uk/2134/9164
Publisher Link: http://pubs.amstat.org/loi/tech
ISSN: 0040-1706
Appears in Collections:Closed Access (Business School)

Files associated with this item:

File Description SizeFormat
20308.pdf514.42 kBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.