TRAFFIC SPEED PREDICTION USING PROBABILISTIC GRAPHICAL MODELS

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F16%3A86098872" target="_blank" >RIV/61989100:27240/16:86098872 - isvavai.cz</a>

Alternative codes found

RIV/61989100:27740/16:86098872

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

TRAFFIC SPEED PREDICTION USING PROBABILISTIC GRAPHICAL MODELS

Original language description

The importance of traffic state prediction steadily increases together with growing volume of traffic. The ability to predict traffic speed and density in short to medium horizon is one of the main tasks of every Intelligent Transportation System. Many such systems are currently developed to monitor and control the traffic flow in various states. It is also very important for dynamic route planning applications. Basically, there are two possible approaches to this prediction. The first is to utilize physical properties of the traffic flow to construct a numerical model. This approach is, however, very difficult to implement. Due to the problems with traffic sensor density, it is very difficult to gather enough data to accurately describe the starting and boundary conditions of the model. The other option is to use historical traffic data and relate information and patterns they contain to the current traffic state by the application of some form of statistical or machine learning approach. Authors propose a solution to use a probabilistic graphical models (PGM) for this task. These models are naturally able to capture all complexities in the traffic and incorporate uncertainty of the traffic data. This paper presents an algorithm based on dynamic Bayesian networks (DBN), which are one of the most widely used PGMs for modelling of dynamical systems. Our algorithm was tested on real data coming from the Czech Republic motorways.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

IN - Informatics

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the third international conference on traffic and transport engineering (ICTTE)

ISBN

978-86-916153-3-8

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

941-948

Publisher name

SCIENTIFIC RESEARCH CENTER LTD BELGRADE

Place of publication

Bělehrad

Event location

Bělehrad

Event date

Nov 24, 2016

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

000391016300134