Markov chain model approach for traffic incident length prediction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F17%3A10238089" target="_blank" >RIV/61989100:27740/17:10238089 - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/citation.cfm?doid=3157737.3157750" target="_blank" >https://dl.acm.org/citation.cfm?doid=3157737.3157750</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3157737.3157750" target="_blank" >10.1145/3157737.3157750</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Markov chain model approach for traffic incident length prediction

Popis výsledku v původním jazyce

One of the most challenging parts of traffic modeling is how to model traffic behavior during traffic incidents. One of the possible approaches to this problem is to use historical data to identify typical incidents and use this knowledge to classify future time series. This classification can be utilized for example in prediction of traffic incident duration. This procedure requires solutions to several problems. The first problem is how can historical time series of traffic incidents be clustered, and these clusters can be parametrized. The second problem is how can time series of new ongoing incidents be classified to these existing clusters and how this classification can be utilized in the prediction of their length. The main aim of this article is to propose a solution to these problems. Methods utilized in addressing these problems are called Markov chains, Dynamic Time Warping, Bayesian classification and Monte Carlo simulation. © 2017 Association for Computing Machinery.

Název v anglickém jazyce

Markov chain model approach for traffic incident length prediction

Popis výsledku anglicky

One of the most challenging parts of traffic modeling is how to model traffic behavior during traffic incidents. One of the possible approaches to this problem is to use historical data to identify typical incidents and use this knowledge to classify future time series. This classification can be utilized for example in prediction of traffic incident duration. This procedure requires solutions to several problems. The first problem is how can historical time series of traffic incidents be clustered, and these clusters can be parametrized. The second problem is how can time series of new ongoing incidents be classified to these existing clusters and how this classification can be utilized in the prediction of their length. The main aim of this article is to propose a solution to these problems. Methods utilized in addressing these problems are called Markov chains, Dynamic Time Warping, Bayesian classification and Monte Carlo simulation. © 2017 Association for Computing Machinery.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

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

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

ACM International Conference Proceeding Series 2017

ISBN

978-1-4503-5376-2

ISSN

—

e-ISSN

neuvedeno

Počet stran výsledku

5

Strana od-do

63-67

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Čcheng-tu

Datum konání akce

12. 10. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—