Merging Bayesian Networks based on different types of input knowledge

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21260%2F18%3A00326495" target="_blank" >RIV/68407700:21260/18:00326495 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Merging Bayesian Networks based on different types of input knowledge

Popis výsledku v původním jazyce

Bayesian networks are one of the most suitable tools for traffic accident data analysis. A well-designed and trained Bayesian network is the first assumption for obtaining good results. Two sources of information can be used for this purpose. They are information extracted from measured historical data and also information specified by an expert. The latter one can also involve some generally known rules or knowledge based on traffic regulations or safety rules. Mostly, only one of these sources of information is used. After training the network can be evaluated with standard methods based on likelihood or prediction error evaluation. The goal of this paper is to show that if two Bayesian networks are created, e.g. one from the data and second from the expert knowledge, they can be merged into one which joins the objective information from data with the subjective opinion from expert and which has better evaluation than the original ones.

Název v anglickém jazyce

Merging Bayesian Networks based on different types of input knowledge

Popis výsledku anglicky

Bayesian networks are one of the most suitable tools for traffic accident data analysis. A well-designed and trained Bayesian network is the first assumption for obtaining good results. Two sources of information can be used for this purpose. They are information extracted from measured historical data and also information specified by an expert. The latter one can also involve some generally known rules or knowledge based on traffic regulations or safety rules. Mostly, only one of these sources of information is used. After training the network can be evaluated with standard methods based on likelihood or prediction error evaluation. The goal of this paper is to show that if two Bayesian networks are created, e.g. one from the data and second from the expert knowledge, they can be merged into one which joins the objective information from data with the subjective opinion from expert and which has better evaluation than the original ones.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Young Transportation Engineers Conference 2018

ISBN

978-80-01-06464-1

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

53-61

Název nakladatele

Fakulta dopravní

Místo vydání

Praha

Místo konání akce

Praha, Horská 3

Datum konání akce

1. 11. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—