Prediction of Daily Traffic Accident Counts and Related Economic Damage in the Czech Republic

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24310%2F16%3A00000281" target="_blank" >RIV/46747885:24310/16:00000281 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Prediction of Daily Traffic Accident Counts and Related Economic Damage in the Czech Republic
Original language description
Free datasets describing weather and traffic accidents in the Czech Republic have been used for the training of neural network that would predict the number of traffic accidents and the level of economic damage for a given day. The aim of the research is to find out whether there are enough statistical dependencies in the available data so that a practically usable predictor could be trained from them. The Pearson’s chi-squared test was used to select input attributes for the neural network. The selected attributes are month, day of week, temperature in two selected preceding days and in the current day, precipitation, and snow. The neural network has been trained on the daily data of the years 2009 till 2014 divided into training and development test sets. The accuracy of the network after this training on more recent days is higher than majority voting, which can motivate a future research.
Czech name
—
Czech description
—

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
34th International Conference Mathematical Methods in Economics 2016 Conference Proceedings
ISBN
978-80-7494-296-9
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
606-611
Publisher name
Technical University of Liberec
Place of publication
Liberec
Event location
Liberec
Event date
Jan 1, 2016
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
000385239500104

Similar results(10)