SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND

This article attempts to model the daily number of road accidents in Poland using data mining methods such as random forests and artificial neural networks. There was compared the network, which takes into account all the analyzed explanatory variables to the network with reduced the number of input...

Full description

Bibliographic Details
Main Author: Kinga Kądziołka
Format: Article
Language:English
Published: University of Gdansk 2015-12-01
Series:Contemporary Economy
Subjects:
Online Access:http://www.wspolczesnagospodarka.pl/?p=1088
_version_ 1811306434702344192
author Kinga Kądziołka
author_facet Kinga Kądziołka
author_sort Kinga Kądziołka
collection DOAJ
description This article attempts to model the daily number of road accidents in Poland using data mining methods such as random forests and artificial neural networks. There was compared the network, which takes into account all the analyzed explanatory variables to the network with reduced the number of input variables. The network with reduced set of input variables was characterized by a slightly lower average absolute percentage error on the test set than the network, which includes all explanatory variables. There was also identified clusters of poviats characterized by high risk of road accidents.
first_indexed 2024-04-13T08:44:22Z
format Article
id doaj.art-869e46922a8c45f3b3e15932a3dbeba3
institution Directory Open Access Journal
issn 2082-677X
2082-677X
language English
last_indexed 2024-04-13T08:44:22Z
publishDate 2015-12-01
publisher University of Gdansk
record_format Article
series Contemporary Economy
spelling doaj.art-869e46922a8c45f3b3e15932a3dbeba32022-12-22T02:53:45ZengUniversity of GdanskContemporary Economy2082-677X2082-677X2015-12-0164123134SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLANDKinga Kądziołka0Prokuratura Okręgowa w KatowicachThis article attempts to model the daily number of road accidents in Poland using data mining methods such as random forests and artificial neural networks. There was compared the network, which takes into account all the analyzed explanatory variables to the network with reduced the number of input variables. The network with reduced set of input variables was characterized by a slightly lower average absolute percentage error on the test set than the network, which includes all explanatory variables. There was also identified clusters of poviats characterized by high risk of road accidents.http://www.wspolczesnagospodarka.pl/?p=1088road accidentneural networkrandom forestMoran statistic
spellingShingle Kinga Kądziołka
SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
Contemporary Economy
road accident
neural network
random forest
Moran statistic
title SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
title_full SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
title_fullStr SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
title_full_unstemmed SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
title_short SPATIO – TEMPORAL ANALYSIS OF ROAD ACCIDENTS IN POLAND
title_sort spatio temporal analysis of road accidents in poland
topic road accident
neural network
random forest
Moran statistic
url http://www.wspolczesnagospodarka.pl/?p=1088
work_keys_str_mv AT kingakadziołka spatiotemporalanalysisofroadaccidentsinpoland