Document Detail


Pattern recognition for road traffic accident severity in Korea.
MedLine Citation:
PMID:  11214896     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
An increasing number of road traffic accidents (RTA) in Korea has emerged as being harmful both for the economy and for safety. An accurately estimated classification model for several severity types of RTA as a function of related factors provides crucial information for the prevention of potential accidents. Here, three data-mining techniques (neural network, logistic regression, decision tree) are used to select a set of influential factors and to build up classification models for accident severity. The three approaches are then compared in terms of classification accuracy. The finding is that accuracy does not differ significantly for each model and that the protective device is the most important factor in the accident severity variation.
Authors:
S Y Sohn; H Shin
Related Documents :
10994606 - Explaining two-lane highway crash rates using land use and hourly exposure.
25322146 - Sample size estimation for negative binomial regression comparing rates of recurrent ev...
20007666 - Effect of 20 mph traffic speed zones on road injuries in london, 1986-2006: controlled ...
20618386 - Persistence of airline accidents.
18922046 - Empirical estimation of biota exposure range for calculation of bioaccumulation paramet...
19553356 - Rank-based estimation in the {ell}1-regularized partly linear model for censored outcom...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Ergonomics     Volume:  44     ISSN:  0014-0139     ISO Abbreviation:  Ergonomics     Publication Date:  2001 Jan 
Date Detail:
Created Date:  2001-02-14     Completed Date:  2001-03-15     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  0373220     Medline TA:  Ergonomics     Country:  England    
Other Details:
Languages:  eng     Pagination:  107-17     Citation Subset:  IM; S    
Affiliation:
Department of Industrial Systems Engineering, Yonsei University, Seoul, Korea. sohns@yonsei.ac.kr
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Accidents, Traffic* / statistics & numerical data
Decision Trees*
Factor Analysis, Statistical
Humans
Korea
Logistic Models*
Neural Networks (Computer)*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Cognitive performance and muscle activation in workers with chronic shoulder myalgia.
Next Document:  Theories of musculoskeletal injury causation.