An Accident Severity Classification Model Based on Multi-Objective Particle Swarm Optimization

Chunlu WANG; Chenye QIU; Xingquan ZUO; Chuanyi LIU

doi:10.1587/transinf.2014EDP7069

An Accident Severity Classification Model Based on Multi-Objective Particle Swarm Optimization

Chunlu WANG, Chenye QIU, Xingquan ZUO, Chuanyi LIU

Full Text Views

0

Cite this

Summary :

Reducing accident severity is an effective way to improve road safety. In the literature of accident severity analysis, two main disadvantages exist: most studies use classification accuracy to measure the quality of a classifier which is not appropriate in the condition of unbalanced dataset; the other is the results are not easy to be interpreted by users. Aiming at these drawbacks, a novel multi-objective particle swarm optimization (MOPSO) method is proposed to identify the contributing factors that impact accident severity. By employing Pareto dominance concept, a set of Pareto optimal rules can be obtained by MOPSO automatically, without any pre-defined threshold or variables. Then the rules are used to form a non-ordered classifier. A MOPSO is applied to discover a set of Pareto optimal rules. The accident data of Beijing between 2008 and 2010 are used to build the model. The proposed approach is compared with several rule learning algorithms. The results show the proposed approach can generate a set of accurate and comprehensible rules which can indicate the relationship between risk factors and accident severity.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.11 pp.2863-2871

Publication Date: 2014/11/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDP7069

Type of Manuscript: PAPER

Category: Artificial Intelligence, Data Mining

Authors

Chunlu WANG
  Beijing University of Posts and Telecommunications
Chenye QIU
  Beijing University of Posts and Telecommunications
Xingquan ZUO
  Beijing University of Posts and Telecommunications
Chuanyi LIU
  Beijing University of Posts and Telecommunications

Keyword

accident severity, particle swarm optimization, multi-objective optimization, ROC curve

Cite this

Copy

Chunlu WANG, Chenye QIU, Xingquan ZUO, Chuanyi LIU, "An Accident Severity Classification Model Based on Multi-Objective Particle Swarm Optimization" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 11, pp. 2863-2871, November 2014, doi: 10.1587/transinf.2014EDP7069.
Abstract: Reducing accident severity is an effective way to improve road safety. In the literature of accident severity analysis, two main disadvantages exist: most studies use classification accuracy to measure the quality of a classifier which is not appropriate in the condition of unbalanced dataset; the other is the results are not easy to be interpreted by users. Aiming at these drawbacks, a novel multi-objective particle swarm optimization (MOPSO) method is proposed to identify the contributing factors that impact accident severity. By employing Pareto dominance concept, a set of Pareto optimal rules can be obtained by MOPSO automatically, without any pre-defined threshold or variables. Then the rules are used to form a non-ordered classifier. A MOPSO is applied to discover a set of Pareto optimal rules. The accident data of Beijing between 2008 and 2010 are used to build the model. The proposed approach is compared with several rule learning algorithms. The results show the proposed approach can generate a set of accurate and comprehensible rules which can indicate the relationship between risk factors and accident severity.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7069/_p

Copy

@ARTICLE{e97-d_11_2863,
author={Chunlu WANG, Chenye QIU, Xingquan ZUO, Chuanyi LIU, },
journal={IEICE TRANSACTIONS on Information},
title={An Accident Severity Classification Model Based on Multi-Objective Particle Swarm Optimization},
year={2014},
volume={E97-D},
number={11},
pages={2863-2871},
abstract={Reducing accident severity is an effective way to improve road safety. In the literature of accident severity analysis, two main disadvantages exist: most studies use classification accuracy to measure the quality of a classifier which is not appropriate in the condition of unbalanced dataset; the other is the results are not easy to be interpreted by users. Aiming at these drawbacks, a novel multi-objective particle swarm optimization (MOPSO) method is proposed to identify the contributing factors that impact accident severity. By employing Pareto dominance concept, a set of Pareto optimal rules can be obtained by MOPSO automatically, without any pre-defined threshold or variables. Then the rules are used to form a non-ordered classifier. A MOPSO is applied to discover a set of Pareto optimal rules. The accident data of Beijing between 2008 and 2010 are used to build the model. The proposed approach is compared with several rule learning algorithms. The results show the proposed approach can generate a set of accurate and comprehensible rules which can indicate the relationship between risk factors and accident severity.},
keywords={},
doi={10.1587/transinf.2014EDP7069},
ISSN={1745-1361},
month={November},}

Copy

TY - JOUR
TI - An Accident Severity Classification Model Based on Multi-Objective Particle Swarm Optimization
T2 - IEICE TRANSACTIONS on Information
SP - 2863
EP - 2871
AU - Chunlu WANG
AU - Chenye QIU
AU - Xingquan ZUO
AU - Chuanyi LIU
PY - 2014
DO - 10.1587/transinf.2014EDP7069
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2014
AB - Reducing accident severity is an effective way to improve road safety. In the literature of accident severity analysis, two main disadvantages exist: most studies use classification accuracy to measure the quality of a classifier which is not appropriate in the condition of unbalanced dataset; the other is the results are not easy to be interpreted by users. Aiming at these drawbacks, a novel multi-objective particle swarm optimization (MOPSO) method is proposed to identify the contributing factors that impact accident severity. By employing Pareto dominance concept, a set of Pareto optimal rules can be obtained by MOPSO automatically, without any pre-defined threshold or variables. Then the rules are used to form a non-ordered classifier. A MOPSO is applied to discover a set of Pareto optimal rules. The accident data of Beijing between 2008 and 2010 are used to build the model. The proposed approach is compared with several rule learning algorithms. The results show the proposed approach can generate a set of accurate and comprehensible rules which can indicate the relationship between risk factors and accident severity.
ER -