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

Abstract

SUMMARYReducing 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.

Evaluation of database balancing techniques for road accident severity classification employing Artificial Neural Network

“…This problem occurs when a dataset is dominated by the main class (for example, accidents WOV) to the detriment of classes considered rarer or minority, such as accidents WV. Furthermore, there are additional experimental complications due to the variations of the database size, which is a factor that leads to signi#icant errors in estimating the level of traf#ic accident injuries (Bolón-Canedo et al, 2014;Wang et al, 2014).…”

“…The oversampling methods, that create a subset based on the original database using the replicating process of certain instances or by creating new instances from the pre-existing classes in the database; and, #inally, the hybrid methods, that combine these two sampling methods (Bolón-Canedo et al, 2014). Wang et al (2014) emphasise that in the literature on traf#ic accident severity, most of the studies use classi#ication accuracy to measure the quality of a given classi#ier as a decision tree, ANN, Bayesian Networks, etc. (Chen et al, 2016) when using an imbalanced dataset.…”