Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks

Abstract

Several different factors contribute to injury severity in traffic accidents, such as driver characteristics, highway characteristics, vehicle characteristics, accidents characteristics, and atmospheric factors. This paper shows the possibility of using Bayesian Networks (BNs) to classify traffic accidents according to their injury severity. BNs are capable of making predictions without the need for pre assumptions and are used to make graphic representations of complex systems with interrelated components. This paper presents an analysis of 1,536 accidents on rural highways in Spain, where 18 variables representing the aforementioned contributing factors were used to build 3 different BNs that classified the severity of accidents into slightly injured and killed or severely injured. The variables that best identify the factors that are associated with a killed or seriously injured accident (accident type, driver age, lighting and number of injuries) were identified by inference.

Analysis of traffic accidents on rural highways using Latent Class Clustering and Bayesian Networks

“…This results are coherent with previous studies which have highlighted some of this variables as key variables in KSI accidents (Abel-Aty 2003;Al-Ghamdi, 2002;de Oña et al, 2011;Gray et al, 2008;Helai et al, 2008;Kashani and Mohyamany, 2011;Kockelman and Kweon, 2002;Pande and Abel-Aty, 2009;Montella et al, 2011).…”

“…The values of accuracy range from 64.0% in C1 to 55.1% in C4. These values are within the same range found in previous studies (Abdelwahab and Abdel-Aty, 2001;De Oña et al, 2011;Mujalli and De Oña, 2011) that used classification techniques for similar objectives. Table 4 shows that only C1 (64.0%) achieved a statistically significant improvement of accuracy as compared with results obtained for the EDB (59.5%).…”

“…Accident type (ACT) has been identified in several previous studies (Al-Ghamdi, 2002;de Oña et al, 2011;Kashani and Mohyamany, 2011;Montella et al, in press) as one of the key variables in accident severity. Particularly, in this study head-on collision (HOC) and collision with pedestrian (CP) were the type of accident with the highest probability of KSI (see Table 6).…”

“…Many different methodological approaches have been used to analyse severity (Savolainen et al, 2011): probit models (Bayesian ordered, binary, bivariate binary, bivariate ordered, heteroskedastic ordered, multivariate, ordered, random parameters ordered), logit models (bayesian hierarchical binomial, binary, generalized ordered, heteroskedastic ordered, markow switching multinomial, mixed generalized ordered, mixed joint binary, multinomial, nested, ordered, random parameters, random parameters ordered, sequential binary, sequential, simultaneous binary), log-linear model, partial proportional odds model, artificial neural networks, and classification and regression trees. Recently, Bayesian Networks (BN) are being used to analyse traffic accident severity, with satisfactory results (Simoncic, 2004;De Oña et al, 2011;Mujalli and de Oña, 2011).…”

Road Traffic Accidents Among Drivers in Abu Dhabi, United Arab Emirates

“…The factors associated with RTA's in the country are comparable to what one would expect in most countries, although a further breakdown of factors under 'other' categories is necessary since that particular category has over half the number of accidents. Other factors identified to contribute to traffic safety include the 4 E's: Engineering, Enforcement, Education and Emergency [11],while human error, vehicle and road network or infrastructure is also a factor in traffic safety reduction [12]. A recent study in the UAE [13] identified driving behaviour, awareness, education and training, infrastructure, vehicle and law enforcement as some of the main factors contributing to traffic safety in the country.…”