Accident Causation Factor Analysis of Traffic Accidents using Rough Relational Analysis

Accident Causation Factor Analysis of Traffic Accidents using Rough Relational Analysis

Caner Erden (Department of Industrial Engineering, Sakarya University, Sakarya, Turkey) and Numan Çelebi (Department of Computer Science, Sakarya University, Sakarya, Turkey)
Copyright: © 2016 |Pages: 12
DOI: 10.4018/IJRSDA.2016070105
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The aim of this study is to show that the decision rules generated from Rough Sets Theory can be used for a new relational analysis. Rough Sets Theory generally works with small datasets more than big data. If we can deal with the decision rules and its complexities, it is still possible to analyze big data with Rough Set Theory. That is why in this study the authors offer a statistical method to overdue problems which belongs to big data. According statistical methods, a lots of decision rules generated from rough sets theory become useful information. Using a real case data on the traffic accident which were taken place in USA in 2013, this paper finds the relationships between accident causation factors which may be referred to decision makers in the field of traffic.
Article Preview

1. Introduction

Traffic accident is a major problem in the world. According to the World Health Organization (WHO), deaths cause by traffic accidents are international epidemic disease and it is spreading very fast around the world (Organization, 5-years WHO Strategy for Road Traffic Injury prevention, 2002). 1.2 million people are killed and 50 million people are injured in a year through traffic accidents (Organization, World Report on Road Traffic Injury Prevention, 2004). Because of these number of casualty, it could be seen that traffic accidents has negative effects on societies and the preventions of traffic accidents are very important in saving the lives of people.

The factors that affect accident occurrences have been discussed by a lot of researchers and public agencies throughout the history of invention of motor vehicle. Researchers are interested in finding factors affecting traffic accidents (Chong, Abraham, & Paprzycki, 2004b) (Chong, Abraham, & Paprzycki, 2004a). Also they tried to find out the factors and rank the factors (Wong & Chung, 2007). Three important major factors that cause traffic accidents are drivers’ faults, road and weather conditions. Driver’s age and gender play important roles when it comes to the factor related to driver (Miaou & Lum, 1993). Besides these factors, alcoholic rates, drug involvements can be considered as other factors of the driver fault. In trying to reduce casualties, automotive engineers and researchers have produce safer motor vehicles with technologies and features such as airbag systems, automatic braking systems, infrared night vision system, adaptive headlamps, backup camera, tire pressure monitoring systems or deflation detection systems, driverless car system etc. Big technology companies are also competing for the driverless car to decrease the number of accidents. Despite all prevention, traffic accident is irrepressible and it will exist forever. Therefore, the main goal is to try to get minimum fatalities in an accident by using different tools including statistical methods, mathematical models, intelligent systems, log-linear models and fuzzy systems.

There are many studies that are trying to find out the relationships between the factors that affects traffic accidents. Buzeman et al.; developed a mathematical model to estimate fatalities using factors such as fleet mass, impact speed distribution and vehicle protection (Buzeman, Vano, & Lovsund, 1998). Kweon and Kockelman also used data to distinguish between driver age, gender, vehicle type, crash type and injury severity (Kweon & Kockelman, 2003). Martin et al. in their work, used a model with crash partner, seat belt use and air bag availability data respectively. They found that car to LTV collisions cause fatalities more than car to car collusions (Martin, Crandall, & Pilkey, 2000). Mayhew et al. used gender factor as an input of the analysis and they studied whether female driver are more successful in driving than male. As a conclusion, they stated that male and female drivers have seen similar reduction in single-vehicle, nighttime and alcohol-related crashes (Mayhew, Ferguson, Desmond, & Simpson, 2003). In 1997, Tavris et al. used a real – life data of patients discharge from Wisconsin hospital with factors affecting traffic accident as gender, age, type of crash and occupant role in motor vehicle crash injuries After analyzed they found that; number of male hospitalized for motor vehicle crash injuries is bigger than female within 95% confidence (Tavris, Kuhn, & Layde, 2001).

Besides those references, there are several studies about Rough set theory on image processing and ad hoc network. Roy et al collected most of studies on image processing in a review article. They indicated that Rough set theory could provide a better framework for the image processing (Roy, Goswami, Chakraborty, Azar, & Dey, 2014). Swati et al. used Rough set theory in several protocols on their review article (Chowdhuri, Roy, Goswami, Azar, & Dey, 2014). On another review study Dey et al. reviewed image mining and framework studies. They also reviewed image mining techniques and association rule generating given by different researchers. This paper also helped to select an appropriate image mining technique among all the available techniques (Dey, 2015).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 4: 4 Issues (2017)
Volume 3: 4 Issues (2016)
Volume 2: 2 Issues (2015)
Volume 1: 2 Issues (2014)
View Complete Journal Contents Listing