Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea
نویسندگان
چکیده
Increasing amount of road traffic in 1990s has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving environmental factors based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we use various algorithms to improve the accuracy of individual classifiers for two categories of severity of road traffic accident. Individual classifiers used are neural network and decision tree. Mainly three different approaches are applied: classifier fusion based on the Dempster–Shafer algorithm, the Bayesian procedure and logistic model; data ensemble fusion based on arcing and bagging; and clustering based on the k-means algorithm. Our empirical study results indicate that a clustering based classification algorithm works best for road traffic accident classification in Korea. # 2002 Elsevier Science Ltd. All rights reserved.
منابع مشابه
O5: Technical Accident Reconstruction-What Can be Learned to Improve Medical Treatment in Trauma Patients
Annually, more than 1 million people were killed in road traffic accidents worldwide every year and an uncounted number were severe injured. In 2012 fatal injuries caused by road traffic accidents are under the top ten lists of causes of death in the world. It´s expected that in the near future road traffic accidents become one of the main causes of death in the world. Most of these fatal injur...
متن کاملOptimum Ensemble Classification for Fully Polarimetric SAR Data Using Global-Local Classification Approach
In this paper, a proposed ensemble classification for fully polarimetric synthetic aperture radar (PolSAR) data using a global-local classification approach is presented. In the first step, to perform the global classification, the training feature space is divided into a specified number of clusters. In the next step to carry out the local classification over each of these clusters, which cont...
متن کاملFactors contributing to fatal road traffic accidents in the South of Kerman during the period from 2013 to 2017, Iran
Background: Several factors influence the growth in the number of road traffic accidents and the resulting death rate. Road accident scenarios can be considered in different seasons and time intervals. In the present study, the role of factors effective in the growth of the number of accidents was explored in the south of Kerman during the period from 2013 to 2017. Materials and Methods: In th...
متن کاملبررسی اپیدمیولوژیک موارد مرگ و میر ثبت شده ناشی از تصادفات برون شهری در استان گلستان در سال 1394
Background and objectives: Road accidents are one of the most important causes of mortality and severe physical and psychological damage which may lead to adverse social, cultural and economic consequences in the human community. Frequency and severity of road accidents in developing countries are noticeably higher in comparison to developed countries. In Iran, 25% of casualties are due to the ...
متن کاملSimulating the Effects of Type and Spacing of Traffic Calming Measures on Urban Road Capacity
One of the major reasons for accidents is speed. Top of Form Inappropriate speed has been identified as the most important causal factor for serious traffic accidents. Traffic calming measures (TCMs) are engineering measures that are widely implemented to improve road safety by considerably reducing vehicle speed. TCMs have been widely used in urban areas to reduce vehicle flow rat...
متن کامل