Determining The Degree Of Drivers Responsibility For Car Accidents By Using Data Mining Methods The Case Of Addis Ababa Traffic Control And Investigation Department

Road traffic accidents (RT As) are now becoming one of the leading public healthrnproblems in Ethiopia. Due to accidents people are dying and getting di sabled furtherrnresulting in property losses. It is more severe in the capital city of Ethiopia, Addis Ababarnwhere most cars in the country are bustling. Most accidents in the capital are due torndriver problems. And most of the fatalities are attributed to the accident type pedestrianrnhit by car.In this research an attempt has been made to apply the detIsion tree and multilayerrnperceptron (MLP) neural network data mining techniques to analyse the accident data.rnThe research focuses on predicting the degree of dri ver' s· responsibility for car acc identsrnand identifying the important factors influencing the different levels of responsibility byrnusing the RTA dataset of Addis Ababa Traffic control and investigation departmentrn(AARTCIO).In the research undertaking standard data m1l1111g methodology has been employed.rnAccordingly, the domain area; in this case the traffic control system is carefully studied,rnthe accident dataset is carefully investigated to have a clear picture and verification of therndata. Preprocessing the data by performing data cleaning, data se lection, datarntransformation and replacing missing value activities are also among the crucial activitiesrnthat have been carried out in this research.Exploratory data analysis (EDA), descriptive modeling, predictive modelingrn(c lassification and regression), discovering patterns and rules and retrieval by content.rnIn accomplishing the data mining task a number of standard techniques and tools can bernemployed. The major data mining techniques according to Berry and Linoff (2004), arerndecision trees, neural networks, cluster Analysis and Statistical methods li ke, Bayesianrninference, logistic regression, log-linear models, the common techniques of clusterrnanalysis are :which are divi sible algoritlu agglomeration algorithm s, partitionalrnclustering, and incremental clustering. Association Rules, genetic algorithms and fuzzyrninference systems are also worth mentioning.

Get Full Work

Report copyright infringement or plagiarism