Classification of Road Accident Patterns


Anuj Sharma , Dehradun Institute of Technology (DIT University); Dr. Sandeep Sharma, Dehradun Institute of Technology (DIT University); Dr. Santosh Kumar, Dehradun Institute of Technology (DIT University)


Road Accident, Data Mining, Neural Network


This paper presents the classification of vehicular road accident patterns using data mining in Uttarakhand state. In order to provide insights for the development of safety improvement strategies. At this aim, data mining techniques are used to analyze the data relative to the 4,130 crashes all including vehicular crashes. Understanding the accidents on age based classification under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Data mining a non-trivial extraction of novel, implicit, and actionable knowledge from large data sets is an evolving technology which is a direct result of the increasing use of computer databases in order to store and retrieve information effectively. It also enables data exploration, data analysis, and data visualization of huge databases at a high level of abstraction, without a specific hypothesis in mind. Understanding the casualties and classifying the road accidents on gender basis can help in improving traffic safety conditions. This paper presents a data mining approaches to explore various factors for vehicular collision. We have used neural network to classify various road accident patterns that can in turn help in analyzing the road accidents and casualties according to age, gender and location within the state. Feed forward neural network is used to evaluate the various results regarding the related study. With the use of data mining techniques it would be analyze and observe the large database having different records of vehicular road crashes in Uttarakhand state.

Other Details

Paper ID: NCILP027
Published in: Conference 1 : NCIL 2015
Publication Date: 16/10/2015
Page(s): 106-111

Article Preview

Download Article