A Novel Framework to Use Association Rule Mining for classification of traffic accident severity

Meenu Gupta

Institute of Technology & Science

Vijender Kumar Solanki

Institute of Technology & Science

Vijay Kumar Singh

Institute of Technology & Science

Introduction: Traffic accidents are an undesirable burden on society. Every year around one million deaths and more than ten million injuries are reported due to traffic accidents. Hence, traffic accidents prevention measures must be taken to overcome the accident rate. Different countries have different geographical and environmental conditions and hence the accident factors diverge in each country. Traffic accident data analysis is very useful in revealing the factors that affect the accidents in different countries. This article was written in the year 2016 in the Institute of Technology & Science, Mohan Nagar, Ghaziabad, up, India.

Methology: We propose a framework to utilize association rule mining (arm) for the severity classification of traffic accidents data obtained from police records in Mujjafarnagar district, Uttarpradesh, India.

Results: The results certainly reveal some hidden factors which can be applied to understand the factors behind road accidentality in this region.

Conclusions: The framework enables us to find three clusters from the data set. Each cluster represents a type of accident severity, i.e. fatal, major injury and minor/no injury. The association rules exposed different factors that are associated with road accidents in each category. The information extracted provides important information which can be employed to adapt preventive measures to overcome the accident severity in Muzzafarnagar district.

Keywords: association rule mining, classification, severity analysis, traffic accident
Published
2017-01-01
Downloads

How to Cite

[1]
M. Gupta, V. Kumar Solanki, and V. Kumar Singh, “A Novel Framework to Use Association Rule Mining for classification of traffic accident severity”, ing. Solidar, vol. 13, no. 21, pp. 37–44, Jan. 2017, doi: 10.16925/in.v13i21.1726.
Metrics
File downloads
382
Citations
  • Citation Indexes: 1
Captures
  • Readers: 22