Analysis of road accident is very important because it can expose the relationship between the different types of attributes that contributes to a road accident. Attributes that affect the road accident can be road attribute, environment attributes, traffic attributes etc. Analyzing road accident can provide the information about the contribution of these attributes which can be utilized to overcome the accident rate. Nowadays, Data mining is a popular technique for examining the road accident dataset. In this study, we have performed the classification of road accident on the basis of road user category. We have used Self Organizing map (SOM), K-modes clustering technique to group the data into homogeneous segments and then applied Support vector machine (SVM), Naive Bayes (NB) and Decision tree to classify the data. We have performed classification on data with and without clustering. The result illustrates that better classification accuracy can be achieved after segmentation of data using clustering.
CITATION STYLE
Tiwari, P., Kumar, S., & Kalitin, D. (2017). Road-user specific analysis of traffic accident using data mining techniques. In Communications in Computer and Information Science (Vol. 776, pp. 398–410). Springer Verlag. https://doi.org/10.1007/978-981-10-6430-2_31
Mendeley helps you to discover research relevant for your work.