Abstract
Nowadays, Traffic accidents (TAs) causes a lot of damage in terms of human and asset. TAs records have been stored and published in many Open Data sources. In this article, we propose a method of using clustering algorithm Density-based Spatial Clustering of Applications with Noise (DBSCAN) to classify the TAs’ records in order to find the Density Traffic Accident Areas (DTAA). We also discuss about the optimal variables in DBSCAN that need to consider when applied in real urban areas. We emphasize the characteristics of DTAA by the Bound Value (BV) and modeling some important traffic characteristics. We then evaluate the performance and efficiency between DBSCAN and K-mean clustering methods. The result clusters and characteristics can be easily adapted to real traffic applications for increase the travel safety.
Highlights
In recent years, Traffic Accident is one of the most brutal “disease” happening in the world
We evaluated our approach with the Open Data set from NYC and Great Britain
Sandor and Peter et al [8] used Density-Based Spatial Clustering of Applications with Noises (DBSCAN) on GPS coordinates of Traffic accidents (TAs) in ordered to form the Black spots where the number of accidents is higher than other areas
Summary
Traffic Accident is one of the most brutal “disease” happening in the world. The Open Data sources are the great help for research on analyze and classify historical data They contain a lot of different type of data; include the records of Traffic Accident. The result gave us the clusters and their abnormal characteristics that we can later use in suggestion methods to avoid these dangerous areas or suggest the one who has the responsibility to check for the cause why that location have so much Traffic Accident happen based on the abnormal characteristics. Al [7] listed the characteristics of TAs in both subjectivity and environment aspect They used Association Rule Mining Algorithm to add the rules to each cluster, the clusters with strong rules will be taken for analysis the cause of TAs. We, want to consider more about how to apply the clustering method and TAs’ characteristics to specific real-life location, so we came up with the Bound Value
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
