Clustering Algorithms to Analyze the Road Traffic Crashes
This work addresses clustering challenges for road traffic crash analysis, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the problem of selecting clustering methods and optimal cluster numbers for road accident data, finding that DBSCAN and OPTICS algorithms are more effective and efficient based on real-life data from North Carolina.
Selecting an appropriate clustering method as well as an optimal number of clusters in road accident data is at times confusing and difficult. This paper analyzes shortcomings of different existing techniques applied to cluster accident-prone areas and recommends using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Ordering Points To Identify the Clustering Structure (OPTICS) to overcome them. Comparative performance analysis based on real-life data on the recorded cases of road accidents in North Carolina also show more effectiveness and efficiency achieved by these algorithms.