Mengelompokkan Daerah Rawan Kecelakaan Di Sumatera Utara dengan Algoritma Clustering

Abstract

The large population has a very large need for motorized vehicles, both 2-wheeled and 4-wheeled, which most people consider to be a primary need, not a secondary need. The large number of vehicle users causes traffic congestion so that the number of accidents increases which can result in many fatalities, minor injuries and serious injuries. The aim of this research is to group accident-prone areas in North Sumatra using the clustering method. The data source used in the research is from BPS on the topic of traffic accidents in the North Sumatra region from 2015-2022. The method used to solve this problem is K-Means Data Mining. The results obtained from this search are 3 clusters with a DBI value of 0.384, cluster 1 contains 1 region, cluster 2 contains 16 regions, and cluster 3 contains 11 regions. Carrying out this research can provide knowledge input for further research regarding the development of the k-means clustering method and help the police, especially the traffic accident handling units in each region, in predicting accidents more easily and tracing possible causes. accidents in the area.