Analisis Pola Kecelakaan Lalu Lintas Menggunakan Metode Clustering Studi Kasus Polresta Samarinda

Abstract

The increase in traffic accidents which cause major consequences, such as injuries and fatalities, can be caused by an increase in population and the need for vehicles in a certain area. It is difficult to predict the time and location of traffic accidents, which are increasing as road length and vehicle movements increase. In the Samarinda Police area, the rapid growth of urbanization and vehicle mobility is a significant challenge in reducing the number of accidents. Statistics show an alarming number of accidents, requiring more effective handling to prevent them from increasing every year. The K-Means clustering algorithm is used in this research to identify accident-prone hours and group road accident data. Six variables including accident rate, number of fatalities, serious injuries, minor injuries, type of accident, and weather were taken from data collected in 2023 by the Samarinda Police Traffic Unit. After data collection, preprocessing and K-Means Clustering stages were carried out using RapidMiner. The results of the analysis help design more effective prevention strategies.