Expert System for Identifying Traffic Accident Risk Levels in Samarinda City Based on Vehicle Density Patterns Using the Certainty Factor Method

Abstract

Traffic accidents are an increasingly serious problem, especially in urban areas such as Samarinda City. This study aims to design and implement an expert system to identify the level of traffic accident risk based on vehicle density patterns using the Certainty Factor (CF) method. The system utilizes expert knowledge and factors influencing accidents, such as traffic density, road conditions, and environmental conditions, to assess the level of risk. The method applied in this study is the Certainty Factor method, which is capable of handling uncertainty in the decision-making process by calculating the Measure of Belief (MB) and Measure of Disbelief (MD) values. The data used consist of secondary data related to road accidents and vehicle density levels. The system was developed using a rule-based approach and modeled using Unified Modeling Language (UML). The research findings indicate that the designed expert system is capable of identifying traffic accident risk levels effectively and efficiently. The calculation using the Certainty Factor method produced a value of 0.91, indicating a high level of risk. This demonstrates that the system can assist users in systematically analyzing accident risks and provide recommendations to reduce the likelihood of accidents. However, the system still has limitations, particularly regarding its dependence on data quality and the completeness of the knowledge base. Therefore, future studies are expected to further develop the system by adding more complex variables and integrating other methods to improve the system’s accuracy and performance.