Application of Case Based Reasoning Using The K-Nearest Neighbor Algorithm in an Expert System for Diagnosing Pests and Diseases of Sugarcane Plants

Sugarcane pests and diseases are still diagnosed manually, which can lead to errors such as data loss or inaccurate data. The goal of this research is to develop an expert system for identifying plant pests and diseases that affect sugarcane yield and quality. This data was obtained through literature study, observation, and interviews. The Case Based Reasoning method is used to find cases by comparing previous cases with recent cases using similarity calculations with the K-Nearest Neighbor algorithm to find the best solution from the identified cases. The results of this study indicate that the expert system for diagnosing sugarcane pests and diseases is easy to use, the appearance is easy to reach, and the diagnostic process does not take a long time. Based on testing the accuracy of the system to diagnose according to the expert's mind, it got an accuracy of 96% from 50 cases tested with the system and got a percentage result of 87.33% from 10 respondents including very feasible criteria.