Analisa Perbandingan Metode Teorema Bayes Dan Case Based Reasoning Diagnosa Penyakit Pada Tanaman Tomat

Abstract

Diseases in tomato plants have a significant impact on the agriculture industry as they can reduce crop yields and tomato quality. Therefore, this research aims to compare the Bayesian Theorem and Case-Based Reasoning (CBR) methods in diagnosing tomato plant diseases. The Bayesian Theorem is a statistical approach based on probability, while CBR uses knowledge from previous cases. This study includes an analysis of the performance of both methods in terms of diagnostic accuracy, result delivery speed, and resource efficiency. The research results have the potential to assist farmers and agricultural experts in choosing the most suitable method for diagnosing tomato plant diseases. Furthermore, the implementation of expert systems in agriculture can have a positive impact on tomato cultivation productivity and sustainability. This research aims to provide practical guidance for stakeholders in the agricultural field and contribute to sustainable agriculture improvement, with a specific focus on disease identification and management in tomato plants. The percentage values of the application of the Bayesian Theorem and Case-Based Reasoning methods show that Case-Based Reasoning has a lower success rate in diagnosing Fusarium Wilt and Bacterial Wilt compared to the Bayesian Theorem. However, Case-Based Reasoning excels in diagnosing Tomato Yellow Leaf Curl Virus (TYLCV), achieving a success rate of 100%, while the Bayesian Theorem reaches 63%.