<![CDATA[This study presents the application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model for predicting Diabetes Mellitus using two primary input features, namely glucose level and body mass index (BMI). The research employs a quantitative experimental approach using the public diabetes dataset obtained from Kaggle. The data underwent preprocessing steps, including cleaning, normalization, and splitting into training and testing subsets. The ANFIS model was designed with fuzzification, rule-based inference, and a hybrid learning algorithm to optimize membership function parameters. Model evaluation was conducted using accuracy, precision, recall, and F1-score. The results show that the ANFIS model achieved an accuracy of 69.70% on the test dataset, demonstrating strong sensitivity in detecting diabetic cases but generating a notable number of false positives. These findings indicate that ANFIS has potential as an early-screening decision support tool, although further optimization and additional features are required to enhance predictive performance.]]>
Copyrights © 2025
