<![CDATA[The increase in obesity has become one of the major challenges in the healthcare sector, requiring quick and effective solutions for early classification and diagnosis. This study aims to develop a web-based system using the K-Nearest Neighbors (KNN) method to classify obesity based on user data, thereby assisting the public in early detection of obesity. The dataset used in this research comprises 2,111 records and 17 attributes, covering various factors related to obesity, such as weight, height, age, gender, genetic factors, and lifestyle, including dietary habits and physical activity. This dataset was obtained from the UCI Repository website. The data is processed using the K-Nearest Neighbors (KNN) method to generate an accurate and relevant obesity classification model. To evaluate the performance of the K-Nearest Neighbors (KNN) model, the dataset was split into training and testing data with a ratio of 80:20 and evaluated using a Confusion Matrix, resulting in an accuracy of 89%. Since the model demonstrates good performance in classifying test data, it can be implemented as a web-based system to test new data. This system will produce weight classification results, including categories such as "Underweight," "Normal Weight," "Overweight," and "Obesity." Thus, the public can easily and accurately classify obesity using this system.]]>
Copyrights © 2025
