Text
KLASIFIKASI PENYAKIT DIABETES MENGGUNAKAN METODE DECISION TREE DAN RANDOM FOREST
Diabetes is a metabolic disease characterized by hyperglycemia caused by defects in insulin secretion or reduced insulin production, slow insulin action or both. Diabetes is one of the deadliest diseases in the world. Accurate classification of people who have positive or negative laboratory test results have diabetes is important to get the right treatment. The purpose of this study is to classify the status of people who have positive or negative laboratory test results for diabetes using the Decision Tree C4.5 and Random Forest methods. In this study used data taken from kaggle.com. This data has a size of 520 and 17 variables. The variables are Age, Gender, Polyuria, Polydipsia, sudden weight loss, weakness, Polyphagia, Genital thrush, visual blurring, Itching, Irritability, delayed healing, partial paresis, muscle stiffness, Alopecia, Obesity, class. The results of this study indicate the level of accuracy, precision, recall, specificity, and F1 score on the Decision Tree C4.5 method respectively of 91.35%, 93.55%, 92.06%, 90.24%, and 92.80%. By using the Random Forest method, the accuracy, precision, recall, specificity, and F1 score levels respectively 98.08%, 100%, 96.88%, 100%, and 98.41%. Based on these measures, it is concluded that the Random Forest method is better than the Decision Tree C4.5 method in classifying the status of people who have positive or negative laboratory test results for diabetes. Keywords: Diabetes, Decision Tree C4.5, Random Forest
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2207004875 | T81689 | T816892022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available