| Autor: |
Aruna, Gadde, Umalwara, Md, Tejaswini, Velpula, Kumaraswamy, Eelandula, Ghate, Sukhaveerji, Rajesh, Mothe |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 2971 Issue 1, p1-9, 9p |
| Abstrakt: |
Diabetes mellitus, also called diabetes, is a class of metabolic diseases that affects hundreds of millions of mankind. It is an extra discoverer of a variety of diseases, for example: coronary failure, blindness, urinary organ diseases etc. The detection of diabetes is of great importance, concerning its severe complications. To reduce these, several investigators are functioning to forecast diabetes at a previous period utilizing many techniques. This approach presents, Classification of Diabetes Mellitus Prediction Using Hybrid Machine Learning (ML) Techniques. The goal of this examination is to implement a technique that can assume a patient's diabetic risk level with the best accuracy. The acquired dataset as the outcome of the K-means Clustering model was fed to a hybrid model with PCA and K-means clustering. Investigations are conducted on the Pima Indians Diabetes Database (PIDD) taken from the UCI ML Repository. The performance of the three algorithms (NB, SVM and Hybrid ML technique) is calculated on different aspects such as Accuracy, Precision, F-Measure and Recall. The investigations presented that Hybrid Machine Learning classifiers method implemented better than the other classifiers exclusively. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
