Διάγνωση διαβήτη με χρήση αλγορίθμων μηχανικής μάθησης
Diabetes diagnosis using machine learning algorithms
View/
Keywords
Diabates ; Αλγόριθμοι μηχανικής μάθησης ; Διάγνωση διαβήτη ; Μηχανές διανυσμάτων υποστήριξης ; Διερευνητική ανάλυση δεδομένων ; Exploratory Data Analysis (EDA) ; Λογιστική παλινδρόμηση ; Logistic regression ; Μηχανές διανυσμάτων υποστήριξης ; Support Vector Machines (SVM) ; Κ-Πλησιέστεροι Γείτονες ; k-Nearest Neighbors (KNN) ; Βαθμιδωτής ενίσχυσης ; Gradient boosting ; Τυχαία δάση ; Random forestsAbstract
This dissertation focuses on improving the diagnosis and prediction of diabetes using
machine learning algorithms. The analysis is performed on a dataset collected from
Kaggle.com, with the objective of developing models that can accurately predict the
probability of developing diabetes. Through exploration, data analysis and the use of
various machine learning algorithms such as Logistic Regression, Support Vector
Machines (SVM), Gradient Boosting, K-Nearest Neighbors (KNN) and Random Forests,
the dissertation seeks to enhance the accuracy of diagnosis. The results of the
research indicate the potential of these algorithms to provide reliable predictions and
highlight the significance of machine learning as a mechanism for improving public
health, suggesting future directions for further research and development.