Etudiant : BELEMOUALEM Chaimae

Filière : Master Web Intelligence et Sciences des Données (WISD)

Encadrant : Pr. EL BEQQALI OMAR

Annèe : 2022

Résumé : This brief is part of a Master's internship carried out at LASPI-LABORATORY at Roanne ,over a period of 5 months to obtain the Master "Web Intelligence and Data Science" in partnership with the Erasmus+ exchange program. This Master is in collaboration with the University Sorbonne Paris Nord (Master in Data Mining and Informatique et Décisionnel, EID2). As a new concept that emerged in the middle of 1990’s, data mining can help researchers gain both novel and deep insights and can facilitate unprecedented understanding of large medical datasets such as diabetes . Diabetes is a chronic disease in which blood sugar levels are too high. It can lead to very dangerous complication such as: heart disease and stroke, and even to complications requiring amputation of one of the parties . By using machine learning and deep learning techniques in the field of diabetes, diabetes diagnosis, diabetes prediction, diabetes self-management, diabetes prevention and patient profile extraction can be achieved to cope with this deadly disease. In this Work , different techniques of maching learning and deep learning were implemented in order to diagnosis diabetes and other algorithms such as ECLAT ,Apriori and FP growth are used to detect patients profiles (Diabetics patients ) . As the results of those different techniques ,the LSTM and SVM with PCA achieved a great accuracy 89.36% ,91,5 respectively .