| Titre : | Deep learning approach for diabetes prediction |
| Auteurs : | Mohanned Adissa, Auteur ; Samir Bourekkache, Directeur de thèse |
| Type de document : | Monographie imprimée |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2023 |
| Format : | 1vol.(60p.) / ill.couv.ill.encoul / 30cm |
| Langues: | Anglais |
| Mots-clés: | Keywords: Diabetes, Artificial intelligence, Machine learning, Deep learning |
| Résumé : |
Diabetes is a chronic disease that needs to be taken seriously, as it can lead to far more dangerous complications if left untreated. Early detection of this disease can greatly help in curing and saving patients. The progression made by artificial intelligence provides solutions that can be used in order to predict diabetes. In this work, we talked about diabetes, machine and deep learning and the approaches that are used to predict diabetes In our project, we have used the LSTM architecture to build a diabetes prediction model, our model achieved accuracy of 98.64% and validation accuracy of 96.99%. |
| Sommaire : |
General introduction.. 1 Chapter Ⅰ: Diabetes .... 3 I.1. Definition ..... 3 I.2. Types of Diabetes ... 4 I.2.1. Type 1 Diabetes ... 4 I.2.2. Type 2 Diabetes ... 7 I.2.3. Gestational Diabetes ... 9 I.3. Complications of diabes... 11 I.4. Prevention of diabetes . 11 I.5. Conclusion ... 12 Chapter Ⅱ: Machine and Deep learning ... 13 II.1. Machine Learning .. 13 II.1.1. Types of Machine Learning ..... 14 II.2. Deep Learning .... 17 II.2.1. Artificial neural network ... 17 II.3. Conclusio.... 21 Chapter Ⅲ: Diabetes prediction .. 22 III.1. Convolutional Neural Networks (CNNs) .... 22 III.2. Recurrent Neural Networks (RNNs) .... 25 III.2.1. Types of Recurrent neural networks .... 27 III.3. Long Short-Term Memory (LSTM) .... 27 III.4. Deep Belief Networks (DBNs) ... 28 III.5. Related Works ... 29 III.6. Conclusion ... 35 Chapter Ⅳ: Design of the approach .... 36 IV.1. Global architecture of the system ... 36 IV.1.1. Dataset ...... 37 IV.1.2. Preprocessing ... 37 IV.1.3. Splitting dataset .. 38 IV.1.4. LSTM ...... 38 IV.1.5. Predictio... 40 IV.1.6. Model evaluation. 40 IV.2. Conclusion ..... 41 Chapter Ⅴ: Implementation and results .... 42 V.1. Implementation frameworks, tools and libraries.. 42 V.2. Implementation phases ..... 43 V.2.1. Loading dataset General conclusion ... 59 References ................. 60 |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/794 | Mémoire master | bibliothèque sciences exactes | Consultable |
