| Titre : | HEART DISEASE ANALYSIS BASED ON DATA MINING, DEEP LEARNING AND WEARABLE TECHNOLGIES |
| Auteurs : | ABDELGHANI KABOT, Auteur ; Belkacem Abdelli, 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, 2019 |
| Format : | 1 vol. (69 p.) / ill. / 29 cm |
| Langues: | Anglais |
| Résumé : |
Information technology has virtually altered every aspect of human life in the present era. The application of informatics in the health sector is rapidly gaining prominence and the bene?ts of this innovative paradigm are being realized across the globe. However, this evolution has a real challenge of how to get maximum out of the patient's data wherever already available, which can employed by high computer technologies such as data mining,deep learning and wearable health technologies, and turned into useful information and knowledge. This data can be used to develop expert systems to save expert clinicians, help in diagnosing some life-threating diseases such as heart diseases and predicting a di?erent diseases before that happening like heart attack, all of this with less cost, processing time and improved diagnosis accuracy by decreasing the number of misdiagnosis.In this study, we have chosen the heart disease as a case of study due to its direct in uence on the human life and the high number of death caused by this type of disease.This study aims to develop a health informatics system for the prediction of heart diseases using data mining, deep learning and wearable health technologies. We worked on the ECG signal and risk factors of the heart state regarding to its capabilities to classify a di?erent heartbeats, some heart diseases based on ECG Arrhythmia and detecting Myocardial Infarction disease as known as heart attack. Data used are gathered from three sources, the ?rst one is the e-Health platform mounted on Raspberry Pi3, which allows to generate and record ECG signals which is a sequence time series, the second source are records provided by Physionet website and the source are patient's life data that are the main risk factors of the heart state similar as heart disease data provided by UCI Machine learning website. We propose in this memory to use CNN, LSTM and k neighbors in the training and testing steps, in order to classify heartbeat types. some CVDs and predict a heart disease. The scored results are quite acceptable, however some adjustments can be introduced to the way of collecting data from patients. Despite this, the trained model still improve high capabilities on classifying heart beat types and Arrhythmias. |
| Sommaire : |
1 introduction 3 1.1 Overview : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.2 Why this title? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.3 Motivation : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.4 Organization of the Thesis : . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2 The State of the Art 10 2.1 Introduction : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.2 Wearable Health Devices Market Trends : . . . . . . . . . . . . . . . . . . 10 2.3 Automatic system and Vital signs (General Works): . . . . . . . . . . . . . 12 2.4 Related works : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.4.1 ECG Denoising : . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.4.2 ECG Heartbeats Classi?cation : . . . . . . . . . . . . . . . . . . . . 15 2.4.3 ECG Arrhythmia Classi?cation : . . . . . . . . . . . . . . . . . . . 16 2.4.4 Heart disease prediction based on DM techniques: . . . . . . . . . . 16 3 Background about heart disease , Data Mining and Deep Learning Tech-niques 17 3.1 Heart : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 3.1.1 The structure of the heart: . . . . . . . . . . . . . . . . . . . . . . . 17 3.1.2 The cardiac cycle : . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.1.3 The process of a Heartbeat : . . . . . . . . . . . . . . . . . . . . . 19 3.2 Cardiac Background : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.3 Heart diseases : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 3.3.1 Myocardial Infarction and heart attack : . . . . . . . . . . . . . . . 22 3.4 Data Mining and Deep Learning : . . . . . . . . . . . . . . . . . . . . . . 23 3.4.1 DM De?nition, Techniques and KDD process : . . . . . . . . . . . 23 3.4.1.1 DM De?nition : . . . . . . . . . . . . . . . . . . . . . . . 23 3.4.1.2 KDD process : . . . . . . . . . . . . . . . . . . . . . . . . 23 3.4.2 DL De?nition and process : . . . . . . . . . . . . . . . . . . . . . . 24 3.4.2.1 DL De?nition : . . . . . . . . . . . . . . . . . . . . . . . 24 3.4.2.2 DL process : . . . . . . . . . . . . . . . . . . . . . . . . . 24 3.4.3 Techniques and Methods Used : . . . . . . . . . . . . . . . . . . . 24 3.4.3.1 Supervised Learning : . . . . . . . . . . . . . . . . . . . . 24 3.4.3.2 Semi-Supervised Learning : . . . . . . . . . . . . . . . . . 25 3.4.3.3 Classi?cation : . . . . . . . . . . . . . . . . . . . . . . . . 25 3.4.3.4 K Neighbors classi?er : . . . . . . . . . . . . . . . . . . . . 25 3.4.3.5 Neural Networks, CNN , AE and LSTM : . . . . . . . . . 26 3.4.3.5.1 Neural Networks: . . . . . . . . . . . . . . . . . . . . . . 26 3.4.3.5.2 Convolutional Neural Networks (CNN) : . . . . . . . . . . 27 3.4.3.5.3 Autoencoders (AE) : . . . . . . . . . . . . . . . . . . . . . 29 3.4.3.5.4 Long short-term memory (LSTM) : . . . . . . . . . . . . . 30 3.5 Conclusion : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4 Conception and Realization 32 4.1 Introduction : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 4.2 Global Vision and Conception: . . . . . . . . . . . . . . . . . . . . . . . . . 32 4.2.1 Global Conception : . . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.3 Detailed conception and realization : . . . . . . . . . . . . . . . . . . . . . 34 4.3.1 Data Selection and Acquisition : . . . . . . . . . . . . . . . . . . . . 34 4.3.1.1 Data Selection : . . . . . . . . . . . . . . . . . . . . . . . . 34 4.3.1.2 Data Acquisition : . . . . . . . . . . . . . . . . . . . . . . 34 4.3.1.2.1 PhysioNet website : . . . . . . . . . . . . . . . . . . . . . . 34 4.3.1.2.2 UCI Machine learning website : . . . . . . . . . . . . . . . 37 4.3.1.2.3 E-Health platform : . . . . . . . . . . . . . . . . . . . . . . 37 4.3.2 Environment of work for the rest of the project : . . . . . . . . . . 42 4.3.2.1 The machine used : . . . . . . . . . . . . . . . . . . . . . . 42 4.3.2.2 The development environment : . . . . . . . . . . . . . . . 42 4.3.3 Pre-processing (ECG Denoising) : . . . . . . . . . . . . . . . . . . . 43 4.3.4 Heartbeats Classi?cation based on 1-D CNN : . . . . . . . . . . . . 43 4.3.4.1 Dataset used and Split : . . . . . . . . . . . . . . . . . . . 43 4.3.4.2 Model Training and validation . . . . . . . . . . . . . . . . 44 4.3.5 ECG Arrhythmia classi?cation : . . . . . . . . . . . . . . . . . . . . 46 4.3.5.1 Detection Myocardial Infarction (MI) Based on LSTM: . . 46 4.3.5.1.1 Dataset used : Exploploration and Split : . . . . . . . . . . 46 4.3.5.1.2 Building the model : . . . . . . . . . . . . . . . . . . . . . 46 4.3.5.2 CVDs Classi?cation : . . . . . . . . . . . . . . . . . . . . . 47 4.3.5.2.1 Dataset used : . . . . . . . . . . . . . . . . . . . . . . . . . 47 4.3.5.2.2 The model : . . . . . . . . . . . . . . . . . . . . . . . . . . 47 4.3.5.2.3 Cleaning data : . . . . . . . . . . . . . . . . . . . . . . . . 48 4.3.5.3 Heart disease prediction based on DM : . . . . . . . . . . 49 4.3.5.3.1 Dataset used : Visualization and Understanding: . . . . . 49 4.3.5.3.2 The model : . . . . . . . . . . . . . . . . . . . . . . . . . . 52 4.4 Our future vision : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 5 Results and discussion : 54 5.1 Introduction : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 5.2 ECG Denoising: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 5.3 ECG Heartbeats classi?cation : . . . . . . . . . . . . . . . . . . . . . . . . 55 5.3.1 Comparison : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 5.4 ECG Arrhythmias Classi?cation : . . . . . . . . . . . . . . . . . . . . . . . 56 5.4.1 Detection Myocardial Infarction (MI) Based on LSTM : . . . . . . 56 5.4.2 CVDs Classi?cation : . . . . . . . . . . . . . . . . . . . . . . . . . . 56 5.5 Heart disease prediction based on DM Techniques: . . . . . . . . . . . . . . 56 6 Conclusion and Future works : 58 6.1 Conclusion : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 6.2 Future works Plan : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 Appendix : 60 .1 Web Application : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 .2 Android Application : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63 Bibliographie 66 |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/440 | Mémoire master | bibliothèque sciences exactes | Consultable |
