| Titre : | Deep Learning and parallelization of Meta-heuristic Methods |
| Auteurs : | Mohamed Akram Khelili, Directeur de thèse ; Okba Kazar, Auteur ; Sihem Slatnia, Directeur de thèse |
| Type de document : | Thése doctorat |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2022 |
| Format : | 1 vol. (133 p.) / couv. ill. en coul / 30 cm |
| Langues: | Français |
| Résumé : |
Healthcare 4.0 is one of the Fourth Industrial Revolution’s outcomes that make a big revolution in the medical field. Healthcare 4.0 came with more facilities advantages that improved the average life expectancy and reduced population mortality. This paradigm depends on intelligent medical devices (wearable devices, sensors), which are supposed to generate a massive amount of data that need to be analyzed and treated with appropriate data-driven algorithms powered by Artificial Intelligence such as machine learning and deep learning (DL). However, one of the most significant limits of DL techniques is the long time required for the training process. Meanwhile, the realtime application of DL techniques, especially in sensitive domains such as healthcare, is still an open question that needs to be treated. On the other hand, meta-heuristic achieved good results in optimizing machine learning models. The Internet of Things (IoT) integrates billions of smart devices that can communicate with one another with minimal human intervention. IoT technologies are crucial in enhancing several real-life smart applications that can improve life quality. Cloud Computing has emerged as a key enabler for IoT applications because it provides scalable and on-demand, anytime, anywhere access to the computing resources. In this thesis, we are interested in improving the efficacity and performance of Computer-aided diagnosis systems in the medical field by decreasing the complexity of the model and increasing the quality of data. To accomplish this, three contributions have been proposed. First, we proposed a computer aid diagnosis system for neonatal seizures detection using metaheuristics and convolutional neural network (CNN) model to enhance the system’s performance by optimizing the CNN model. Secondly, we focused our interest on the covid-19 pandemic and proposed a computer-aided diagnosis system for its detection. In this contribution, we investigate Marine Predator Algorithm to optimize the configuration of the CNN model that will improve the system’s performance. In the third contribution, we aimed to improve the performance of the computer aid diagnosis system for covid-19. This contribution aims to discover the power of optimizing the data using different AI methods such as Principal Component Analysis (PCA), Discrete wavelet transform (DWT), and Teager Kaiser Energy Operator (TKEO). The proposed methods and the obtained results were validated with comparative studies using benchmark and public medical data |
| Sommaire : |
Contents Abstract . ii Abstract . . . . . . . iii Publications of the author . . . . v List of figures . . . . . . . xiv List of tables . . . . . . xv List of abbreviations . . . . xvi I General introduction 1 1 Context .. . . . . . 1 2 Problem statements . . . 2 3 Contributions . . . 3 4 Thesis Structure . . 6 II Preliminaries and Basic Concepts 8 1 Introduction . . . 8 2 Machine learning . 8 2.1 Supervised Learning . 10 2.2 Unsupervised Learning . . . 10 2.3 Semi-supervised Learning .. 10 2.4 Reinforcement learning . . 11 2.5 Transfer learning . . .. . 11 3 Deep Learning . . . . 11 3.1 Convolutional Neural Network (CNN) 13 3.2 Recurrent Neural Network . 14 3.3 Long short-term memory .. 15 3.4 Generative adversarial network .. . 16 3.5 Restricted Boltzmann Machines 17 3.6 Deep Belief Network . 3.8 Autoencoder . . . 19 3.9 Denoising Autoencoder .. 20 3.10 Stacked (Denoising)Autoencoders 20 4 Metaheuristic . 22 4.1 Complexity Theory . . . . 24 4.1.1 Complexity of Algorithms 24 4.1.2 Big−O notation . 24 4.1.3 Polynomial-time algorithm 25 4.1.4 Complexity of shortest path algorithms 25 4.1.5 Exponential-time algorithm .25 4.1.6 Big−Ω notation . .. . 25 4.1.7 Big−Θ notation . 25 4.2 Complexity of Problems . . . 26 4.2.1 problems of class P . . 27 4.2.2 problems of class NP .. 27 4.3 Categories of Metaheuristics . 28 4.3.1 Single-Solution Based Metaheuristics .28 4.3.2 Population-based Metaheuristics 29 4.4 Types of Metaheuristics . . . . 30 5 Big Data . . . . 31 5.1 Big Data applications. 31 5.1.1 Smart Grid .. 31 5.1.2 E-health . 31 5.1.3 Internet of Things (IoT) . 32 5.1.4 Political services and government monitoring 32 5.1.5 Big Data in healthcare 32 5.2 Big data analytical techniques and technologies in healthcare . . 33 5.3 Challenges in big data analytics in healthcare 34 6 Internet of Things . 35 6.1 IoT technologies 35 6.1.1 Radio-Frequency Identification (RFID) 36 6.1.2 Near Field Communication (NFC)36 6.1.3 Low-Rate Wireless personal area network (LR-WPAN) 36 6.1.4 Bluetooth 36 6.1.5 ZigBee 37 6.1.6 Wireless Fidelity (Wi-Fi) 37 6.1.7 Worldwide interoperability for Microwave Access (WiMAX) 37 6.1.8 Mobile communications . . . . . . . . . . . . . . . . . 38 6.1.9 Wireless sensor networks (WSN) . . 38 6.2 IoT protocols . . . . . . . . . . 39 6.2.1 Constrained application protocol (CoAP) 39 6.2.2 Message queue telemetry transport (MQTT) . 39 6.2.3 Extensible messaging and presence protocol (XMPP) . 40 6.2.4 Low-power wireless personal area networks (LoWPAN) 40 6.2.5 Z-Wave 40 7 Cloud Computing . . . . . . . . . 41 7.1 Types of Cloud computing . . .. . 41 7.2 Services of Cloud computing . . . . 41 7.3 Cloud computing challenges . . .. . 42 7.3.1 Scalable Storage . . . . . . 42 7.3.2 Load Balancing . . . . . . 42 7.3.3 Security . . . . . . . . 42 |
| En ligne : | http://thesis.univ-biskra.dz/5867/1/Khelili_Mohamed_Akram.pdf |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| TINF/179 | Théses de doctorat | bibliothèque sciences exactes | Consultable |
