http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/16 Sun, 15 Mar 2026 05:32:06 GMT 2026-03-15T05:32:06Z http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1316 Titre: Medical Image Segmentation Based on Artificial Intelligence Approaches Auteur(s): Mokhtari, chakir Résumé: Medical image segmentation is a critical preprocessing step in computer-aided diagnosis, treatment planning, and biomedical research. While Fuzzy C-Means (FCM) clustering is a widely adopted technique for this task due to its ability to handle inherent ambiguities in medical data, its performance is highly sensitive to initial parameters and is prone to convergence to local optima. This thesis presents a comprehensive approach to overcoming these limitations through two primary contributions. First, we provide an overview of medical imaging and the fundamental challenges of segmentation. We then detail traditional clustering-based methods, with a specific focus on the FCM algorithm, outlining its strengths and well-documented limitations. To address these limitations, we explore bio-inspired optimization metaheuristics as a powerful strategy for guiding the clustering process. The core contribution of this work is the novel hybridization of the Artificial Bee Colony (ABC) algorithm with FCM. The proposed method focuses on the simultaneous optimization of the crucial FCM parameters: primarily the number of cluster centers and their values and the optimization of the objective function by escaping to the local optima, to achieve a superior and more robust segmentation outcome. The effectiveness of this hybrid ABC-FCM approach is rigorously validated through experiments on both simulated brain MRI and real clinical MRI brain images. Results demonstrate a significant improvement in segmentation accuracy and convergence behavior compared to standard FCM and other optimization-enhanced variants. The second major contribution is the development of a new cluster validity index (CVI) to automatically determine the optimal number of segments. This index is designed to enhance the separation metric of the IMI index by incorporating a measure based on Kullback-Leibler (KL) divergence, which better captures the statistical distance between fuzzy clusters. Experimental results confirm that the proposed KL-based CVI outperforms existing indices in accurately identifying the true number of clusters in both synthetic and complex medical imagery. This thesis offers significant advancements in AI-driven medical image segmentation by introducing an optimized clustering framework and a more robust validation metric, both contributing to higher diagnostic reliability. Wed, 15 Oct 2025 00:00:00 GMT http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1316 2025-10-15T00:00:00Z http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1293 Titre: Contribution à la reconnaissance hors ligne de l'écriture arabe manuscrite Auteur(s): Chadli, Mohamed Amine Résumé: Offline Arabic Handwritten Text Recognition (HTR) is an important research area. Contributing to its development may have significant and exciting implications for many Arabic-speaking countries, where Arabic is the official spoken and written language. This thesis has examined the Arabic handwritten language, its characteristics, and the challenges of recognizing its written script. We conducted thorough literature reviews on classical and modern deep learning methods for recognizing Arabic script. We delve deep into the resources used to train the Arabic HTR systems, trying to extract all the known databases of Arabic handwritten text. We also investigated the data augmentation approaches used to enrich the handwritten Arabic text databases with new data. Later, we proposed a new deep learning architecture based on Convolutional Recurrent Neural Network (CRNN) to recognize offline Arabic scripts. As a final contribution, we proposed a new data augmentation technique based on Moving Least Squares (MLS), specifically designed to generate new images of Arabic handwritten text to serve as training data for deep learning systems. Thu, 17 Jul 2025 00:00:00 GMT http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1293 2025-07-17T00:00:00Z http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1292 Titre: Energy-Constrained Resource Allocation and Scheduling in Cloud Computing Auteur(s): Mehor, Yamina Résumé: In virtualized cloud computing systems, energy reduction is a major concern since it can provide many major benefits, such as reducing operating costs, increasing system efficiency, and protecting the environment. Typically, customers submit their appli- cations with millions of tasks executed in cloud data centers by thousands of high- performance servers installed. The cloud offers a variety of services through virtual machines (VMs). These latter usually consume a large amount of energy. Such energy consumption increases the cost of electricity and has a negative environmental effect. To maintain a better performance of the services offered by data centers and a reason- able energy consumption. A detailed study of the behavior of these systems is essential for the design of efficient optimization solutions to reduce energy consumption. This thesis work focuses on the development of a task scheduling model in order to minimize the energy consumption of data center resources while meeting customer requirements for quality of services. Thu, 17 Jul 2025 00:00:00 GMT http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1292 2025-07-17T00:00:00Z http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1261 Titre: Distributed system for image segmentation based on parallel metaheuristics Auteur(s): Mezaghrani, Ali Résumé: In recent years, the integration of distributed systems with parallel processing techniques has significantly advanced the field of image processing. Distributed systems enable the efficient handling of large datasets by dividing the computational tasks across multiple nodes, improving both speed and scalability. Parallelization in image processing enhances performance by executing multiple tasks simultaneously, making it possible to process high- resolution images and complex datasets in real time. Metaheuristic algorithms have been widely adopted for optimization tasks in image processing due to their ability to explore large search spaces effectively. These algorithms, when coupled with machine learning (ML) models, provide powerful solutions for feature selection in classification tasks. Metaheuristics help identify the most relevant features from large datasets, thereby enhancing the classification performance of ML models. Further, parallel metaheuristics, deployed in a distributed environment, can optimize image segmentation processes by splitting the task across multiple computational units, thereby speeding up the process while maintaining or improving segmentation accuracy. Bearing those in mind, we propose in this thesis, four hybrid methods focusing on feature selection, classification, and parallel image segmentation. The first method employs Grey Wolf Optimization (GWO) for selecting the most relevant features, followed by a Random Forest (RF) classifier to perform accurate classification. The second method integrates Correlation-based filtering with GWO to enhance the feature selection process, and applies various machine learning classifiers for comparative performance analysis. For parallel image segmentation, we designed two parallel approaches to improve efficiency and accuracy. The first is a Parallel Whale Optimization Algorithm (WOA) combined with K-Means clustering, implemented using multiprocessing to accelerate the segmentation process. The second method uses Grey Wolf Optimization in combination with Fuzzy C-Means (FCM), leveraging GPU acceleration for parallel execution. This approach significantly reduces computational time while maintaining high segmentation quality. All methods are evaluated using standard performance metrics. Our aim is to demonstrate the effectiveness of parallel metaheuristics and hybrid selection-classification strategies in medical image analysis. In conclusion, this thesis shows that combining parallel computing, metaheuristic optimization, and machine learning offers an effective, accurate, and scalable solution to challenges in medical image analysis, contributing to the development of next-generation diagnostic systems. Sun, 22 Jun 2025 00:00:00 GMT http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1261 2025-06-22T00:00:00Z