Thèse de Doctorat
Permanent URI for this collection
Browse
Recent Submissions
- ItemPartage de Secret en Utilisant des Métaheuristiques Bionispirées(2024) ZENDER RouiaTechnology has progressed a lot in recent decades, especially in terms of computing power and will probably continue to do so in the future, Moore's law is there to support it. This had disastrous repercussions on the information security; although cryptography has also evolved a lot in terms of encryption algorithms, recent supercomputers are capable of overcoming some cryptosystems. This has led researchers in this field to investigate new avenues, such as secret sharing, which over time has proven to be the most secure solution currently used for protecting its secret. The main axis around which revolves the subject of this thesis is precisely this secret sharing paradigm, requiring cooperation and collaboration on the part of secret keepers based on distributed trust and jointly managed control of the security situation.During these last years, various sharing algorithms have been proposed. Indeed, security in the field of IT in general and computer systems in particular have contributed a lot in the evolution of this discipline which belongs to cryptography and which is based on strong theoretical pillars such as: modular arithmetic and coding theory. Contribution in this research work consists of the proposal of a new secret sharing scheme based on bioinspired hexagonal structure and integer decomposition. As a metaheuristic inspiration, hexagonal structure was inspired from nature where it’s common in constructs made by biological systems and the intelligent behaviours of a bee swarm. For integer decomposition, it is known that the oldest method is Fermat’s factorization, which is based on the representation of an odd integer as the difference of two squares, while for the proposed decomposition every positive integer has a unique factorization into two factors. To check functionality and efficiency of the proposed scheme, it was applied to digital images processing domain where it has exhibited good properties: it is lossless and ideal, its flexibility allows many extensions to handle additional situations, it can add new or delete an old participant and it can detect and identify cheater. Aside these interesting features, experimental results demonstrate that this scheme has a good security level.
- ItemUn environnement d'exécution de simulation basé sur le calcul volontaire(2020) KADACHE NABILLe calcul volontaire (CV) est devenu une technique relativement mature de calcul distribué. Son principe consisté a exploiter le temps de repos des machines ordinaires connectées a internet et avec le consentement de leurs propriétaires. Les applications cibles sont généralement des projets scientiques nécessitant un temps et des ressources énormes de calcul. Les plateformes de calcul volontaire existantes soulévent plusieurs dés concernant les diérentes fonctions qui doivent ^etre assurées. Dans une premére partie de notre travail, nous essayons d'apporter des solutions a deux dés inhérents au CV ; Le premier concerne l'implication de volontaires, qui constitue le maillon faible de ce type de systémes. Nous proposons un nouvel environnement de calcul volontaire social (SVCE) intégrant les fonctionnalités récentes de Facebook afin d'impliquer davantage de volontaires. Le deuxiéme probléme, que nous avons abordé, est celui de l'ordonnancement des t^aches dans les systémes de CV. Pour cela, nous proposons un algorithme qui consistéa générer, pour chaque volontaire, un nombre de taches élémentaires dont le cout d'exécutionre éte la capacité de calcul momentanée des ressources disponibles des volontaires, la validité de notre algorithme est illustrée expérimentalement. Dans la deuxiéme partie de notre thése, nous nous penchons sur la simulation distribuée, nous proposons à cet éet un environnement de simulation (VolSIM) qui combine les techniques liées au calcul volontaire àn d'exécuter des simulations qui requiérent des ressources conséquentes.
- ItemMachine Learning Pour La Détection Des Communautés(2024) Wafa LOUAFIThe burgeoning field of social network analysis has garnered considerable attention, with a particular focus on the critical area of community detection. Communities, construed as clusters of closely interconnected nodes with weaker ties to the broader network, play a pivotal role in understanding the evolution of network structures, an essential aspect of network analysis. This thesis conducts a comprehensive exploration into community detection algorithms and unsupervised learning methods, subsequently delving into the application of machine learning techniques in this domain. Two distinct methods are presented: one focused on detecting overlapping communities and the other on identifying disjoint communities. Notably, our methods involve the selection of vital nodes through subgraphs, operating individually on each node, while the clustering process itself occurs globally across the entire network. The implementation leverages various unsupervised machine learning techniques, including hierarchical clustering and k-means, showcasing efficiency and ease of implementation. The standout feature of our methods lies in their demonstrated superiority, achieving enhanced accuracy and performance compared to contemporary methodologies. Substantiating this claim, meticulous evaluations were conducted on both real and synthetic network datasets. Beyond these achievements, the research opens avenues for future exploration in understanding the broader implications and applications of community detection within evolving network structures.
- ItemAutomatic multi-documents text summarization using Binary Biology Migration Algorithm(2024) Mohamed BOUSSALEMAs the World Wide Web continues to expand, the process of identifying pertinent information within its vast volume of documents becomes increasingly challenging. This complexity necessitates the development of efficient solutions, one of which is automatic text summarization; an active research area dedicated to extracting key information from extensive text. The difficulties are further compounded when addressing multi-document text summarization, due to the diversity of topics and sheer volume of information. In response to this issue, this study introduces a novel approach based on swarm intelligence algorithm called biology migration algorithm (BMA). Our proposed approach is; Binary Biology Migration Algorithm for Multi-Document Summarization (BBMA-MDS). Viewing multidocument summarization as a combinatorial optimization problem, this approach leverages the biology migration algorithm to select an optimal combination of sentences. Evaluations of the proposed algorithm's performance are conducted using the ROUGE metrics, which facilitate a comparison between the automatically generated summary and the reference summary, commonly known as the 'gold standard summary'. For a comprehensive evaluation, the well-established DUC2002 and DUC2004 datasets are employed. The results demonstrate the superior performance of the BBMA-MDS approach when compared to alternative algorithms, including firefly and particle swarm optimization, as indicated by the selected metrics. This study thus contributes effectively according to the evaluation to the field by proposing BBMA-MDS as an effective solution for the multi-document text summarization problem.
- ItemUne approche coopérative basée sur l’IoT pour améliorer la qualité du trafic routier(2023-12-21) Tarek Amine HADDADNowadays, automobiles have become very useful for the daily transportation of both people and goods. However, the increase in their numbers has generated a significant rise in demands for the use of road networks, which can lead to delays, traffic congestion, and poor traffic flow, especially in large cities and global metropolises. This type of problem often referred to as road congestion, can be caused by other factors such as road works, accidents, insufficient traffic management, etc. Many strategies to reduce traffic congestion have been adopted by governments and transport agencies. These strategies include building new roads, planning additional public transport routes, real- time traffic management, etc. On the other hand, traffic signal control (TSC) represents one of the modern trends that can play a crucial role in traffic management. It also refers to the management and coordination of traffic lights on road networks in order to effectively control traffic and improve traffic flow. This can involve adjusting the traffic light cycle time based on real traffic to optimize certain performance parameters. Modern TSC systems can adopt technologies such as traffic sensors, surveillance cameras and data processing algorithms to optimize traffic management. Reinforcement learning (RL) is an intelligent approach widely adopted by adaptive TSC systems to optimize traffic signal management, enhancing traffic flow. Indeed, it is possible to train a system to learn how to adjust traffic light cycle times based on the state of real traffic in order to reduce road congestion. In this thesis, we propose several cooperative approaches based on Deep Reinforcement Learning (DRL) to intelligently optimize the management of traffic lights in a road network with multiple intersections. We have thus modeled our problem as a multi-agent reinforcement learning system (MARL). This involves the use of multiple agents each of whom can learn to make decisions in terms of adjusting light cycle times to the local traffic situation, and these decisions can be synchronized with the decisions made by other agents to ensure optimal functioning of the entire system. In such approaches, each agent can receive from its neighbors their states, actions and rewards, combining them with its own state, action and reward to make the appropriate decisions. Experimental results under different scenarios show that the proposed approaches outperform many state-of-the-art approaches in terms of three parameters: Average Waiting Time (AWT), Average Queue Length (AQL) and average CO2 emission (AEC).