Projet de Fin d'Études : Mémoire de Master

Permanent URI for this collection

https://dspace.estin.dz/handle/123456789/7

Browse

Now showing 1 - 10 of 10

Predictive maintenance: state of the art based on Machine learning methods
(ESTIN, 2024) BELAYALI Rezkia; OURARI Tinhinane
This study explores the evolving role of machine learning in revolutionizing predictive maintenance (PdM) within Industry 4.0, emphasizing the transition from traditional methods to advanced, data-driven approaches, particularly highlighting deep learning's transformative impact. It examines key technologies such as IoT (Internet of Things) sensors for real-time vibration analysis and addresses the efficacy of data-driven models, stressing the importance of managing data quality. The study also explores state-of-the-art approaches that integrate both single-model and multi-model frameworks, combining machine learning (ML) with physics-based models and statistical techniques. This integrated approach enhances anomaly detection, fault classification, and estimation of remaining useful life (RUL), contributing to a robust PdM framework designed for Industry 4.0 environments. Keywords: Predictive maintenance, industry 4.0, machine learning, single model, multimodel, data-driven, IoT, vibration, RUL, anomaly detection, classification.
Predictive Maintenance: Review of Current Methods and Techniques
(ESTIN, 2024) Asma BOUROUBA; Narima ALKAMA
Achieving operational excellence is crucial for maintaining competitiveness in today’s industrial landscape. Traditional maintenance strategies, both reactive and preventive, often fail to fully utilize the abundant data available. The emergence of Industry 4.0, emphasizing data acquisition and analytics, has introduced predictive maintenance, allowing for real-time insights into equipment health and proactive interventions. Business Intelligence (BI) systems play a central role in this shift by converting raw data into actionable insights, facilitating informed decision-making. This work examines the integration of Natural Language Processing (NLP), probabilistic models, and machine learning techniques in predictive maintenance, offering a comprehensive review of current methodologies. The research highlights how these advanced technologies can improve equipment reliability, reduce downtime, and optimize resource allocation, thereby enhancing production efficiency and profitability. The findings support a transition from traditional maintenance approaches to more proactive strategies, aligning with Industry 4.0 goals and fostering a data-driven, automated industrial environment
Seismic Image Segmentation based on Deep Learning for the Characterization of Hydrocarbon reservoirs in the oil & Gas Industry : Comparative study
(ESTIN, 2024) Anis MOHAMMEDI
Salt Domes are subsurface geological formations critical for hydrocarbon exploration and storage. They often serve as traps for hydrocarbons, significantly contributing to the defining characteristics of reservoirs in the oil and gas industry. Accurately identifying and delineating these structures is essential for efficient resource management. Traditional methods for detecting salt domes rely heavily on manual interpretation, which is timeconsuming and prone to errors. Recent advancements in Deep Learning, particularly in Semantic Segmentation, offer promising solutions to automate and enhance this process. This study explores the application of state-of-the-art Deep Learning models, including Convolutional Neural Networks (CNNs), U-Net architectures, and Transformer-based approaches, for the Semantic Segmentation of Salt Domes in Seismic Images. Generative AI techniques are also examined for data augmentation and enhancing model robustness. The integration of these advanced models aims to improve the precision and reliability of Salt Dome identification, potentially transforming the field of geophysical exploration. Keywords— Salt Domes, Semantic Segmentation, Deep Learning, Generative AI, CNN, UNet, Transformers, Seismic Imaging, Hydrocarbon Exploration
Deep Reinforcement Learning for Vechicle Platooning Optimization
(ESTIN, 2024) Amani Chaimaa Sellam
Automated vehicle platooning has emerged as a significant method for improving traffic efficiency, reducing fuel consumption, and enhancing road safety. This thesis investigates the optimization of vehicle platooning using reinforcement learning techniques, specifically focusing on Deep Q-Networks (DQN) integrated with dueling networks and prioritized experience replay (PER). A two-layered approach is employed, where the first layer identifies joinable platoons and evaluates the benefits of joining them, and the second layer uses reinforcement learning to optimize merging, lane-changing, and acceleration strategies. The results of the simulation demonstrate that the proposed method significantly reduces travel time, fuel consumption, and improves the overall safety of the platooning process. Future work includes extending the model to mixed traffic environments with both autonomous and human-driven vehicles, as well as integrating predictive traffic models. Keywords: Automated vehicle platooning, Deep Q-Networks, Dueling networks, Prioritized experience replay, Reinforcement learning, Traffic efficiency, Fuel
Traffic Management Optimization in the Presence of Automated Vehicles
(Tassadit, 2025-01-25) Cheima MEZDOUR
Traffic congestion on freeways is a significant issue today due to the high volume of vehicles. This congestion impacts traffic flow and can lead to severe delays. Effective traffic management methods and solutions are essential to mitigate this problem and enhance safety for all road users. One specific issue in freeway traffic congestion is the problem of ramp metering. This occurs when vehicles merge from an entrance ramp onto the main freeway. Any malfunction or inefficiency in the traffic light system at these ramps can cause significant congestion and even lead to accidents. By implementing a sophisticated decision-making system that follows a realworld network, we can develop better policies to address this issue. This approach can optimize traffic flow, reduce congestion, and improve overall road safety. We proposed a deep q-learning algorithm to address this problem, which guarantees better learning policies and adapt to changing traffic conditions in real-time, learning optimal actions to take at different states of traffic flow in complex environments. Deep Q-Networks(DQNs) can be used across multiple ramps, so this can improve the scalability of the model. So during this study, we will present the performance of this algorithm compared to traditional systems in improving the efficiency of traffic control.
Literature Review on energy Efficiency Wireless Sensor Net Works
(Tassadit, 2025-01-25) BOUTAOUI Nada
Energy efficiency in WSNs is a problem of resource optimization among sensor nodes that needs to meet the operational constraints for maximum network lifetime and performance. In essence, achieving optimal energy efficiency in WSNs means bing capable of balancing power consumptions, quality of data, and reliability of networks within various deployment scenarios. This issue has become increasingly complicated due to the rapid growth of IoT applications, heterogeneous sensor technologies, and dynamic operation environments. Because of this, it has become a topic of top priority for researchers who are working on the development of proficient methods so that energy management can be done easily and effectively by WSNs operators and designers. The present research work includes a bibliographic study on different approaches followed in WSN energy optimization, focusing on the most recent advances that have incorporated ML and Graph-based techniques. In the following, we will talk about some classic energy-saving approaches, modern ML techniques including Reinforcement Learning (RL), and the potential of Graph Convolutional Networks (GCNs) and Federated Learning (FL) in addressing energy efficiency challenges in WSNs.
Enchancing Adversarial Robustness in Machine Learning: Techniques and Evaluations
(Tassadit, 2025-01-25) Ahmed Yacine Bouchouareb
This master’s report aims to provide a comprehensive review of the literature on the robustness of machine learning models against adversarial attacks. The pri-mary objectives are to explore existing methodologies, highlight key research find-ings, and identify gaps in current knowledge. The report examines autoencoder-based approaches for detecting adversarial examples as well as other defensive techniques such as adversarial training and regularization techniques. Various adversarial crafting methods, such as Fast Gradient Sign Method (FGSM)[10] and Projected Gradient Descent (PGD)[17], are analyzed in depth. The insights gained will serve as a solid foundation for the development of more robust models in future research.
Review of Techniques for Optimizing Intelligent Video Recording Using Activity Detection in Surveillance Systems
(Tassadit, 2025-01-25) MELIZOU Ouassila; TOUATI Hayet
This master thesis presents a comprehensive review of various activity detection methods that can be used in surveillance systems to capture relevant footage. The review encompasses twenty articles, covering a wide range of intelligent video system approaches. The key methodologies examined include background subtraction, optical flow, machine learning techniques such as Support Vector Machines, and deep learning techniques including You Only Look Once, Convolutional Neural Networks, and Faster Region-based Convolutional Neural Networks. Each method is thoroughly explained, with an emphasis on their respective strengths and weaknesses. The analysis provides insights into the current state of the art and identifies potential areas for future research and development in surveillance systems.
State-of-the-Art Analysis : Exploring the Integration of Visual Data for Enhancing the Accuracy and Reliability of Recommender Systems
(Tassadit, 2025-01-25) TOUATI Yanis
This dissertation presents a comprehensive analysis of recommender systems, focusing on the integration of visual data to enhance recommendation accuracy and reliability. Chapter One provides a General introduction to recommender systems, emphasizing their importance in our nowadays technologies. Chapter Two explores the state-of-the-art in recommender systems, discussing various methodologies and advancements, with a particular focus on the incorporation of visual data. The chapter highlights the transformative potential of visual data integration in shaping personalized recommendation experiences across different platforms and domains and then we conclude the study by synthesizing the the summarizing of the State-of-the-Art and the challenges associated with visual data integration.
Recommender systems for multimodal transportation systems in smart cities
(Tassadit, 2025-01-25) Madadi Mounia

Browse

Browsing Projet de Fin d'Études : Mémoire de Master by Issue Date

Results Per Page

Sort Options