Doctorat Recherche Opérationnelle
Permanent URI for this collectionhdl:123456789/1390
Browse
2 results
Search Results
Item Using Multi-objective Meta-heuristics for Data Mining(university of bordj bou arreridj, 2025-01-05) Soumaia KAHLOULThe ability to extract knowledge from large datasets is essential for innovation and informed decision-making, a process known as knowledge extraction or data mining. Traditional methods often fall short in fully utilizing data potential, necessitating the development of new algorithms for better insights. This thesis explores an innovative approach by integrating deep learning with advanced feature selection techniques to improve the classification accuracy of COVID-19 cases from chest X-ray images. The dataset includes X-ray images categorized as COVID-19, pneumonia, and normal. We employ the Binary Multi-Objective Henry Gas Solubility Optimization Algorithm (B-MOHGSO) for feature selection and leverage models like AlexNet, VGG19, GoogleNet, and ResNet for feature extraction. Eight versions of B-MOHGSO were tested, with k-nearest neighbors (k-NN) as the classifier. The study highlights the significant impact of S-shaped and V-shaped transfer functions on binary transformations and classifier performance in high-dimensional medical imaging. Notably, B-MOHGSO algorithms, particularly those using V-shaped transfer functions, excelled in selecting relevant features while maintaining high accuracy. When combined with the VGG19 model and SVM classifier, B-MOHGSO significantly reduced the feature set without sacrificing performance. The application of B-MOHGSO in COVID-19 classification is crucial for identifying key features that enhance diagnostic processes and treatment strategies. By adapting MOHGSO for discrete optimization, this research aims to address the complexities of high-dimensional medical data and improve healthcare analytics outcomes.Item Multi-objective Optimization for Supply Chain Management(Université de Bordj Bou Arreridj Faculty of Mathematics and Computer Science, 2024-02-22) Hemici, MeriemThe research activity of this research falls under two major themes: multi objective optimization and supply chain management (SCM). Multiobjective optimization is a branch of combinatorial optimization whose specificity is to seek to optimize several objectives simultaneously for the same problem. As a result, the use of multi-objective optimization methods allows companies to use optimal strategic solutions to optimize and improve the quality of deci sions for SCM. In this thesis, we proposed three new multi-objective evolutionary algorithms to solve three important problems in SCM where our attention was focused on the part related to transportation and distribution problems, namely the vehi cle routing problem with time windows, the multi-depot green vehicle routing problem, and the ambulance relocation and dispatching problem. The first algorithm called External Archive Guided Nondominated Sorting Ge netic Algorithm II (EAG-NSGA-II) is based on improving the NSGA-II algo rithm by integrating the local search method and an external population called “archive” to store the non-dominated solutions to solve the multi-depot green vehicle routing problem. While in the second algorithm, an improved MOEA/D algorithm using simulated annealing (SA) was proposed to solve the ambu lance relocation and dispatching problem. In the last algorithm, a new evolu tionary algorithm was developed by combining the ϵ-MOEA algorithm, local search method, and multi-type crossover operators to solve the vehicle routing problem with time windows. After being tested, the proposed algorithms have shown encouraging results in both solving the vehicle routing problem with time windows, the multi-depot green vehicle routing problem, and the ambulance relocation and dispatching problem, and have been found to be more efficient compared to many multi objective evolutionary algorithms.