Ecole Nationale Polytechnique - DSpace

Bienvenue sur la plateforme de diffusion en ligne de la production académique de l'ENP.

Une meilleure accessibilité pour toute la communauté universitaire.

Communities in DSpace

Select a community to browse its collections.

Recent Submissions

  • Thumbnail Image
    Item type:Item,
    Teste
    (2026) safir; Samira,Safir directeur de thèse
  • Thumbnail Image
    Item type:Item,
    Confidentielle.pdf
    (2026) fatima; samira,dir.
  • Thumbnail Image
    Item type:Item,
    Test 2 pour la nouvelle version
    (ENP, 2026) Taleb, Radia Dir. de thèse : Hamlaoui, Fatma Zohra; Hamlaoui, Fatma zohra, Dir. de thèse
    Un essai pour evaluation
  • Thumbnail Image
    Item type:Item,
    Conception d’un Outil de BI Conversationnelle Basé sur le RAG Agentic
    (2026) KERFA Alia; ARKI Oussama, DIR.
    This thesis presents the design and development of an intelligent analytical assistant system based on a multi-agent Agentic RAG architecture. The system enables users to query heterogeneous data sources using natural language. It incorporates semantic schema retrieval mechanisms and a modu- lar reasoning process to automatically generate queries, produce contextualized analyses, and create adapted visualizations. The system was evaluated across four dimensions: schema retrieval quality, query generation ac- curacy, reasoning coherence, and response relevance. The results demonstrate the effectiveness of the Agentic RAG approach for conversational Business Intelligence systems, improving flexibility, adaptability, and overall user experience.
  • Thumbnail Image
    Item type:Item,
    Valorization of non-living microbial biomass for the adsorptive removal of cationic dyes from multicomponent aqueous systems : mechanistic study, DFT adsorption energy analysis, modeling, and machine learning-based optimization
    (2026) Othmani, Amira; Selatnia, Ammar, Directeur de thèse
    This research investigates the valorization of Streptomyces rimosus biomass, an industrial byproduct of antibiotic production, as an eco-friendly biosorbent for the removal of cationic dyes (Basic Blue 41, Basic Red 46, and Basic Yellow 28) from multicomponent aqueous systems. Comprehensive physicochemical characterization confirmed the presence of active functional groups responsible for high adsorption affinity. Adsorption kinetics and isotherms revealed a spontaneous, endothermic, and predominantly chemisorptive process. Density Functional Theory (DFT) analyses correlated adsorption energies and electronic descriptors with experimental performance, elucidating molecular-level interaction mechanisms. Advanced machine learning models, including a Tri-Hybrid DNN–NAS–PSO framework, provided accurate prediction and optimization of adsorption behavior. The study establishes S. Rimosus biomass as a sustainable and efficient biosorbent, offering a circular-economy approach for industrial wastewater remediation.