Browsing by Author "Debbi, Hichem: Supervisor"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    A Web-based Platform for Healthcare with Different Services
    (University Mohamed Boudiaf of M’sila, Faculty of Mathematics and Informatics, Department of Computer Science, 2024-06) Ben Dahmane, Dhiya El Haq; Kouriche, Oussama; Debbi, Hichem: Supervisor
    Healthcare management systems revolutionize patient care by replacing paper charts with digital records, allowing doctors instant access to comprehensive patient histories. These platforms also empower patients, enabling them to schedule appointments online and review their medical data securely. In the rapidly evolving technological landscape, new architectures and approaches have emerged to address the limitations of traditional systems. Multi-tenancy architectures have become a necessity, providing added architectural value for companies with virtualized systems (Cloud, Fog, Edge, etc.) and a valuable skill set for engineers and developers. To address the ambiguity surrounding this architectural trend, our contribution to this work (focused on application rather than research) is based on the use of the highest degree of multitenancy architecture, "unique database," when designing and building a Cloud Software-as-aService (SaaS) application. This approach aims to demystify the conceptual and programming complexities associated with this architectural trend, leveraging a SaaS application tailored for healthcare establishments that supports the demands of its tenants. To realize this distinguished multi-tenant SaaS application, the Laravel Framework has been targeted in this thesis. By adopting a multi-tenancy architecture with a unique database, the proposed healthcare cabin management platform offers a scalable and efficient solution for healthcare providers.
  • Thumbnail Image
    ItemOpen Access
    On the detection of pneumonia using deep learning and explainability
    (University Mohamed Boudiaf of M’sila, 2024-06) Chaa, Amina; Dilmi, Noussaiba; Debbi, Hichem: Supervisor
    Pneumonia detection from chest X-ray images is achieved using the pre-trained VGG16 deep learning model, known for its ability to extract relevant features from images. The process involves feeding the X-ray images into the VGG16 model, which then analyzes and classifies them to detect signs of pneumonia. To build trust in the model’s decisions, explainability techniques such as Causal Explanation CNN (CexCNN) and CAM are employed. These techniques provide visual explanations by highlighting the regions of the X-ray images that the model focuses on when making its predictions. CexCNN offers casual robust explanations, indicating which features are most influential in the decision-making process, thus leading to gain confidence in the CNN model. Which is very crucial especially in the medical field.