Browsing by Author "Reporter: Amraoui, Noureddine"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Studying The Effectiveness of Federated Learning in The Healthcare Domain
    (University of M'sila, 2023-06-10) Bouberra, Thameur; Seghiri, Yassin; Reporter: Amraoui, Noureddine
    Federated Learning (FL) has emerged as a promising approach for training Machine Learning (ML) models in decentralized settings, such as Smart Healthcare Systems (SHSs). Adoption of FL in SHSs provides many advantages especially the preservation of patient’s privacy. This project aims to investigate the effectiveness of FL in the context of SHSs by comparing it with the traditional data-centralized approach. Specifically, four FL strategies are implemented using the Flower framework, with each strategy trained on four different types of datasets: brain tumor, pneumonia, Alzheimer's disease, and COVID-19. The performance of these FL strategies is then compared to that of a data-centralized model trained on the same datasets. Our obtained experimental results reveal that the accuracy of the FL models is in general less than the data-centralized model for all four strategies. Such disparity in accuracy is explained by the challenges associated with decentralized FL learning in SHS settings. Nevertheless, such a small extent of difference can be tolerated considering the benefits of FL brought to SHSs. Thus, we may conclude that there should be a trade-off between high accuracy and FL advantages.
  • Thumbnail Image
    ItemOpen Access
    A University Recommender System based on Students Profiles
    (University of M'sila, 2023-06-10) Barka, Wafa; Bouarbi, Mounya; Reporter: Amraoui, Noureddine
    Although universities are known for their pursuit of knowledge and research, they do not fully exploit the potential of the vast amounts of data they generate and collect. One consequence of this is that future students face a daunting university selection process. This work aims to devise a Recommender System (RS) that can automatically propose the best universities for students which can simplify their selection process and raise their chances of admission. To evaluate the effectiveness and feasibility of our proposed RS, we collect relevant data from various sources. This data includes student profiles, academic qualifications, preferences, and other factors. We analyze this data to evaluate the performance of our recommender system and its ability to generate accurate and useful recommendations. Our obtained results show that our University RS is in average effective in generating personalized recommendations based on three powerful algorithms, namely, K-Nearest Neighbors (KNN), Random Forest, and Support Vector Machine (SVM).