Rihab Saidi

Ms. Rihab Saidi

National school of engineering of gabes, Gabès, Tunisia
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2024 in IEEE Access
Verified
Journal Article
Open access
RSRihab Saidi
Rihab Saidi
IRInes Rahmany
Ines Rahmany
SDSalah Dhahri
Salah Dhahri
TMTarek Moulahi
Tarek Moulahi
This study presents a novel approach for the early diagnosis of prevalent chest diseases, including COVID-19, pneumonia, and lung cancer, utilizing advanced machine learning techniques. The research focuses on addressing the limitations of traditional diagnostic methods by introducing Federated Learning as a collaborative and privacy-preserving solution. By leveraging Federated Learning, stakeholders can collectively develop accurate diagnostic models without directly sharing sensitive medical data, ensuring both privacy and diagnostic accuracy. Furthermore, the study proposes a multi-classification Federated Learning method enhanced by blockchain technology to reinforce data security and privacy. Experimental results demonstrate the effectiveness of this approach compared to centralized models, showcasing comparable performance in terms of accuracy and superior achievement in terms of privacy preservation. The integration of blockchain into the Federated Learning framework holds promise for a robust system prioritizing data privacy and security in the healthcare domain. This innovative combination not only advances machine learning in medical diagnostics but also sets a forward-looking approach for safeguarding patient information in today’s data-driven healthcare landscape.

4 June 2024
Verified
Conference Paper
Closed access
RSRihab Saidi
Rihab Saidi
TMTarek Moulahi
Tarek Moulahi
SASuliman Aladhadh
Suliman Aladhadh
SZSalah Zidi
Salah Zidi
Our innovative federated learning approach addresses the evolving landscape of collaborative machine learning by strategically sharing $80 \%$ of the dataset among decentralized devices. Utilizing TensorFlow Federated and integrating privacy-preserving techniques like differential privacy, our framework seeks to harmonize enhanced model accuracy with robust privacy preservation (20%). Through extensive experiments, we showcase the significant improvement in model accuracy (98.53%) compared to traditional federated learning (97.55%). Analyzing trade-offs between accuracy and privacy preservation, we offer insights into the impact of varied data partitioning ratios and privacy-preserving parameters. This contribution presents an effective methodology for privacy-conscious collaborative model training, unveiling opportunities to optimize federated learning processes and emphasizing the delicate balance between model performance and privacy in collaborative machine learning environments.

22 September 2023
Verified
Book Chapter
Closed access
PDF file
IRInes Rahmany
Ines Rahmany
RSRihab Saidi
Rihab Saidi
TMTarek Moulahi
Tarek Moulahi
MAMutiq Mohammed Almutiq
Mutiq Mohammed Almutiq

30 June 2026 in Machine Learning with Applications
Verified
Journal Article
Open access
RSRihab Saidi
Rihab Saidi
TMTarek Moulahi
Tarek Moulahi
SZSalah Zidi
Salah Zidi
SMSami Mahfoudhi
Sami Mahfoudhi

7 April 2026 in Sustainable Computing: Informatics and Systems
Verified
Journal Article
Closed access
RSRihab Saidi
Rihab Saidi
TMTarek Moulahi
Tarek Moulahi
SZSalah Zidi
Salah Zidi
SMSami Mahfoudhi
Sami Mahfoudhi