Norah Alrusayni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Norah Alrusayni has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Asma Abdulghani Al-Shargabi
Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia
1 shared publication - Mohammed Abdullah Al-Hagery
Department of Computer Science, College of Computer, Qassim University, Buraydah, Saudi Arabia
1 shared publication - Reem Almutiri
Qassim University
1 shared publication - Sarah Alhumud
Qassim University
1 shared publication - Sarah K. Alhabeeb
Qassim University
1 shared publication
Latest Publications
- Open Access
- 17 April 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (4) , 213
Heterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) Edge–Cloud Inference in IoT Environments
In resource-constrained environments, distributed split learning allows for collaborative training; however, the system suffers from high communication overhead and is sensitive to system heterogeneity. Despite advances in IoT data reduction and distributed learning, existing approaches treat heterogeneity, adaptability, and communication efficiency as separate problems. As a result, the Heterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) framework is proposed, enabling adaptive adjustment of communication payloads to instantaneous bandwidth conditions during training. This approach distinguishes itself by focusing on feature-representation-level adaptation, offering seamless transitions between linear PCA, nonlinear Tiny Autoencoder (TinyAE), and hybrid PCA–AE compression methods without requiring changes to architecture or retraining. Experiments were conducted using the CIFAR10 and CI=NIC datasets with a lightweight ResNet-18 backbone under Dirichlet-based non-IID data partitioning and fluctuating network scenarios. HADFL-AC achieves significant communication reductions of 80.86% on CIFAR-10 and 77.2% on CINIC-10, as well as significant reductions in training time and energy consumption. In addition, the framework achieved these gains while maintaining competitive performance, reaching 79.58% on CIFAR-10 and exhibiting stable convergence on CINIC-10. Consequently, the results demonstrate that leveraging network heterogeneity as an adaptive signal facilitates efficient and scalable distributed learning while effectively balancing communication efficiency and model accuracy.
- 17 April 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (4) , 213
Open AccessHeterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) Edge–Cloud Inference in IoT Environments
In resource-constrained environments, distributed split learning allows for collaborative training; however, the system suffers from high communication overhead and is sensitive to system heterogeneity. Despite advances in IoT data reduction and distributed learning, existing approaches treat heterogeneity, adaptability, and communication efficiency as separate problems. As a result, the Heterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) framework is proposed, enabling adaptive adjustment of communication payloads to instantaneous bandwidth conditions during training. This approach distinguishes itself by focusing on feature-representation-level adaptation, offering seamless transitions between linear PCA, nonlinear Tiny Autoencoder (TinyAE), and hybrid PCA–AE compression methods without requiring changes to architecture or retraining. Experiments were conducted using the CIFAR10 and CI=NIC datasets with a lightweight ResNet-18 backbone under Dirichlet-based non-IID data partitioning and fluctuating network scenarios. HADFL-AC achieves significant communication reductions of 80.86% on CIFAR-10 and 77.2% on CINIC-10, as well as significant reductions in training time and energy consumption. In addition, the framework achieved these gains while maintaining competitive performance, reaching 79.58% on CIFAR-10 and exhibiting stable convergence on CINIC-10. Consequently, the results demonstrate that leveraging network heterogeneity as an adaptive signal facilitates efficient and scalable distributed learning while effectively balancing communication efficiency and model accuracy.
- Open Access
- 1 March 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (1) , 581-596
Blockchain and machine learning in education: a literature review
There is a growing influence around the use of technology in education, with many solutions already being implemented and many others being explored. Using various forms of technology to assist the educational process has increased dramatically in the previous decade in education systems in many respects. Both machine learning and the blockchain have had a significant impact on education. The purpose of this study is to conduct a literature review on the application of machine learning and blockchain technology in educational institutions. Additionally, this study examines the potential applications, benefits, and challenges those educational institutions may face as a result of using machine learning and blockchain technologies. Using machine learning and blockchain in educational systems will have a positive impact on the entire educational process and student achievement. Researchers, academics, and practitioners will benefit from this study to focus on a wider range of educational applications and solve the related issues of machine learning and blockchain technology in the education sector.
- 1 March 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (1) , 581-596
Open AccessBlockchain and machine learning in education: a literature review
There is a growing influence around the use of technology in education, with many solutions already being implemented and many others being explored. Using various forms of technology to assist the educational process has increased dramatically in the previous decade in education systems in many respects. Both machine learning and the blockchain have had a significant impact on education. The purpose of this study is to conduct a literature review on the application of machine learning and blockchain technology in educational institutions. Additionally, this study examines the potential applications, benefits, and challenges those educational institutions may face as a result of using machine learning and blockchain technologies. Using machine learning and blockchain in educational systems will have a positive impact on the entire educational process and student achievement. Researchers, academics, and practitioners will benefit from this study to focus on a wider range of educational applications and solve the related issues of machine learning and blockchain technology in the education sector.