Naram Mhaisen

TL;DR: This paper first shows that a major cause of the performance drop is the weighted distance between the distribution over classes on users’ devices and the global distribution, and designs a hierarchical learning system that performs Federated Gradient Descent on the user-edge layer and Federated Averaging on the edge-cloud layer.

TL;DR: In this article, the authors proposed an optimized solution for user assignment and resource allocation over hierarchical federated learning (FL) architecture for IoT heterogeneous systems, which is a promising solution for telemonitoring systems that demand intensive data collection, for detection, classification, and prediction of future events, from different locations while maintaining a strict privacy constraint.

TL;DR: Simulation results show that if individual BESSs achieve a certain maximum threshold of exploitability, then the network of distributed Besss is more robust to cyber-attacks in smart contract-defined control.

TL;DR: This paper introduces a general SC-based IoT monitoring framework that can leverage the security features of public blockchains while minimizing the corresponding monetary cost.

TL;DR: This paper first shows that a major cause of the performance drop is the weighted distance between the distribution over classes on users' devices and the global distribution, and designs a hierarchical learning system that performs Federated Gradient Descent on the user-edge layer and Federated Averaging on the edge-cloud layer.