Efficient Transformer-based Hyper-parameter Optimization for Resource-constrained IoT Environments

1 code implementation • 18 Mar 2024 • Ibrahim Shaer, Soodeh Nikan, Abdallah Shami

The hyper-parameter optimization (HPO) process is imperative for finding the best-performing Convolutional Neural Networks (CNNs).

Reinforcement Learning (RL)

Thwarting Cybersecurity Attacks with Explainable Concept Drift

no code implementations • 18 Mar 2024 • Ibrahim Shaer, Abdallah Shami

The results show that FDE successfully identifies 85. 77 % of drifting features and showcases its utility in the DL adaptation method under the CD phenomenon.

CorrFL: Correlation-Based Neural Network Architecture for Unavailability Concerns in a Heterogeneous IoT Environment

1 code implementation • 22 Jul 2023 • Ibrahim Shaer, Abdallah Shami

The generated CorrFL models for the unavailable IoT device from the available ones trained on the new environment are compared against models trained on different use cases, referred to as the benchmark model.

Federated Learning

Sound Event Classification in an Industrial Environment: Pipe Leakage Detection Use Case

no code implementations • 5 May 2022 • Ibrahim Shaer, Abdallah Shami

An extensive experimental procedure was carried out on two datasets, one with background industrial noise and one without, to evaluate the validity of the proposed pipeline.

feature selection

Concept Drift Detection in Federated Networked Systems

no code implementations • 13 Sep 2021 • Dimitrios Michael Manias, Ibrahim Shaer, Li Yang, Abdallah Shami

As next-generation networks materialize, increasing levels of intelligence are required.

Dimensionality Reduction Federated Learning