AI-Augmented Metasurface Synthesis for Dynamic Beam Steering in Reconfigurable Antenna Arrays by Bostani, Ali

“…As compared to the conventional heuristic methods, for example, genetic algorithms (GA), particle swarm optimization (PSO), the approach based on DRLs has rapid policy convergence, has relatively less computational latency, and is autonomous to adapt to dynamic wireless conditions. …”
Get full text
Get full text

Leveraging UAVs for Coverage in Cell-Free Vehicular Networks by Samir, Moataz

“…Then, we leverage deep reinforcement learning to propose an approach for learning the optimal trajectories of the deployed UAVs to efficiently maximize the coverage, where we adopt Actor-Critic algorithm to learn the vehicular environment and its dynamics to handle the complex continuous action space. …”
Get full text
Get full text
Get full text
Get full text

Privacy-Preserving Fog Aggregation of Smart Grid Data Using Dynamic Differentially-Private Data Perturbation by Fawaz Kserawi (16904859)

“…A significant body of work in the literature employs differential privacy methods with constraining predefined parameters to achieve the optimal trade-off between privacy and utility of the data. …”

UAV-Aided Projection-Based Compressive Data Gathering in Wireless Sensor Networks by Ebrahimi, Dariush

“…We formulate a joint optimization problem and divide it into four complementary subproblems to generate close-to-optimal results with lower complexity. …”
Get full text
Get full text
Get full text
Get full text

3D deployment of UAVs in wireless networks for traffic offloading and edge computing. (c2019) by Islambouli, Rania

“…This being said, computation tasks generated by IoT devices can be pro- cessed in less latency and with much lower energy consumption at the devices. To optimally deploy UAVs as mounted cloudlets, we formulate our problem as mixed integer program and then use an e cient meta-heuristic algorithm to generate optimized results for large scale IoT networks. …”
Get full text
Get full text
Get full text

MoveSchedule by Zouein, Pierette

“…The layout construction algorithm that underlies MoveSchedule uses Constraint Satisfaction to find the set of all positions that meet the constraints on resources' positions and Linear Programming to find the optimal positions that minimize resource transportation and relocation costs. …”
Get full text
Get full text
Get full text

Hybrid deep learning based threat intelligence framework for Industrial IoT systems by Jahanzaib Malik (23718816)

“…The proposed approach was also compared against several contemporary deep learning-based architectures and existing benchmark algorithms. The results indicate that the proposed method achieves superior detection accuracy, with only a minimal compromise in speed efficiency. …”