Addressing Data Distribution Shifts in Online Machine Learning Powered Smart City Applications Using Augmented Test-Time Adaptation

no code implementations • 2 Nov 2022 • Shawqi Al-Maliki, Faissal El Bouanani, Mohamed Abdallah, Junaid Qadir, Ala Al-Fuqaha

Data distribution shift is a common problem in machine learning-powered smart city applications where the test data differs from the training data.

Test-time Adaptation

Budgeted Online Selection of Candidate IoT Clients to Participate in Federated Learning

no code implementations • 16 Nov 2020 • Ihab Mohammed, Shadha Tabatabai, Ala Al-Fuqaha, Faissal El Bouanani, Junaid Qadir, Basheer Qolomany, Mohsen Guizani

In this work, we solve the problem of optimizing accuracy in stateful FL with a budgeted number of candidate clients by selecting the best candidate clients in terms of test accuracy to participate in the training process.

Federated Learning

Large Intelligent Surface Assisted Non-Orthogonal Multiple Access: Performance Analysis

no code implementations • 19 Jul 2020 • Lina Bariah, Sami Muhaidat, Paschalis C. Sofotasios, Faissal El Bouanani, Octavia A. Dobre, Walaa Hamouda

Specifically, we consider a downlink NOMA system, in which data transmission between a base station (BS) and $L$ NOMA users is assisted by an LIS comprising $M$ reflective elements.