Fahmida Afrin

Fahmida is a Ph.D. candidate in Wireless Communications and Machine Learning at Old Dominion University, with over 7 years of combined academic and research experience in the United States.

Her work lies at the intersection of machine learning, spectrum management, and spectrum sensing in 5G/6G communication systems, where she designs intelligent frameworks to enable reliable coexistence between next-generation wireless networks and radar systems.

Throughout her research journey, Fahmida has worked extensively with MATLAB 5G Toolbox, Python-based signal processing, and Graph Neural Networks (GNNs) to model, simulate, and analyze mid-band (3.5 GHz CBRS) interference scenarios.

Her research has resulted in IEEE-published findings on low-SNR signal classification using advanced GNN and CNN architectures.

Some of Fahmida's recent contributions include: -Developing multi-scale GNN models for robust signal classification under high-interference conditions. -Designing ResGCN-based RF fingerprinting frameworks, improving IoT device authentication accuracy by 62% over traditional CNN baselines. Recognized through DoD and NSF-funded initiatives, my research supports the U.S. mission of secure, spectrum-efficient 5G/6G deployment, benefiting both defense and commercial communications infrastructure.

She is passionate about advancing ML-driven signal intelligence and wireless innovation to build resilient, data-driven networks. 

Fahmida's CV: https://sics-c.org/wp-content/uploads/Resume_Afrin.pdf