ASSOCIATE PROFESSOR, PhD, P. Eng, SMIEEE
Electrical Engineering and Computer Science
Lassonde School of Engineering
York university, Toronto, Canada
Office: LAS-2008
Phone: (416) 736-2100, ext. 20889
Email: hinat@yorku.ca
NGWN research lab is led by Dr. Hina Tabassum. She is currently an Associate Professor in the Department of Electrical Engineering and Computer Science (EECS), York University, Toronto, Canada, and Visiting Faculty at University of Toronto (2024-2025). She is appointed as York research Chair (2023 - 2028) in 5G/6G-enabled mobility and sensing applications. She is listed in Stanford’s top 2% of the world’s top researchers in 2021, 2022, 2023, and 2024. She has been selected as IEEE ComSoc Distinguished Lecturer for the class of 2025-2026!
She was recognized as one of the 10 Rising Stars in “N2Women: Rising Stars in Networking and Communications List” in 2022 and received Lassonde Innovation Award in 2023. She (co)-authored 90+ articles in top-tier IEEE journals, magazines, and conferences. She was the Founding Chair of IEEE ComSoc RCC Special Interest Group (SIG) on Terahertz Communications (2021-2023) and served as the Chair of Women in Computer Science and Engineering (WiCSE), York University, (2018-2020). She was a Research Associate in the area of "Modeling, Analysis, and Optimization of 5G Networks" at Department of Electrical and Computer Engineering, University of Manitoba, Canada, under the supervision of Prof. Ekram Hossain. She obtained her PhD in the area of "Interference Modeling and Management of Heterogeneous Wireless Communication Networks", in June 2013, under the supervision of Prof. Mohamed Slim Alouini. She received Bachelors of Electronics Engineering from NED University of Technology (NEDUET) and secure First Position among all engineering universities of Karachi, Pakistan for which she received Gold medals from NEDUET and from SIEMENS. She then joined R&D at Pakistan Space and Upper Atmosphere Research Commission (SUPARCO) and received Best Performance Award in 2009.
She is a registered member of
Center for AI and Society (CAIS), and
Mobility Innovation Center (MOVE) at York University
She is currently a Co-PI on the following two NSERC CREATE initiatives:
SMART (Smart Mobility Advanced Research & Training) [2024 -2030] ($1.65 M)
GMD-MSTI (Geomagnetic Disturbance in Modern Societies and Technological Infrastructures) [2025-2031] ($1.65 M).
She was recognized as Exemplary Reviewer (Top 2% of all reviewers) by IEEE Transactions on Communications in 2015, 2016, 2017, 2019, and 2020. She was recognized as Exemplary Editor by IEEE Communications Letters in 2020, and Exemplary Editor by IEEE Transactions on Green Communications and Networking in 2023, and Best Editor by IEEE Open Journal on Communications Society in 2023.
She served as an Associate Editor in IEEE Open Journal of Communications Society (IEEE OJCOMS) (2019 - 2023), in IEEE Transactions on Green Communications (IEEE TGCN) (2020 - 2023), Associate Editor in IEEE Communications Surveys and Tutorials (IEEE COMST) (Sep 2021 -Aug 2025), and in IEEE Communications Letters (IEEE COMML) (2019 - 2023) . She is currently serving as
Area Editor in IEEE Communications Surveys and Tutorials (IEEE COMST) (Aug 2025 -)
Area Editor in IEEE Open Journal of Communications Society (IEEE OJCOMS) (June 2023 -)
Associate Editor in IEEE Transactions on Mobile Computing (IEEE TMC) (Feb 2025 -)
Associate Editor in IEEE Transactions on Wireless Communications (IEEE TWC) (Nov. 2023 -)
Associate Editor in IEEE Transactions on Communications (IEEE TCOM) (June 2022 -)
Research Themes and Corresponding Research Articles
Wireless sensing is a process of collecting and analyzing wireless channel state information (CSI) or received signal strength indicator (RSSI) to capture environment dynamics and enable various sensing services such as
human activity recognition
vital signs monitoring
indoor localization
motion sensing
Fall detection and crowd counting
Deep learning methods offer a solution to learn hidden CSI patterns and perform human activity recognition, indoor localization, and motion sensing.
We introduce a novel multi-objective integrated sensing and communications (ISAC) framework to enable collaborative wireless sensing in conjunction with over-the-air federated-edge learning (OTA-FEEL). The framework enables multi-task OTA aggregation to handle sensing and learning simultaneously, while benefiting from dual-purpose uplink signals for both communications and target sensing. Numerical results demonstrate that the proposed dual-purpose OTA-FEEL-enabled collaborative ISAC framework enhances sensing accuracy without adversely affecting the performance of the primary OTA-FEEL task. While conventional single-shot collaborative sensing schemes are limited by the average error of local estimators, the proposed algorithm achieves the CRB of the considered problem.
EMForecaster is a novel deep learning architecture designed for forecasting electromagnetic field exposure. It leverages multi-scale temporal pattern processing through patching, reversible instance normalization, and dimension mixing. To quantify uncertainty, it integrates conformal prediction, ensuring a guaranteed coverage rate of 1−α. Additionally, it introduces a 'Trade-off Score' metric that balances forecast reliability with the width of prediction intervals. EMForecaster outperforms existing methods significantly—achieving 53.97% improvement over the Transformer model and 38.44% over the average baseline in point forecasting. In conformal forecasting, it delivers an optimal balance between interval width and coverage, surpassing the average baseline by 24.73% and the Transformer by 49.17% [https://github.com/xmootoo/emforecaster]
We introduce a novel unsupervised learning framework for solving constrained optimization problems with non-convex constraints. Central to our approach is a differentiable projection function that ensures zero constraint violation by mapping outputs directly onto the feasible solution space. By integrating this projection mechanism with a custom neural network and unsupervised training, our method effectively optimizes the primary objective. Applied to wireless network optimization, the framework demonstrates superior performance, faster convergence, and greater computational efficiency compared to genetic algorithms and existing projection-based techniques—all while consistently maintaining perfect constraint satisfaction. This generalizable approach offers a compelling solution for complex optimization problems where traditional methods often fall short in enforcing constraints and achieving high-quality results.
We developed integrated 5G network – highway simulation testbed. We developed multi-objective reinforcement learning framework for joint network selection and speed optimization in a multi-band RF/THz network with known and unknown transportation and telecommunication preferences.
From traffic engineering perspective, it is critical to:
Optimize the speed of vehicles to maximize the traffic flow and minimize collisions. Higher speeds imply better traffic flow but increase collisions.
From communication engineering perspective, it is crucial to:
Optimize the speed of vehicles to maximize the data rates and minimize handoffs. Higher speeds imply more handoffs and reduced data rates.
Recent Updates and Activities: Tutorials, Panels, and Talks