Scholar
Steve Drew
Google Scholar ID: mGMBNN4AAAAJ
Assistant Professor at University of Calgary
Citations & Impact
Citations
559
H-index
14
i10-index
17
Publications
20
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - Paper “UltraMotion: High-precision Ultrasonic Arm Tracking for Real-world Exercises” accepted for publication in IEEE Transactions on Mobile Computing.
- - Paper “FedLE: Federated Learning Client Selection with Lifespan Extension for Edge IoT Networks” accepted for presentation at 2023 IEEE International Conference on Communications.
- - Paper “USDNL: Uncertainty-based Single Dropout in Noisy Label Learning” accepted for publication at Thirty-Seventh AAAI Conference on Artificial Intelligence.
- - Guided a student team to win 3rd place in the CANIS Hackathon for Data Visualization.
- - Collaborated with Illidan Lab at Michigan State University to win 3rd place in the U.S. Privacy-enhancing Technologies Prize Challenge.
Research Experience
- - Founded DENOS Lab, focusing on developing federated learning methods to address challenges posed by infrastructure heterogeneity.
- - Investigating how carefully designed FL methods can guide cloud-edge service orchestration to tackle issues like model performance degradation and longer convergence times.
- - Exploring the use of federated learning to handle missing data, interoperability, and fairness in EHRs.
Background
- Founder of the Distributed Edge Learning and Orchestration Systems (DENOS) Lab; research interests include federated learning for edge service orchestration and federated learning on electronic health records.
