Papers
1
Total Citations
1
H-Index
1
About
Woo-Jin Han is a pioneering researcher at the intersection of edge AI, federated learning, and resource-constrained robotics. His work fundamentally addresses the computational and privacy bottlenecks of traditional deep neural networks in mobile systems. His most cited paper, "Hyperdimensional Computing-Based Federated Learning in Mobile Robots Through Synthetic Oversampling" (2025, 1 citation), introduces a groundbreaking framework that replaces power-hungry neural networks with hyperdimensional computing—a brain-inspired, lightweight paradigm. This approach enables efficient, privacy-preserving collaborative learning among mobile robots while using synthetic oversampling to handle data imbalance, a critical challenge in real-world deployment. Though early in its citation trajectory, this work signals a paradigm shift for swarm robotics and IoT devices, where energy and bandwidth are scarce. Han’s contributions are particularly notable for bridging the gap between theoretical efficiency and practical robotics, offering a scalable alternative to conventional federated learning. His research is poised to influence next-generation autonomous systems, from warehouse drones to environmental monitors, by making on-device intelligence both feasible and secure.
Research Focus
Key Achievements
Top Papers
- 1