Tun-Yao Hung
Papers
1
Total Citations
32
H-Index
1
About
Tun-Yao Hung is a researcher at the forefront of visible light positioning (VLP) systems, where he leverages machine learning to overcome fundamental challenges in indoor localization. His most cited work, "Positioning Unit Cell Model Duplication With Residual Concatenation Neural Network (RCNN) and Transfer Learning for Visible Light Positioning (VLP)" (2021, 32 citations), addresses a critical bottleneck: the trade-off between positioning accuracy and the computational cost of training models across large areas. Hung’s key contribution is a novel framework that divides the space into smaller “positioning unit cells” and uses a residual concatenation neural network (RCNN) combined with transfer learning to efficiently replicate models across cells. This approach dramatically reduces training time and complexity while maintaining high accuracy, a significant advance for practical VLP deployment. His work has been cited by peers exploring deep learning for optical wireless communications and sensor fusion, underscoring its impact on the field. Hung’s research bridges the gap between theoretical ML models and real-world VLP applications, offering a scalable solution that could enable precise indoor navigation for smart buildings, warehouses, and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1