Shao-Hua Song
Papers
1
Total Citations
32
H-Index
1
About
Shao-Hua Song is a leading researcher in visible light positioning (VLP) systems, where his work bridges optical communication and machine learning to achieve unprecedented indoor localization accuracy. His most influential contribution, the development of a Residual Concatenation Neural Network (RCNN) with transfer learning for VLP, has garnered 32 citations and fundamentally advanced how positioning unit cells are modeled. By innovatively duplicating unit cell models and applying residual concatenation architectures, Song dramatically reduces the training time and computational complexity that previously plagued large-area VLP deployments. His approach enables practical, high-precision positioning without the need for exhaustive data collection across every cell, solving a critical bottleneck in the field. This work has been recognized as a cornerstone for scalable indoor positioning systems, influencing subsequent research in both optical wireless communications and deep learning for localization. Song’s contributions are particularly notable for their direct applicability to smart environments, autonomous navigation, and IoT infrastructure, where his methods continue to shape the trajectory of visible light-based positioning technologies.
Research Focus
Key Achievements
Top Papers
- 1