Yun-Han Chang
Papers
2
Total Citations
45
H-Index
2
About
Yun-Han Chang is a leading researcher in visible light positioning (VLP) systems, where they have pioneered the integration of advanced machine learning techniques to solve real-time indoor tracking challenges. Their work focuses on enhancing positioning accuracy for critical applications including augmented reality, autonomous mobile robots, and Internet-of-Things services. Chang's most impactful contribution, "Positioning Unit Cell Model Duplication With Residual Concatenation Neural Network (RCNN) and Transfer Learning for Visible Light Positioning (VLP)" (2021, 32 citations), introduced an innovative approach that dramatically reduces training time and computational complexity by dividing large areas into positioning unit cells. This work has become foundational for efficient VLP system design. More recently, Chang advanced the field with "Real-Time Indoor Visible Light Positioning (VLP) Using Long Short Term Memory Neural Network (LSTM-NN) with Principal Component Analysis (PCA)" (2024, 13 citations), demonstrating how temporal neural networks can achieve high-reliability real-time tracking. By combining deep learning architectures with dimensionality reduction techniques, Chang has established new benchmarks for accuracy in indoor positioning systems, making them a key figure in the evolution of next-generation location-based services.
Research Focus
Key Achievements
Top Papers
- 1
- 2