Hao-Wei Chan
Papers
1
Total Citations
9
H-Index
1
About
Hao-Wei Chan is a researcher whose work sits at the intersection of wireless localization and machine learning. His primary research focus is on improving indoor positioning systems, specifically by leveraging the Wi-Fi Fine Time Measurement (FTM) protocol. Chan’s most significant contribution is a novel neural network (NN) model that predicts the location of Wi-Fi access points while simultaneously identifying non-line-of-sight (NLOS) conditions. This work, detailed in his 2021 paper "Transfer Learning of Wi-Fi FTM Responder Positioning with NLOS Identification," has garnered 9 citations. The key innovation lies in using a robot to collect FTM data, training the NN on a single FTM responder, and then applying transfer learning to generalize the model to new environments. This approach effectively tackles the persistent challenge of NLOS interference in indoor positioning, which often degrades accuracy. By enabling more reliable and adaptable location estimation, Chan’s research holds promise for applications in robotics, autonomous navigation, and smart building technologies, marking him as a rising contributor to the field of wireless sensing and localization.
Research Focus
Key Achievements
Top Papers
- 1