Changgue Park
Papers
1
Total Citations
20
H-Index
1
About
Dr. Changgue Park is a leading researcher in indoor localization and deep learning, whose work has significantly advanced the field of real-time positioning systems. His primary research areas include sensor-based localization, recurrent neural networks, and attention mechanisms for spatial intelligence. Park's most notable contribution is the development of RONet, a novel architecture that employs stacked bidirectional LSTM networks with residual attention for range-only indoor localization. This groundbreaking approach, detailed in his highly cited 2019 paper with 20 citations, demonstrated remarkable accuracy in realistic conditions by effectively learning temporal dependencies from range measurements. The RONet model represents a paradigm shift from traditional geometric localization methods to data-driven approaches, enabling robust positioning even in challenging indoor environments where GPS fails. Park's work has been instrumental in bridging the gap between theoretical deep learning and practical localization systems, with applications spanning robotics, IoT, and autonomous navigation. His innovative integration of residual connections with attention mechanisms in temporal models has inspired subsequent research in sensor fusion and sequential data processing, establishing him as a key figure in the evolution of intelligent positioning technologies.
Research Focus
Key Achievements
Top Papers
- 1