Jun-Young Jung
Papers
2
Total Citations
12
H-Index
2
About
Jun-Young Jung is a pioneering researcher in the field of rehabilitation robotics, with a primary focus on developing intelligent control systems for exoskeleton-assisted gait therapy. His work centers on the critical challenge of enabling robotic exoskeletons to accurately recognize and respond to a patient’s movement intentions—both the timing and the type of motion—to facilitate more natural and effective walking rehabilitation. In his influential 2012 study, Jung introduced a hybrid control method that integrates intention recognition with robotic actuation, laying foundational groundwork for patient-driven therapy. He further advanced the field in 2015 by proposing a gait phase classifier based on Recurrent Neural Networks (RNNs), a novel approach that leverages the dynamic, time-dependent nature of human walking. This work demonstrated that RNNs are more suitable than traditional feedforward networks for modeling gait, offering a significant improvement in real-time classification accuracy. Though his most-cited papers currently hold 6 citations each, their conceptual impact is substantial, bridging robotics, machine learning, and clinical rehabilitation. Jung’s contributions continue to inspire innovations in adaptive, intention-aware exoskeletons for stroke survivors.
Research Focus
Key Achievements
Top Papers
- 1
- 2A Gait Phase Classifier using a Recurrent Neural Network6 citations · 2015