Papers

3

Total Citations

29

H-Index

3

About

Junhyuk Choi is a leading researcher in brain-computer interfaces (BCI) and rehabilitation robotics, with a focus on decoding human motor intent for lower-limb exoskeleton control. His work centers on using electroencephalography (EEG) and electromyography (EMG) signals to predict gait states, movement intentions, and speed, aiming to make robotic gait training more responsive and patient-driven. In his most-cited work (17 citations), Choi developed a spatio-spectral convolutional neural network to classify walking versus standing states from EEG, addressing the critical accuracy-versus-responsiveness trade-off in real-time BCI. He further advanced the field by comparing Motor Imagery, Selective Attention, and hybrid paradigms for left/right movement decoding (8 citations), demonstrating that hybrid approaches can improve classification robustness. Notably, his 2020 study on predicting intended gait speed from soleus surface EMG (4 citations) directly tackles the problem of insufficient patient effort during robot-assisted rehabilitation—a key barrier to effective stroke recovery. Choi’s contributions are foundational for creating intuitive, adaptive exoskeletons that respond to user intent, promising more engaging and effective neurorehabilitation.

Research Focus

Key Achievements

3
H-Index
3
Papers
29
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
EEG-based Gait State and Gait Intention Recognition Using Spatio-Spectral Convolutional Neural Network
17 citations · 2019
📈 Most Prolific Year: 2019 (2 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: Korea Institute of Science and Technology, Bio-Medical Science (South Korea)

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago