Byeong-Hoo Lee
Papers
5
Total Citations
141
H-Index
4
About
Byeong-Hoo Lee is a prominent researcher specializing in brain-computer interfaces (BCIs), neural signal processing, and human-robot interaction. His work sits at the intersection of neuroscience and robotics, focusing on developing non-invasive systems that translate human brain activity into meaningful control signals for external devices such as robotic arms. Lee's most significant contribution is his 2020 multimodal signal dataset capturing 11 intuitive movement tasks from the upper extremity across multiple sessions, which has garnered 76 citations and serves as a foundational resource for BCI researchers worldwide. Complementing this, his hierarchical flow convolutional neural network for classifying forearm movement imagery from EEG signals (41 citations) represents a meaningful advance in decoding kinematic intent from brain signals with greater precision. Beyond data and algorithms, Lee has translated his research into practical applications, demonstrating vision-guided robotic arm control through brain-machine interfaces and developing iteratively calibratable networks designed to improve reliability in real-world EEG-based robotic control. His more recent explorations into visual imagery paradigms and channel optimization reflect a commitment to refining BCI usability in online environments. Collectively, his work has accumulated over 140 citations, establishing him as a meaningful contributor to assistive robotics and neural engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5