Papers
6
Total Citations
118
H-Index
5
About
Keun-Tae Kim is a biomedical engineer and neurotechnology researcher whose work sits at the intersection of brain-computer interfaces (BCIs), neural signal processing, and assistive robotics. His research has made significant contributions to enabling individuals with physical disabilities — including stroke patients and amputees — to interact with robotic systems through non-invasive neural and muscular signals. Kim is perhaps best known for his pioneering work on EEG-based control systems, including a motor imagery-driven robotic wheelchair that introduced five-directional command capability to overcome limitations in earlier BCI designs (34 citations). He has extended this approach to robot arm control, demonstrating the feasibility of decoding multi-directional reaching movements from brain signals (23 citations). In parallel, his research into electromyography (EMG) has produced robust classification frameworks for prosthetic hand control using convolutional neural networks (23 citations), as well as adaptive multi-user myoelectric interfaces. A particularly impactful recent contribution applies multi-task heterogeneous ensemble learning for cross-subject EEG classification in stroke rehabilitation contexts (22 citations), addressing the critical challenge of individual variability in BCI systems. Across his body of work, Kim consistently bridges fundamental neuroscience with practical engineering solutions, advancing accessible, user-adaptive assistive technologies for those with motor impairments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6