Tae‐Ju Lee

Papers

Total Citations

H-Index

About

Tae-Ju Lee is a pioneering researcher at the intersection of brain-computer interfaces (BCI) and machine learning, whose work has opened new pathways for non-invasive neural control systems. His most influential contribution is the application of deep belief networks (DBN) to classify imagined speech from electroencephalogram (EEG) signals—a breakthrough that demonstrated how deep learning can decode complex cognitive states directly from brain activity. This foundational 2015 study, with 11 citations, established a novel framework for silent communication via BCI. Lee also made critical advances in understanding the neural correlates of motor intention, showing in his 2013 work (7 citations) how EEG power spectra in alpha, beta, and gamma bands systematically change with hand grip force levels at 25%, 50%, and 75% of maximum voluntary contraction. This research directly enabled proportional force control for robotic prosthetics, moving BCI beyond simple binary commands. By bridging neural signal processing with practical robotic applications, Lee’s work has laid essential groundwork for assistive technologies that restore motor function and communication for individuals with severe paralysis.