A research team led by Professor Ji-Woong Choi of the Department of Electrical Engineering and Computer Science at DGIST, in collaboration with teams led by Professor Han-Joon Kim of Kumoh National Institute of Technology, Professor Kyong Hwan Jin of Korea University, and Dr. Jong-Cheol Rah of the Korea Brain Research Institute, has developed "NONOS," a deep-learning-based analysis technology that precisely separates "rhythms" from underlying "background signals" in brain signals with high temporal resolution. Brain signals mix "rhythms (oscillatory components)" with "background signals (non-oscillatory components)"; in Parkinson's disease patients, the strength of "beta waves," which oscillate dozens of times per second, becomes excessively high and is associated with slowed movement and used as an indicator for assessing treatment effectiveness. Conventional filtering techniques calculate beta wave strength without accounting for background signals, potentially mistaking changes in background signals for changes in rhythms, while newer methods that remove background signals group signals into fixed time windows and can miss brief changes in rhythms. NONOS is an AI model trained to extract only background components that follow the pattern in which background signal power decreases exponentially with increasing frequency; subtracting these from original signals leaves pure rhythmic components. In analyses of brain signals from Parkinson's disease patients, NONOS reached 0.98 in predicting which foot a patient would step forward with, versus 0.54–0.79 for conventional methods, and in experiments using mice