Explore the groundbreaking research that powers our neurorehabilitation platform, from Hebbian plasticity to closed-loop brain-computer interfaces.
Donald Hebb's principle forms the foundation of neural plasticity. When neurons are activated simultaneously, synaptic connections strengthen through Long-Term Potentiation (LTP). Our 500ms predictive window ensures brain intent forms before movement, maximizing this effect.
Hebb, D.O. (1949). The Organization of Behavior. Wiley.
Click neurons to see Hebbian strengthening
Move mouse over the hand to activate mirror neurons
Discovered by Rizzolatti's team, mirror neurons fire both during action execution AND observation. Virtual limbs performing perfect movements create consistent success feedback, activating the motor cortex and promoting neural reorganization even in severely affected limbs.
Rizzolatti, G. et al. (1996). Cognitive Brain Research.
Rhythmic musical elements engage the right hemisphere to bypass damaged language areas. The predictable temporal structure of music provides scaffolding for motor planning, while rhythm entrainment synchronizes neural oscillations across brain regions.
Schlaug G et al. (2010). Music Perception.
Click nodes to jump the signal
Traditional rehabilitation is open-loop. Our closed-loop system creates continuous feedback: EEG detects motor intent → game responds with visual/auditory action → patient perceives success → neural pathway strengthens. This real-time contingency maximizes neuroplastic change.
Daly, J.J. & Wolpaw, J.R. (2008). Lancet Neurology.
14-channel wireless EEG headset capturing focus, relaxation, and motor imagery signals. Real-time brainwave analysis via Cortex API enables precise detection of motor intent before physical movement occurs.
High-precision accelerometer and gyroscope data at 100Hz for movement tracking. 500ms haptic priming delivers rhythm cues before expected movements, preparing the motor system for action.
MediaPipe hand tracking provides 21 3D landmarks per hand at 30fps using just a standard webcam. Deep learning models enable precise finger movement detection for fine motor rehabilitation exercises.
Hebb, D.O. (1949). The Organization of Behavior. Wiley.
Rizzolatti, G. et al. (1996). Cognitive Brain Research, 3(2).
Daly, J.J. & Wolpaw, J.R. (2008). Lancet Neurology, 7(11).
Ramachandran, V.S. (2009). Brain, 132(7).