Real-​time analysis of movement kinematics can benefit multiple different strategies in rehabilitation after stroke, including allowing closed-​loop brain stimulation. Use of inertial measurement units (IMUs) allows detection of movement and extraction of kinematic features, but application in real-​time remains challenging. This project will develop algorithms for real-​time movement data analysis and feature extraction in typical rehabilitation tasks and general real-​life movements. In turn, these algorithms will be applied to control novel brain stimulation approaches in stroke neurorehabilitation.