no code implementations • 26 Mar 2021 • Zhichao Liang, Zixiang Luo, Keyin Liu, Jingwei Qiu, Quanying Liu
In this work, rooted in optimal control theory, we propose a Koopman-MPC framework for real-time closed-loop electrical neuromodulation in epilepsy, which integrates i) a deep Koopman operator based dynamical model to predict the temporal evolution of epileptic EEG with an approximate finite-dimensional linear dynamics and ii) a model predictive control (MPC) module to design optimal seizure suppression strategies.