Serhii Bahdasariants

This paper introduces a phase decoder that reconstructs missing muscle activity from sparse EMG signals, achieving accurate phase estimation and muscle activation reconstruction in real-time.

The paper shows that a two-stage model (APE) outperforms a direct-mapping neural network in predicting limb dynamics under novel conditions by explicitly modeling equations of motion and numerical integration.

The paper introduces ANNet, a physics-informed neural network that unifies inverse and forward dynamics computations using a shared learned representation based on Appell's acceleration energy.

This paper develops an artificial physics engine using neural networks to simulate inverse dynamics of arm and hand movement with low torque errors.

This study evaluates how joint impedance affects the accuracy and stability of dynamic leg simulations using explicit and implicit solvers, finding that viscoelasticity reduces errors in explicit methods.