Mixed matrix factorization: a novel algorithm for the extraction of kinematic-muscular synergies
Alessandro Scano, Robert Mihai Mira, Andrea d’Avella
Abstract
The mixed matrix factorization (MMF) is a novel method for extracting kinematic-muscular synergies. The previous state of the art algorithm (NMFpn) factorizes separately positive and rectified negative waveforms; the MMF instead employs a gradient descent method to factorize mixed kinematic unconstrained data and muscular non-negative data. MMF achieves perfect reconstruction on noiseless data, improving the NMFpn. MMF shows promising applicability on real data.
Topics & Concepts
KinematicsComputer scienceAlgorithmMatrix (chemical analysis)Matrix decompositionGradient descentNoise (video)Artificial intelligencePattern recognition (psychology)MathematicsImage (mathematics)Quantum mechanicsPhysicsComposite materialClassical mechanicsEigenvalues and eigenvectorsArtificial neural networkMaterials scienceMotor Control and AdaptationBalance, Gait, and Falls PreventionMuscle activation and electromyography studies