Similar to ICA or IVA, we must assume a non-Gaussian distribution as the generative model of source signals to solve the BSS problem.
The ultimate goal is to integrate the scientific results into a larger scale model of source term and near-field processes.
The canonical model of source separation is a transformation model: hypothetical source signals are observed after they have undergone an invertible transform, namely left multiplication by an invertible matrix.
The Bayesian method is a statistical procedure that allows the systematic incorporation and proper weighting of experimental data, prior knowledge of model and parameters, and probabilistic models of sources of experimental error.
More modern approaches include explicit specification and modeling of sources of heteroskedasticity.
Such methods include signal-space projection, independent component analysis, modeling of sources and artifacts etc.
The numerical earthquake model includes models of source rupture and 3D wave propagation.
Assessing the impacts of partial mass depletion in DNAPL source zones: I. Analytical modeling of source strength functions and plume response.
In order to understand the origin of ground motions from this earthquake and how it caused such strong shaking in Taipei, a numerical earthquake model is analyzed, including models of source rupture and wave propagation.
