A nonlinear source separation approach for the Nicolsky-Eisenman model

In previous works [7, 8], we proposed source separation methods for a simplified version of the Nicolsky-Eisenman (NE) model, which is related to a chemical sensing application. In the present paper, we provide a method able to deal with the complete NE model. Basically, such a model can be seen as a composition of a non-diagonal nonlinear transformation followed by a diagonal nonlinear transformation, i.e. a set of component-wise functions. The basic idea behind the developed technique is to estimate the parameters of these two stages in a separate fashion by using a prior knowledge of the sources, namely the fact that one of the sources is constant during a certain period of time. Simulations attest the viability of the proposed technique.