VSN is the acronym of Variable sorting for normalization: a recently proposed algorithm, which, for a given set of multivariate signals, automatically produces a weighting function favoring signal variables that are only impacted by additive and multiplicative effects, and not by the response(s) of interest. The weighting function can be introduced in SNV preprocessing, or also with more complex baselines, such as polynomial ones.

The details of the algorithm can be found in:
G. Rabatel, F. Marini, B. Walczak, J.-M. Roger, VSN: Variable sorting for normalization. J. Chemometr. 34 (2020) e3164.

Download the Matlab code