Testing stationarity with surrogates - A one-class SVM approach

An operational framework is developed for testing stationarity relatively to an observation scale, in both stochastic and deterministic contexts. The proposed method is based on a comparison between global and local time-frequency features. The originality is to make use of a family of stationary surrogates for defining the null hypothesis and to base on them a statistical test implemented as a one-class Support Vector Machine. The time-frequency features extracted from the surrogates are considered as a learning set and used to detect departure from stationnarity. The principle of the method is presented, and some results are shown on typical models of signals that can be thought of as stationary or nonstationary, depending on the observation scale used.