Revisiting and Testing Stationarity in the Time-Frequency Plane
Dr. Patrick Flandrin
Department of Ecole Normale Superieure de Lyon, France
7th Floor Board Room, CoRE Building
The concept of stationarity is revisited from an operational perspective that explicitly takes into account the observation scale. A general, time-frequency-based, framework is described for testing such a relative stationarity via the introduction of stationarized surrogate data. Two variations are discussed, based on either dissimilarity measures between local and global spectra, or machine learning approaches. Different extensions, including wavelet-based tests for images and transient detection, are considered.
Patrick Flandrin is a CNRS Senior Researcher, working with the "Signals, Systems and Physics" Group in the Physics Department of Ecole Normale Supérieure de Lyon, France. His research interests are mostly in nonstationary signal processing (with emphasis on time-frequency methods and wavelets), scaling processes and complex systems. He authored numerous publications in those areas over the last 30 years, including the book "Time-Frequency/Time-Scale Analysis" (Academic Press, 1999). Dr Flandrin has been awarded the Philip Morris Scientific Prize in 1991, the SPIE Wavelet Pioneer Award in 2001 and the Prix Michel Monpetit from the French Academy of Sciences in 2001. Fellow of IEEE (2002) and EURASIP (2009), he has been elected Member of the French Academy of Sciences in 2010.