Distance measures for signal processing and pattern recognition
Signal Processing
Testing for nonlinearity in time series: the method of surrogate data
Conference proceedings on Interpretation of time series from nonlinear mechanical systems
Support Vector Data Description
Machine Learning
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
Estimating the Support of a High-Dimensional Distribution
Neural Computation
Bibliography on cyclostationarity
Signal Processing
Testing Stationarity with Surrogates - A One-Class SVM Approach
SSP '07 Proceedings of the 2007 IEEE/SP 14th Workshop on Statistical Signal Processing
A nonparametric test for stationarity based on local Fourier analysis
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Multitaper Time-Frequency Reassignment for Nonstationary Spectrum Estimation and Chirp Enhancement
IEEE Transactions on Signal Processing
Time-Frequency Learning Machines
IEEE Transactions on Signal Processing - Part II
On the Description of Spectrogram Probabilities With a Chi-Squared Law
IEEE Transactions on Signal Processing
A New Nonstationarity Detector
IEEE Transactions on Signal Processing
Hi-index | 35.69 |
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 of stationarity and to base on them two different statistical tests. The first one makes use of suitably chosen distances between local and global spectra, whereas the second one is implemented as a one-class classifier, the time-frequency features extracted from the surrogates being interpreted as a learning set for stationarity. The principle of the method and of its two variations 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.