An online kernel change detection algorithm

A number of abrupt change detection methods have been proposed in the past, among which are efficient model-based techniques such as the Generalized Likelihood Ratio (GLR) test. We consider the case where no accurate nor tractable model can be found, using a model-free approach, called Kernel change detection (KCD). KCD compares two sets of descriptors extracted online from the signal at each time instant: The immediate past set and the immediate future set. Based on the soft margin single-class Support Vector Machine (SVM), we build a dissimilarity measure in feature space between those sets, without estimating densities as an intermediary step. This dissimilarity measure is shown to be asymptotically equivalent to the Fisher ratio in the Gaussian case. Implementation issues are addressed; in particular, the dissimilarity measure can be computed online in input space. Simulation results on both synthetic signals and real music signals show the efficiency of KCD.

[1]  Marie-Françoise Lucas,et al.  Wavelet-packet basis selection for abrupt changes detection in multicomponent signals , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[2]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[3]  Arthur Gretton,et al.  On-line one-class support vector machines. An application to signal segmentation , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[4]  Arthur Gretton,et al.  An online support vector machine for abnormal events detection , 2006, Signal Process..

[5]  Visakan Kadirkamanathan,et al.  Particle filtering-based fault detection in non-linear stochastic systems , 2002, Int. J. Syst. Sci..

[6]  Fredrik Gustafsson,et al.  Adaptive filtering and change detection , 2000 .

[7]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[8]  Frédéric Bimbot,et al.  Experiments on speech tracking in audio documents using Gaussian mixture modeling , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[9]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[10]  F. Gustafsson.  The marginalized likelihood ratio test for detecting abrupt changes , 1996, IEEE Trans. Autom. Control..

[11]  Alexander J. Smola,et al.  Online learning with kernels , 2001, IEEE Transactions on Signal Processing.

[12]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[13]  Patrick Flandrin,et al.  Time-Frequency/Time-Scale Analysis , 1998 .

[14]  Simon J. Godsill,et al.  Detection of abrupt spectral changes using support vector machines an application to audio signal segmentation , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[15]  Jean-Yves Tourneret,et al.  Bayesian off-line detection of multiple change-points corrupted by multiplicative noise: application to SAR image edge detection , 2003, Signal Process..

[16]  R. Vanderbei.  LOQO:an interior point code for quadratic programming , 1999 .

[17]  Simon J. Godsill,et al.  Bayesian harmonic models for musical signal analysis , 2003 .

[18]  J. Mercer.  Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .

[19]  C. Doncarli,et al.  Stationarity index for abrupt changes detection in the time-frequency plane , 1996, IEEE Signal Processing Letters.

[20]  C. Doncarli,et al.  Improved optimization of time-frequency-based signal classifiers , 2001, IEEE Signal Processing Letters.

[21]  Dinh-Tuan Pham,et al.  Fast algorithms for mutual information based independent component analysis , 2004, IEEE Transactions on Signal Processing.

[22]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[23]  Gunnar Rätsch,et al.  Input space versus feature space in kernel-based methods , 1999, IEEE Trans. Neural Networks.

[24]  Robert D. Nowak,et al.  Wavelet-based statistical signal processing using hidden Markov models , 1998, IEEE Trans. Signal Process..

[25]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[26]  P.J.W. Rayner,et al.  Optimized support vector machines for nonstationary signal classification , 2002, IEEE Signal Processing Letters.

[27]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[28]  Jean-Yves Tourneret,et al.  Classification of chirp signals using hierarchical Bayesian learning and MCMC methods , 2002, IEEE Trans. Signal Process..

[29]  Régine André-Obrecht,et al.  A new statistical approach for the automatic segmentation of continuous speech signals , 1988, IEEE Trans. Acoust. Speech Signal Process..

[30]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .

[31]  Christophe Andrieu,et al.  Bayesian curve fitting using MCMC with applications to signal segmentation , 2002, IEEE Trans. Signal Process..