Neural Network Aided Glitch-Burst Discrimination and Glitch Classification

We investigate the potential of neural-network based classifiers for discriminating gravitational wave bursts (GWBs) of a given canonical family (e.g. core-collapse supernova waveforms) from typical transient instrumental artifacts (glitches), in the data of a single detector. The further classification of glitches into typical sets is explored.In order to provide a proof of concept,we use the core-collapse supernova waveform catalog produced by H. Dimmelmeier and co-Workers, and the data base of glitches observed in laser interferometer gravitational wave observatory (LIGO) data maintained by P. Saulson and co-Workers to construct datasets of (windowed) transient waveforms (glitches and bursts) in additive (Gaussian and compound-Gaussian) noise with different signal-tonoise ratios (SNR). Principal component analysis (PCA) is next implemented for reducing data dimensionality, yielding results consistent with, and extending those in the literature. Then, a multilayer perceptron is trained by a backpropagation algorithm (MLP-BP) on a data subset, and used to classify the transients as glitch or burst. A Self-Organizing Map (SOM) architecture is finally used to classify the glitches. The glitch/burst discrimination and glitch classification abilities are gauged in terms of the related truth tables. Preliminary results suggest that the approach is effective and robust throughout the SNR range of practical interest. Perspective applications pertain both to distributed (network, multisensor) detection of GWBs, where someintelligenceat the single node level can be introduced, and instrument diagnostics/optimization, where spurious transients can be identified, classified and hopefully traced back to their entry points

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  et al.,et al.  Primary proton spectrum between 200-TeV and 1000-TeV observed with the Tibet burst detector and air shower array , 2000 .

[3]  Gustavo A. Medina Tanco,et al.  A multivariate study of mass composition for simulated showers at the Auger South Observatory , 2001 .

[4]  Soumya D. Mohanty,et al.  Coherent network analysis for triggered gravitational wave burst searches , 2007, 0709.0940.

[5]  S. Mukherjee.  Preliminary results from the hierarchical glitch pipeline , 2007 .

[6]  W. Hofmann,et al.  Particle identification by multifractal parameters in γ-astronomy with the HEGRA-Cherenkov-telescopes , 2001 .

[7]  Steven A. Gabriel,et al.  Neural network prediction of solar energetic proton events with long lead times , 2002 .

[8]  R. Horowitz,et al.  Self-organizing neural networks: convergence properties , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[9]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[10]  C. Ott,et al.  Gravitational wave burst signal from core collapse of rotating stars , 2008, 0806.4953.

[11]  Julien Sylvestre.  Optimal generalization of power filters for gravitational wave bursts from single to multiple detectors , 2003 .

[12]  ARGO-YBJ Collaboration presented by S. Bussino.  Gamma-Hadron Discrimination with a Neural Network in the ARGO-YBJ Experiment , 1999 .

[13]  Tucson,et al.  Gravitational Waves from Axisymmetric, Rotating Stellar Core Collapse , 2003, astro-ph/0307472.

[14]  Salvatore Rampone,et al.  Three-and-six-month-before forecast of water resources in a karst aquifer in the Terminio massif (Southern Italy) , 2013, Appl. Soft Comput..

[15]  Andrea Vicer'e.  Optimal detection of burst events in gravitational wave interferometric observatories , 2002 .

[16]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Ik Siong Heng,et al.  Rotating stellar core-collapse waveform decomposition: a principal component analysis approach , 2008, 0810.5707.

[18]  Andreas Haungs,et al.  Image and non-image parameters of atmospheric Cherenkov events: a comparative study of their γ-ray/hadron classification potential in ultrahigh energy regime , 2002 .

[19]  Soumya D. Mohanty,et al.  Variability of signal-to-noise ratio and the network analysis of gravitational wave burst signals , 2006, gr-qc/0601076.

[20]  L. Milano,et al.  A Neural Network-based ARX Model of Virgo Noise ” , 1999 .

[21]  Patrice Hello,et al.  Detection in coincidence of gravitational wave bursts with a network of interferometric detectors: Geometric acceptance and timing , 2002 .

[22]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[23]  Maria Principe,et al.  Modeling the impulsive noise component and its effect on the operation of a simple coherent network algorithm for detecting unmodeled gravitational wave bursts , 2008, 0806.4574.

[24]  J. Font,et al.  Relativistic simulations of rotational core collapse - II. Collapse dynamics and gravitational radiation , 2002, astro-ph/0204289.

[25]  T. Zwerger,et al.  Dynamics and gravitational wave signature of axisymmetric rotational core collapse , 1997 .

[26]  Gainesville,et al.  Constraint Likelihood analysis for a network of gravitational wave detectors , 2005 .

[27]  Stephane Kreckelbergh,et al.  Coincidence and coherent data analysis methods for gravitational wave bursts in a network of interferometric detectors , 2003 .

[28]  Roberto Tagliaferri,et al.  A neural network-based approach to noise identification of interferometric GW antennas: the case of the 40 m Caltech laser interferometer , 2002 .

[29]  Klaus Schulten,et al.  Self-organizing maps: ordering, convergence properties and energy functions , 1992, Biological Cybernetics.

[30]  Laura Cadonati,et al.  CorrPower: a cross-correlation-based algorithm for triggered and untriggered gravitational-wave burst searches , 2005 .

[31]  Fabio Postiglione,et al.  Robust gravitational wave burst detection and source localization in a network of interferometers using cross-Wigner spectra , 2011, 1112.5105.

[32]  Klaus Schulten,et al.  Self-organizing maps: stationary states, metastability and convergence rate , 1992, Biological Cybernetics.

[33]  M. Tinto,et al.  Near optimal solution to the inverse problem for gravitational-wave bursts. , 1989, Physical review. D, Particles and fields.

[34]  Leo Stein,et al.  Coherent network analysis technique for discriminating gravitational-wave bursts from instrumental noise , 2006 .