Deep wavelet scattering features for infrasonic threat identification

Infrasonic waves continue to be a staple of threat identification due to their presence in a variety of natural and man-made events, along with their low-frequency characteristics supporting detection over great distances. Considering the large set of phenomena that produce infrasound, it is critical to develop methodologies that exploit the unique signatures generated by such events to aid in threat identification. In this work, we propose a new infrasonic time-series classification technique based on the recently introduced Wavelet Scattering Transform (WST). Leveraging concepts from wavelet theory and signal processing, the WST induces a deep feature mapping on time series that is locally time invariant and stable to time-warping deformations through cascades of signal filtering and modulus operators. We demonstrate that the WST features can be utilized with a variety of classification methods to gain better discrimination. Experimental validation on the Library of Typical Infrasonic Signals (LOTIS)—containing infrasound events from mountain associated waves, microbaroms, internal atmospheric gravity waves and volcanic eruptions—illustrates the effectiveness of our approach and demonstrate it to be competitive with other state-of-the-art classification techniques.

[1]  Charles R. Wilson,et al.  Infrasonic Waves and Auroral Activity , 1967, Nature.

[2]  Paul S. Addison,et al.  LOW-OSCILLATION COMPLEX WAVELETS , 2002 .

[3]  Joakim Andén,et al.  Deep Scattering Spectrum , 2013, IEEE Transactions on Signal Processing.

[4]  Sergios Theodoridis,et al.  Machine Learning: A Bayesian and Optimization Perspective , 2015 .

[5]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[6]  Alain Hauchecorne,et al.  Infrasound monitoring for atmospheric studies , 2009 .

[7]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[8]  Stéphane Mallat,et al.  Group Invariant Scattering , 2011, ArXiv.

[9]  Alfred J. Bedard,et al.  Infrasound Originating Near Mountainous Regions in Colorado , 1978 .

[10]  Abul Hasan Siddiqi Applied Functional Analysis: Numerical Methods, Wavelet Methods, and Image Processing , 2003 .

[11]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[12]  J. Seiner,et al.  Infrasonic jet noise from volcanic eruptions , 2009 .

[13]  Dmitry Bobrov,et al.  CTBTO: Goals, Networks, Data Analysis and Data Availability , 2012 .

[14]  Y. Meyer Wavelets and Operators , 1993 .

[15]  Donald Estep,et al.  Applied Mathematics: Body and Soul , 2003 .

[16]  Aurelio Dominguez-Gonzalez,et al.  Empirical Wavelet Transform-based Detection of Anomalies in ULF Geomagnetic Signals Associated to Seismic Events with a Fuzzy Logic-based System for Automatic Diagnosis , 2015 .

[17]  Chokri Ben Amar,et al.  Beta wavelets. Synthesis and application to lossy image compression , 2005, Adv. Eng. Softw..

[18]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[19]  R. Duffin,et al.  A class of nonharmonic Fourier series , 1952 .

[20]  S. Mallat,et al.  Invariant Scattering Convolution Networks , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  G. Weiss,et al.  Littlewood-Paley Theory and the Study of Function Spaces , 1991 .

[22]  L. Ceranna,et al.  Localization of microbarom sources using the IMS infrasound network , 2012 .

[23]  Hans-Georg Stark Wavelets and Signal Processing: An Application-Based Introduction , 2005 .

[24]  R. Balan,et al.  Density, Overcompleteness, and Localization of Frames. I. Theory , 2005, math/0510360.

[25]  Kasso A. Okoudjou,et al.  Finite Frame Theory: A Complete Introduction to Overcompleteness , 2016 .

[26]  Alan V. Oppenheim,et al.  Discrete-time Signal Processing. Vol.2 , 2001 .

[27]  Fredric M. Ham,et al.  Discrimination of volcano activity and mountain-associated waves using infrasonic data and a backpropagation neural network , 1999, Defense, Security, and Sensing.

[28]  Roland Klees,et al.  Wavelets in the Geosciences , 2000 .

[29]  Luiz Velho,et al.  From Fourier Analysis to Wavelets , 2015 .

[30]  Li Li Selected Applications of Convex Optimization , 2015 .

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

[32]  Peter G. Casazza,et al.  Finite Frames: Theory and Applications , 2012 .

[33]  C. Torrence,et al.  A Practical Guide to Wavelet Analysis. , 1998 .

[34]  Michael J. Piovoso,et al.  A new family of wavelets : the Poisson wavelet transform , 1997 .