Acoustic analysis of big ocean data to monitor fish sounds

Abstract This paper presents a novel framework for monitoring fish sounds based on acoustic analysis of noisy big ocean data. The proposed method involves multiresolution acoustic features (MRAF) extraction and RPCA (robust principal component analysis) based feature selection for monitoring of natural fish sounds produced in situ by the plainfin midshipman (Porichthys notatus); here, we investigate this fish's grunts, growls and groans. Both local and contextual information are exploited by MRAF, while sparse components of the MRAF matrix obtained through RPCA is found to be more robust to overlapping low-frequency spectral contents among different classes. The simulation results obtained from real-recorded ocean data reveal the advantages of the proposed scheme for monitoring underwater soundscapes and determining a variety of fish sounds in natural marine habitats.

[1]  Maria Hansson-Sandsten,et al.  Classification of bird song syllables using singular vectors of the multitaper spectrogram , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[2]  T. Ravichandran,et al.  A novel approach for speech feature extraction by Cubic-Log compression in MFCC , 2013, 2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering.

[3]  Yann Guermeur,et al.  MSVMpack: A Multi-Class Support Vector Machine Package , 2011, J. Mach. Learn. Res..

[4]  D. Bodnar,et al.  Complementary explana-tions for existing phenotypes in an acoustic communication system , 1999 .

[5]  David A. Mann,et al.  Listening to Fish , 2006 .

[6]  Robert R. Meyer,et al.  A variable-penalty alternating directions method for convex optimization , 1998, Math. Program..

[7]  A. Bass,et al.  Novel underwater soundscape: acoustic repertoire of plainfin midshipman fish , 2014, Journal of Experimental Biology.

[8]  J. Sisneros.  Seasonal plasticity of auditory saccular sensitivity in the vocal plainfin midshipman fish, Porichthys notatus. , 2009, Journal of neurophysiology.

[9]  Thierry Bouwmans,et al.  Foreground Detection by Robust PCA Solved via a Linearized Alternating Direction Method , 2012, ICIAR.

[10]  Ü. Dogan,et al.  Fast training of multi-class support vector machines , 2005 .

[11]  A. Kasumyan,et al.  Sounds and sound production in fishes , 2008, Journal of Ichthyology.

[12]  R. Fay,et al.  Soundscapes and the sense of hearing of fishes. , 2009, Integrative zoology.

[13]  M. Holderied,et al.  Soundscapes and living communities in coral reefs: Temporal and spatial variation , 2015 .

[14]  Len Thomas,et al.  A method for detecting whistles, moans, and other frequency contour sounds. , 2011, The Journal of the Acoustical Society of America.

[15]  R. Glowinski,et al.  Augmented Lagrangian and Operator-Splitting Methods in Nonlinear Mechanics , 1987 .

[16]  Francis Juanes,et al.  Listening to fish: Applications of passive acoustics to fisheries , 2006 .

[17]  S. Cullis-Suzuki.  Fish and ships : impacts of boat noise on the singing fish, Porichthys notatus , 2015 .

[18]  T. Tricas,et al.  Acoustic communication in territorial butterflyfish: test of the sound production hypothesis , 2006, Journal of Experimental Biology.

[19]  A. Popper,et al.  A noisy spring: the impact of globally rising underwater sound levels on fish. , 2010, Trends in ecology & evolution.

[20]  E. D. Chesmore,et al.  Automated identification of field-recorded songs of four British grasshoppers using bioacoustic signal recognition , 2004, Bulletin of Entomological Research.

[21]  Feng Jin,et al.  Identification of fish vocalizations from ocean acoustic data , 2016 .

[22]  Bernard L. Krause.  The Great Animal Orchestra: Finding the Origins of Music in the World's Wild Places , 2012 .

[23]  Xiaoming Yuan,et al.  Sparse and low-rank matrix decomposition via alternating direction method , 2013 .

[24]  Sarika Cullis-Suzuki.  Singing Fish in an Ocean of Noise: Effects of Boat Noise on the Plainfin Midshipman (Porichthys notatus) in a Natural Ecosystem. , 2016, Advances in experimental medicine and biology.

[25]  M. Fine,et al.  Use of Passive Acoustics for Assessing Behavioral Interactions in Individual Toadfish , 2008 .

[26]  Carmen C. Y. Poon,et al.  Big Data for Health , 2015, IEEE Journal of Biomedical and Health Informatics.

[27]  A. Kasumyan.  Acoustic signaling in fish , 2009, Journal of Ichthyology.

[28]  Koby Crammer,et al.  On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines , 2002, J. Mach. Learn. Res..

[29]  Charles Guyon,et al.  Robust Principal Component Analysis for Background Subtraction: Systematic Evaluation and Comparative Analysis , 2012 .

[30]  Josefin Starkhammar,et al.  Evaluation of seven time-frequency representation algorithms applied to broadband echolocation signals , 2015 .

[31]  Andrew H. Bass,et al.  Alternative male spawning tactics and acoustic signals in the plainfin midshipman fish , 2010 .

[32]  Luis J. Villanueva-Rivera,et al.  Soundscape Ecology: The Science of Sound in the Landscape , 2011 .