Analysis of signals under compositional noise with applications to SONAR data

Tucker, J. Derek; Wu, Wei; Srivastava, Anuj

doi:10.1109/JOE.2013.2254213

Title: Analysis of signals under compositional noise with applications to SONAR data

Abstract

In this paper, we consider the problem of denoising and classification of SONAR signals observed under compositional noise, i.e., they have been warped randomly along the x-axis. The traditional techniques do not account for such noise and, consequently, cannot provide a robust classification of signals. We apply a recent framework that: 1) uses a distance-based objective function for data alignment and noise reduction; and 2) leads to warping-invariant distances between signals for robust clustering and classification. We use this framework to introduce two distances that can be used for signal classification: a) a y-distance, which is the distance between the aligned signals; and b) an x-distance that measures the amount of warping needed to align the signals. We focus on the task of clustering and classifying objects, using acoustic spectrum (acoustic color), which is complicated by the uncertainties in aspect angles at data collections. Small changes in the aspect angles corrupt signals in a way that amounts to compositional noise. As a result, we demonstrate the use of the developed metrics in classification of acoustic color data and highlight improvements in signal classification over current methods.

Authors:

Tucker, J. Derek ^[1]; Wu, Wei ^[1]; Srivastava, Anuj ^[1]

Florida State Univ., Tallahassee, FL (United States)

Publication Date:: 2013-07-09

Research Org.:: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Sponsoring Org.:: ONR; USDOE

OSTI Identifier:: 1329617

Report Number(s):: SAND-2016-10053J
Journal ID: ISSN 0364-9059; 648092

Grant/Contract Number:: AC04-94AL85000

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Journal of Oceanic Engineering

Additional Journal Information:: Journal Volume: 39; Journal Issue: 2; Journal ID: ISSN 0364-9059

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 47 OTHER INSTRUMENTATION; noise; measurement; acoustics; image color analysis; Sonar applications; robustness; SONAR; compositional noise; functional data analysis; random warping; spectral signal classification; signal registration

Citation Formats


                    Tucker, J. Derek, Wu, Wei, and Srivastava, Anuj. Analysis of signals under compositional noise with applications to SONAR data.  United States: N. p., 2013. 
Web.  doi:10.1109/JOE.2013.2254213.

Copy to clipboard


                    Tucker, J. Derek, Wu, Wei, & Srivastava, Anuj. Analysis of signals under compositional noise with applications to SONAR data.  United States.  https://doi.org/10.1109/JOE.2013.2254213

Copy to clipboard


                    Tucker, J. Derek, Wu, Wei, and Srivastava, Anuj. Tue .  
"Analysis of signals under compositional noise with applications to SONAR data".  United States.  https://doi.org/10.1109/JOE.2013.2254213.  https://www.osti.gov/servlets/purl/1329617.

Copy to clipboard


                    
@article{osti_1329617,

  title        = {Analysis of signals under compositional noise with applications to SONAR data},

  author       = {Tucker, J. Derek and Wu, Wei and Srivastava, Anuj},

  abstractNote = {In this paper, we consider the problem of denoising and classification of SONAR signals observed under compositional noise, i.e., they have been warped randomly along the x-axis. The traditional techniques do not account for such noise and, consequently, cannot provide a robust classification of signals. We apply a recent framework that: 1) uses a distance-based objective function for data alignment and noise reduction; and 2) leads to warping-invariant distances between signals for robust clustering and classification. We use this framework to introduce two distances that can be used for signal classification: a) a y-distance, which is the distance between the aligned signals; and b) an x-distance that measures the amount of warping needed to align the signals. We focus on the task of clustering and classifying objects, using acoustic spectrum (acoustic color), which is complicated by the uncertainties in aspect angles at data collections. Small changes in the aspect angles corrupt signals in a way that amounts to compositional noise. As a result, we demonstrate the use of the developed metrics in classification of acoustic color data and highlight improvements in signal classification over current methods.},

  doi          = {10.1109/JOE.2013.2254213},

  journal      = {IEEE Journal of Oceanic Engineering},

  number       = 2,

  volume       = 39,

  place        = {United States},

  year         = {2013},

  month        = {7}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/JOE.2013.2254213

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 7 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referencing / citing this record:

Elastic functional principal component regression
journal, April 2018

Tucker, J. Derek; Lewis, John R.; Srivastava, Anuj
Statistical Analysis and Data Mining: The ASA Data Science Journal, Vol. 12, Issue 2
DOI: 10.1002/sam.11399

Similar Records in DOE PAGES and OSTI.GOV collections:

Using Machine Learning to Discern Eruption in Noisy Environments: A Case Study Using CO2-Driven Cold-Water Geyser in Chimayó, New Mexico

Journal Article Yuan, Baichuan ; Tan, Yen Joe ; Mudunuru, Maruti Kumar ; ... - Seismological Research Letters

In this paper, we present an approach based on machine learning (ML) to distinguish eruption and precursory signals of Chimayó geyser (New Mexico, U.S.A.) under noisy environmental conditions. This geyser can be considered a natural analog of CO₂ intrusion into shallow water aquifers. By studying this geyser, we can understand upwelling of CO₂-rich fluids from depth, which has relevance to leak monitoring in a CO₂ sequestration project. ML methods such as random forests (RFs) are known to be robust multiclass classifiers and perform well under unfavorable, noisy conditions. However, the extent of the RF method’s accuracy is poorly understood formore »« less
Cited by 10
https://doi.org/10.1785/0220180306

Full Text Available
Classification with asymmetric label noise: Consistency and maximal denoising

Journal Article Blanchard, Gilles ; Flaska, Marek ; Handy, Gregory ; ... - Electronic Journal of Statistics

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are known. In this work, we give conditions that are necessary and sufficient for the true class-conditional distributions to be identifiable. These conditions are weaker than those analyzed previously, and allow for the classes to be nonseparable and the noise levels to be asymmetric and unknown. The conditions essentially state that amore »« less
Cited by 26
https://doi.org/10.1214/16-EJS1193

Full Text Available
Signal analysis by means of time-frequency (Wigner-type) distributions -- Applications to sonar and radar echoes

Journal Article Gaunaurd, G ; Strifors, H C - Proceedings of the IEEE

Time series data have been traditionally analyzed in either the time or the frequency domains. For signals with a time-varying frequency content, the combined time-frequency (TF) representations, based on the Cohen class of (generalized) Wigner distributions (WD`s) offer a powerful analysis tool. Using them, it is possible to: (1) trace the time-evolution of the resonance features usually present in a standard sonar cross section (SCS), or in a radar cross section (RCS) and (2) extract target information that may be difficult to even notice in an ordinary SCS or RCS. After a brief review of the fundamental properties of themore »« less
https://doi.org/10.1109/5.535243
Qualitative and quantitative processing of side-scan sonar data

Conference Dwan, F S ; Anderson, A L ; Hilde, T W.C. - AAPG Bulletin (American Association of Petroleum Geologists); (USA)

Modern side-scan sonar systems allow vast areas of seafloor to be rapidly imaged and quantitatively mapped in detail. The application of remote sensing image processing techniques can be used to correct for various distortions inherent in raw sonography. Corrections are possible for water column, slant-range, aspect ratio, speckle and striping noise, multiple returns, power drop-off, and for georeferencing. The final products reveal seafloor features and patterns that are geometrically correct, georeferenced, and have improved signal/noise ratio. These products can be merged with other georeferenced data bases for further database management and information extraction. In order to compare data collected bymore »« less
Deep Learning for Automated Identification of Eels in Sonar Data

Technical Report Jacobson, Paul ; Deng, Zhiqun ; Hou, Zhangshuan ; ...

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploitedmore »« less

Similar Records

Title: Analysis of signals under compositional noise with applications to SONAR data

Abstract

Citation Formats

Elastic functional principal component regression journal, April 2018

Elastic functional principal component regression
journal, April 2018