Matching pursuit classification for time-varying acoustic emissions

Samuel P. Ebenezer, Antonia Papandreou-Suppappola, Seth B. Suppappola

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Time-varying techniques have been shown to be successful for classifying acoustic signals. In this paper, we propose a time-frequency based method for classifying time-varying, transient acoustic emissions using the matching pursuit decomposition (MPD) algorithm. Before classification, the MPD dictionary is formed using time and frequency shifted versions of selected learning signals. We show the superior classification performance of this method by applying it to real data obtained from an acoustic monitoring system. The main objective of an acoustic signal classifier in this system is to identify the acoustic emissions that may occur in concrete structures in distress. We study different strategies for binary and M-class classification, their dependence on the learning signals, and our classification results. We also discuss techniques to reduce the MPD processing time by pre-processing the test signals.

Original languageEnglish (US)
Title of host publicationConference Record of the Asilomar Conference on Signals, Systems and Computers
EditorsM.B. Matthews
Pages715-719
Number of pages5
Volume1
StatePublished - 2001
Event35th Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 4 2001Nov 7 2001

Other

Other35th Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/4/0111/7/01

Fingerprint

Acoustic emissions
Acoustics
Decomposition
Glossaries
Processing
Concrete construction
Classifiers
Monitoring

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Ebenezer, S. P., Papandreou-Suppappola, A., & Suppappola, S. B. (2001). Matching pursuit classification for time-varying acoustic emissions. In M. B. Matthews (Ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers (Vol. 1, pp. 715-719)

Matching pursuit classification for time-varying acoustic emissions. / Ebenezer, Samuel P.; Papandreou-Suppappola, Antonia; Suppappola, Seth B.

Conference Record of the Asilomar Conference on Signals, Systems and Computers. ed. / M.B. Matthews. Vol. 1 2001. p. 715-719.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ebenezer, SP, Papandreou-Suppappola, A & Suppappola, SB 2001, Matching pursuit classification for time-varying acoustic emissions. in MB Matthews (ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers. vol. 1, pp. 715-719, 35th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/4/01.
Ebenezer SP, Papandreou-Suppappola A, Suppappola SB. Matching pursuit classification for time-varying acoustic emissions. In Matthews MB, editor, Conference Record of the Asilomar Conference on Signals, Systems and Computers. Vol. 1. 2001. p. 715-719
Ebenezer, Samuel P. ; Papandreou-Suppappola, Antonia ; Suppappola, Seth B. / Matching pursuit classification for time-varying acoustic emissions. Conference Record of the Asilomar Conference on Signals, Systems and Computers. editor / M.B. Matthews. Vol. 1 2001. pp. 715-719
@inproceedings{fae93604b5e64c97ba2a6826fd62ee32,
title = "Matching pursuit classification for time-varying acoustic emissions",
abstract = "Time-varying techniques have been shown to be successful for classifying acoustic signals. In this paper, we propose a time-frequency based method for classifying time-varying, transient acoustic emissions using the matching pursuit decomposition (MPD) algorithm. Before classification, the MPD dictionary is formed using time and frequency shifted versions of selected learning signals. We show the superior classification performance of this method by applying it to real data obtained from an acoustic monitoring system. The main objective of an acoustic signal classifier in this system is to identify the acoustic emissions that may occur in concrete structures in distress. We study different strategies for binary and M-class classification, their dependence on the learning signals, and our classification results. We also discuss techniques to reduce the MPD processing time by pre-processing the test signals.",
author = "Ebenezer, {Samuel P.} and Antonia Papandreou-Suppappola and Suppappola, {Seth B.}",
year = "2001",
language = "English (US)",
volume = "1",
pages = "715--719",
editor = "M.B. Matthews",
booktitle = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Matching pursuit classification for time-varying acoustic emissions

AU - Ebenezer, Samuel P.

AU - Papandreou-Suppappola, Antonia

AU - Suppappola, Seth B.

PY - 2001

Y1 - 2001

N2 - Time-varying techniques have been shown to be successful for classifying acoustic signals. In this paper, we propose a time-frequency based method for classifying time-varying, transient acoustic emissions using the matching pursuit decomposition (MPD) algorithm. Before classification, the MPD dictionary is formed using time and frequency shifted versions of selected learning signals. We show the superior classification performance of this method by applying it to real data obtained from an acoustic monitoring system. The main objective of an acoustic signal classifier in this system is to identify the acoustic emissions that may occur in concrete structures in distress. We study different strategies for binary and M-class classification, their dependence on the learning signals, and our classification results. We also discuss techniques to reduce the MPD processing time by pre-processing the test signals.

AB - Time-varying techniques have been shown to be successful for classifying acoustic signals. In this paper, we propose a time-frequency based method for classifying time-varying, transient acoustic emissions using the matching pursuit decomposition (MPD) algorithm. Before classification, the MPD dictionary is formed using time and frequency shifted versions of selected learning signals. We show the superior classification performance of this method by applying it to real data obtained from an acoustic monitoring system. The main objective of an acoustic signal classifier in this system is to identify the acoustic emissions that may occur in concrete structures in distress. We study different strategies for binary and M-class classification, their dependence on the learning signals, and our classification results. We also discuss techniques to reduce the MPD processing time by pre-processing the test signals.

UR - http://www.scopus.com/inward/record.url?scp=0035574897&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035574897&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0035574897

VL - 1

SP - 715

EP - 719

BT - Conference Record of the Asilomar Conference on Signals, Systems and Computers

A2 - Matthews, M.B.

ER -