Robust water leakage detection approach using the sound signals and pattern recognition

Yuriko Terao, Akira Mita

研究成果: Conference contribution

2 引用 (Scopus)

抄録

Water supply systems are essential for public health, ease of living, and industrial activity; basic to any modern city. But water leakage is a serious problem as it leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. Today, the most common leakage detection method is based on human expertise. An expert, using a microphone and headset, listens to the sound of water flowing in pipes and relies on their experience to determine if and where a leak exists. The purpose of this study is to propose an easy and stable automatic leak detection method using acoustics. In the present study, 10 leakage sounds, and 10 pseudo-sounds were used to train a Support Vector Machine (SVM) which was then tested using 69 sounds. Three features were used in the SVM: average Itakura Distance, maximum Itakura Distance and the largest eigenvalue as derived from Principal Component Analysis. This paper focuses on the Itakura Distance, which is a measure of the difference between AR models fitted to two data sets, and is found using the identified AR model parameters. In this study, 10 leakage sounds are used as a standard reference set of data. The average Itakura Distance is the average difference between a test datum and the 10 reference data. The maximum Itakura Distance is the maximum difference between a test datum and the 10 reference data. Using these measures and the PCA eigenvalues as features for our SVM, classification accuracy of 97.1 % was obtained.

元の言語English
ホスト出版物のタイトルProceedings of SPIE - The International Society for Optical Engineering
6932
DOI
出版物ステータスPublished - 2008
イベントSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2008 - San Diego, CA, United States
継続期間: 2008 3 102008 3 13

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2008
United States
San Diego, CA
期間08/3/1008/3/13

Fingerprint

pattern recognition
Pattern recognition
leakage
Acoustic waves
acoustics
Support vector machines
water
Water
eigenvalues
Water supply systems
Leak detection
earphones
public health
Public health
Microphones
Water supply
disasters
Principal component analysis
Disasters
principal components analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

これを引用

Terao, Y., & Mita, A. (2008). Robust water leakage detection approach using the sound signals and pattern recognition. : Proceedings of SPIE - The International Society for Optical Engineering (巻 6932). [69322D] https://doi.org/10.1117/12.775968

Robust water leakage detection approach using the sound signals and pattern recognition. / Terao, Yuriko; Mita, Akira.

Proceedings of SPIE - The International Society for Optical Engineering. 巻 6932 2008. 69322D.

研究成果: Conference contribution

Terao, Y & Mita, A 2008, Robust water leakage detection approach using the sound signals and pattern recognition. : Proceedings of SPIE - The International Society for Optical Engineering. 巻. 6932, 69322D, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2008, San Diego, CA, United States, 08/3/10. https://doi.org/10.1117/12.775968
Terao Y, Mita A. Robust water leakage detection approach using the sound signals and pattern recognition. : Proceedings of SPIE - The International Society for Optical Engineering. 巻 6932. 2008. 69322D https://doi.org/10.1117/12.775968
Terao, Yuriko ; Mita, Akira. / Robust water leakage detection approach using the sound signals and pattern recognition. Proceedings of SPIE - The International Society for Optical Engineering. 巻 6932 2008.
@inproceedings{3e1dc7603d8140d09f2a79036355ad18,
title = "Robust water leakage detection approach using the sound signals and pattern recognition",
abstract = "Water supply systems are essential for public health, ease of living, and industrial activity; basic to any modern city. But water leakage is a serious problem as it leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. Today, the most common leakage detection method is based on human expertise. An expert, using a microphone and headset, listens to the sound of water flowing in pipes and relies on their experience to determine if and where a leak exists. The purpose of this study is to propose an easy and stable automatic leak detection method using acoustics. In the present study, 10 leakage sounds, and 10 pseudo-sounds were used to train a Support Vector Machine (SVM) which was then tested using 69 sounds. Three features were used in the SVM: average Itakura Distance, maximum Itakura Distance and the largest eigenvalue as derived from Principal Component Analysis. This paper focuses on the Itakura Distance, which is a measure of the difference between AR models fitted to two data sets, and is found using the identified AR model parameters. In this study, 10 leakage sounds are used as a standard reference set of data. The average Itakura Distance is the average difference between a test datum and the 10 reference data. The maximum Itakura Distance is the maximum difference between a test datum and the 10 reference data. Using these measures and the PCA eigenvalues as features for our SVM, classification accuracy of 97.1 {\%} was obtained.",
keywords = "Itakura distance, Leak detection, Support vector machine",
author = "Yuriko Terao and Akira Mita",
year = "2008",
doi = "10.1117/12.775968",
language = "English",
volume = "6932",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Robust water leakage detection approach using the sound signals and pattern recognition

AU - Terao, Yuriko

AU - Mita, Akira

PY - 2008

Y1 - 2008

N2 - Water supply systems are essential for public health, ease of living, and industrial activity; basic to any modern city. But water leakage is a serious problem as it leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. Today, the most common leakage detection method is based on human expertise. An expert, using a microphone and headset, listens to the sound of water flowing in pipes and relies on their experience to determine if and where a leak exists. The purpose of this study is to propose an easy and stable automatic leak detection method using acoustics. In the present study, 10 leakage sounds, and 10 pseudo-sounds were used to train a Support Vector Machine (SVM) which was then tested using 69 sounds. Three features were used in the SVM: average Itakura Distance, maximum Itakura Distance and the largest eigenvalue as derived from Principal Component Analysis. This paper focuses on the Itakura Distance, which is a measure of the difference between AR models fitted to two data sets, and is found using the identified AR model parameters. In this study, 10 leakage sounds are used as a standard reference set of data. The average Itakura Distance is the average difference between a test datum and the 10 reference data. The maximum Itakura Distance is the maximum difference between a test datum and the 10 reference data. Using these measures and the PCA eigenvalues as features for our SVM, classification accuracy of 97.1 % was obtained.

AB - Water supply systems are essential for public health, ease of living, and industrial activity; basic to any modern city. But water leakage is a serious problem as it leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. Today, the most common leakage detection method is based on human expertise. An expert, using a microphone and headset, listens to the sound of water flowing in pipes and relies on their experience to determine if and where a leak exists. The purpose of this study is to propose an easy and stable automatic leak detection method using acoustics. In the present study, 10 leakage sounds, and 10 pseudo-sounds were used to train a Support Vector Machine (SVM) which was then tested using 69 sounds. Three features were used in the SVM: average Itakura Distance, maximum Itakura Distance and the largest eigenvalue as derived from Principal Component Analysis. This paper focuses on the Itakura Distance, which is a measure of the difference between AR models fitted to two data sets, and is found using the identified AR model parameters. In this study, 10 leakage sounds are used as a standard reference set of data. The average Itakura Distance is the average difference between a test datum and the 10 reference data. The maximum Itakura Distance is the maximum difference between a test datum and the 10 reference data. Using these measures and the PCA eigenvalues as features for our SVM, classification accuracy of 97.1 % was obtained.

KW - Itakura distance

KW - Leak detection

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=44349101094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44349101094&partnerID=8YFLogxK

U2 - 10.1117/12.775968

DO - 10.1117/12.775968

M3 - Conference contribution

AN - SCOPUS:44349101094

VL - 6932

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -