PCA based water leakage detection method using complex fourier components

Chikako Kondo, Akira Mita

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds are collected and the Fourier components are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components, and feature vectors are created from PCA parameters. Based on it, the Support Vector Machine (SVM) is built. The results show that the proposed method could achieve a very high accuracy.

Original languageEnglish
Pages (from-to)965-972
Number of pages8
JournalJournal of Environmental Engineering
Volume74
Issue number642
DOIs
Publication statusPublished - 2009 Aug

Fingerprint

Principal component analysis
Acoustic waves
Water
Water supply
Disasters
Support vector machines
Fourier transforms

Keywords

  • Principal Component Analysis
  • Support Vector Machine
  • Time Frequency Analysis
  • Water Leakage Detection

ASJC Scopus subject areas

  • Environmental Engineering

Cite this

PCA based water leakage detection method using complex fourier components. / Kondo, Chikako; Mita, Akira.

In: Journal of Environmental Engineering, Vol. 74, No. 642, 08.2009, p. 965-972.

Research output: Contribution to journalArticle

@article{087252f5d4604ddc8b216036fca86ab7,
title = "PCA based water leakage detection method using complex fourier components",
abstract = "The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds are collected and the Fourier components are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components, and feature vectors are created from PCA parameters. Based on it, the Support Vector Machine (SVM) is built. The results show that the proposed method could achieve a very high accuracy.",
keywords = "Principal Component Analysis, Support Vector Machine, Time Frequency Analysis, Water Leakage Detection",
author = "Chikako Kondo and Akira Mita",
year = "2009",
month = "8",
doi = "10.3130/aije.74.965",
language = "English",
volume = "74",
pages = "965--972",
journal = "Journal of Environmental Engineering (Japan)",
issn = "1348-0685",
publisher = "Architectural Institute of Japan",
number = "642",

}

TY - JOUR

T1 - PCA based water leakage detection method using complex fourier components

AU - Kondo, Chikako

AU - Mita, Akira

PY - 2009/8

Y1 - 2009/8

N2 - The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds are collected and the Fourier components are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components, and feature vectors are created from PCA parameters. Based on it, the Support Vector Machine (SVM) is built. The results show that the proposed method could achieve a very high accuracy.

AB - The water leakage leads to deficient water supplies, roads caving in, leakage in buildings, and secondary disasters. In this study, we propose the PCA-based automatic water leakage detection method considering complex Fourier components. The water leakage sounds and pseudo sounds are collected and the Fourier components are obtained through the short-time Fourier transform (STFT). Then the principal component analysis (PCA) is applied to complex Fourier components, and feature vectors are created from PCA parameters. Based on it, the Support Vector Machine (SVM) is built. The results show that the proposed method could achieve a very high accuracy.

KW - Principal Component Analysis

KW - Support Vector Machine

KW - Time Frequency Analysis

KW - Water Leakage Detection

UR - http://www.scopus.com/inward/record.url?scp=79954567394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954567394&partnerID=8YFLogxK

U2 - 10.3130/aije.74.965

DO - 10.3130/aije.74.965

M3 - Article

AN - SCOPUS:79954567394

VL - 74

SP - 965

EP - 972

JO - Journal of Environmental Engineering (Japan)

JF - Journal of Environmental Engineering (Japan)

SN - 1348-0685

IS - 642

ER -