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

Keywords

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

ASJC Scopus subject areas

  • Environmental Engineering

Cite this