12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Frequency analysis for real-time identification...
View graph of relations

« Back

Frequency analysis for real-time identification of sick pigs and disease monitoring in pig houses.

Research output: Contribution in Book/Report/ProceedingsConference contribution

Published

  • V. Exadaktylos
  • M. Silva
  • J.-M. Aerts
  • C. James Taylor
  • S. Ferrari
  • M. Guarino
  • D. Berckmans
Publication date06/2007
Host publicationPrecision livestock farming '07
EditorsS. Cox
Place of publicationWageningen
PublisherWageningen Academic Publishers
Pages125-131
Number of pages7
ISBN (Print)978-90-8686-023-4
Original languageEnglish

Abstract

This paper extends existing cough identification methods and proposes a real-time version for identifying sick pig cough sounds. The analysis and classification is based on the frequency domain characteristics of the signal and a comparison to a reference set is made. This technique evaluates fuzzy c-means clustering to identify the reference set that mirrors the cough characteristics. The identification process can be implemented for real-time applications that would improve and speed up the treatment procedure in pig houses.