Classification of underwater broadband bio-acoustics using spectro-temporal features

Navinda Kottege*, Raja Jurdak, Frederieke Kroon, Dean Jones

*Corresponding author for this work

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

9 Citations (Scopus)

Abstract

Large scale freshwater monitoring networks can passively capture sound for species detection or classification. The sheer volume of acoustic recordings in such systems requires in-network classification. Most of the recent work on bio- acoustic in-network classification targets narrowband or short-durations signals, which renders it unsuitable for classifying species that emit broadband short-duration signals. This paper proposes a method for broadband sound based classification for large scale aquatic monitoring networks. The method is based on the extraction of a small set of spectral and temporal features. We collect empirical fish sounds, using the case study of the spotted tilapia (Tilapia mariae) which is an invasive freshwater fish species in Australia, and extract spectral and temporal features with our method. We then evaluate the classification accuracy and precision of these features for detecting tilapia sounds against the performance of existing narrowband sound features. The results show that using logistic regression with our limited feature set yields the best performance. Surprisingly, performance slightly improves when we downsample the signal from 44.1 to 16 kHz, indicating that our method is well-suited for classification on embedded devices. We quantify the computational benefits of our approach for enabling broader long-term in-situ species tracking in underwater environments.

Original languageEnglish
Title of host publicationProceedings of the 7th ACM International Conference on Underwater Networks and Systems, WUWNet 2012
Place of PublicationNew York
PublisherACM
Pages1-8
Number of pages8
ISBN (Print)9781450317733
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event7th ACM International Conference on Underwater Networks and Systems, WUWNet 2012 - Los Angeles, CA, United States
Duration: 5 Nov 20126 Nov 2012

Other

Other7th ACM International Conference on Underwater Networks and Systems, WUWNet 2012
CountryUnited States
CityLos Angeles, CA
Period5/11/126/11/12

Keywords

  • Bio-acoustics
  • Classification
  • Detection
  • Freshwater fish
  • Sound
  • Tilapia
  • Underwater

Fingerprint Dive into the research topics of 'Classification of underwater broadband bio-acoustics using spectro-temporal features'. Together they form a unique fingerprint.

Cite this