Intrinsic structure study of whale vocalizations

Yin Xian, Xiaobai Sun, Wenjing Liao, Yuan Zhang, Douglas Nowacek, Loren Nolte

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Whale vocalizations can be modeled as polynomial-phase signals, which are widely used in radar and sonar applications. Such signals lie on a nonlinear manifold parameterized by polynomial phase coefficients. In this paper, we apply manifold learning methods, in particular ISOMAP and Laplacian Eigenmap, to examine the underlying geometric structure of whale vocalizations. We can improve the classification accuracy by using the intrinsic structure of whale vocalizations. Our experiments on the DCLDE conference and MobySound data show that manifold learning methods such as ISOMAP and Laplacian eigenmap outperform linear dimension reduction methods such as Principal Component Analysis (PCA) and Multidimensional Scaling (MDS).
Original languageEnglish
Title of host publicationOCEANS 2016 MTS/IEEE Monterey
PublisherIEEE
Number of pages5
ISBN (Electronic)9781509015375
ISBN (Print)9781509015276
DOIs
Publication statusPublished - Sept 2016
EventOCEANS 2016 MTS/IEEE Monterey - Monterey, United States
Duration: 19 Sept 201623 Sept 2016
https://ieeexplore.ieee.org/xpl/conhome/7750936/proceeding

Publication series

NameOCEANS

Conference

ConferenceOCEANS 2016 MTS/IEEE Monterey
Country/TerritoryUnited States
CityMonterey
Period19/09/1623/09/16
Internet address

User-Defined Keywords

  • Whale vocalizations
  • polynomial-phase signals
  • manifold learning
  • whale classification

Fingerprint

Dive into the research topics of 'Intrinsic structure study of whale vocalizations'. Together they form a unique fingerprint.

Cite this