Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Scientific ReportsOpen Access

A hybrid method combining rule-based filter and machine learning to detect porpoise and vessel sounds from a pulse event recorder

View Full Paper
Ask AI
Bookmark
Share

Authors

MOMayu OgawaJapan Agency for Marine-Earth Science and TechnologySKSatoko KimuraKyoto UniversityNINozomu IshiaiKyoto University

Discussion

Loading...

Member takes

Overview

This approach combines a rule-based filter and a random forest model to enhance detection accuracy in marine monitoring.

Key Points

  • The hybrid method improves detection accuracy for porpoise and vessel sounds in marine environments.
  • Detection accuracy reached 97% for porpoise clicks and 99% for vessel noise, significantly reducing false positives.
  • A rule-based filter was initially used, which achieved nearly 100% detection accuracy but had high false positive rates.
  • This method supports long-term ecological monitoring of small cetacean populations while handling complex noise data.

Cite This Study

Ogawa et al. (2025) studied this question.

synapsesocial.com/papers/68c1d03e54b1d3bfb60f71c8https://doi.org/10.1038/s41598-025-16370-1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Brief Review of Known Effects of Noise on Marine Mammals2007 · 151 citations
  2. 2Density estimation of Yangtze finless porpoises using passive acoustic sensors and automated click train detection2010 · 46 citations
  3. 3Acoustic discrimination between harbor porpoises and delphinids by using a simple two-band comparison2014 · 11 citations
  4. 4Detection and classification of narrow-band high frequency echolocation clicks from drifting recorders2020 · 18 citations
  5. 5Acoustic differentiation and classification of wild belugas and narwhals using echolocation clicks2021 · 16 citations