"This all sounds fishy" - My PhD research summarized in 3 minutes. My PhD is done now, but this research is still going. Stay tuned. #3MT #fishsounds #PhDone #Tech4Wildlife @UVicScience @CanHealthyOcean @JuanesLab.

A summary of what the new US administration is doing to science.

Getting quite lively on the other platform. So good to see interesting science posts again. Come join us on the other side :-).

RT @animal_prattle: We've made lots of friends on Blu*sky in the past 2 days, incl @DMennill @MathevonNicolas @xenocanto .Added them to our….

The Woods Hole Oceanographic Institution (WHOI) invites candidates to apply to the open full-time tenure-track or tenured positions. Interests include ocean acoustics. . Application deadline: December 6, 2024.

RT @DIIORIOLucia1: 🚨 !! JOB ALERT !! 2 years #postdoc. Join the SEAPhony team @Cefrem1 to use passive acoustic data in the study of the dy….

RT @DefectorMedia: The gang's all here! 🎁

RT @FrouinMouy: 1/7 .Excited to share our new study on the northern elephant seals. Published in @PLOSONE , unrevealing their deep sea unde….

Help us design a low-cost open-source hydrophone & acoustic recorder by completing this short survey. It will help us understand the current usage of underwater acoustic recorders and the specific need for a low-cost device. #bioacoustics

RT @CoralMorph: Read a fresh scientific paper on Fish Sounds recorded at the @CoralCityCamera site ✨🐟🎤✨🐟. https://t….

@WILDLABSNET #tech4wildlife #bioacoustics.

This work would have been impossible without the support of @DFO_Pacific @NOAAResearch @NSERC_CRSNG @CanHealthyOcean @JuanesLab @MitacsCanada @NOAAFish_NEFSC @jascoacoustics.

Work only possible with amazing co-authors: @ArcherEcology , Stan Dosso, Sarah Dudas, @ecophilina , @colin_foord , @wdhalliday, @JuanesLab, Darienne Lancaster, Sofie Van Parijs, and Danna Haggarty.

We provide an open-source implementation of the CNN detector that includes detailed documentation and a tutorial. Check it out:

Our findings:.1. The CNN performed up to 1.9 times better than Random Forest.2. In some cases, the CNN was able to find more faint fish sounds than the human analyst.3. The CNN performed well in environments it was not trained in.4. CNN detection errors are predictable.

We implemented and compared 2 different approaches to automatically detect fish sounds in passive acoustic recordings. One is based on Random Forest which is a more traditional machine learning approach. The other one is using CNN which is a more modern deep learning approach.

Mouy X, Archer SK, Dosso S, Dudas S, English P, Foord C, Halliday W, Juanes F, Lancaster D, Van Parijs S and Haggarty D (2024). Automatic detection of unidentified fish sounds: a comparison of traditional machine learning with deep learning. Front. Remote Sens. 5:1439995.

I am excited to share our new paper on the automatic detection of fish sounds: Automatic detection of unidentified fish sounds: a comparison of traditional machine learning with deep learning. #fishsounds 🐠🐟🔊. 🧵1/5.

Passive Acoustic Monitoring. for the human body. Another cool episode from #TwentyThousandHertz #DallasTaylor.

RT @FrouinMouy: 🥳Thank you! Our project about sub-adult male northern elephant seals🦭 got the third place (🥉) in the video category [Commu….

RT @FrouinMouy: Our #Tech4Wildlife project in BC uses a combination of high-definition video, acoustic imaging sonar, and acoustic recorder….