@lorenejeantet.bsky.social
PostDoc @AIMS South Africa (https://aims.ac.za/) 🇿🇦 Biologging / Bioacoustics and AI for Wildlife monitoring 🐢🦈🐧
Thrilled to showcase how artificial intelligence can support wildlife monitoring and conservation ! 🤗 🐧 🐢
10.10.2025 09:57 — 👍 0 🔁 0 💬 0 📌 0
🎉 Last day at AIMS for our student Matthew (co-supervised with Emmanuel Dufourq)! He presented his 2-year project: a lightweight pose estimation model to monitor African penguins 🐧 + custom Raspberry Pi camera system for remote footage capture 🎥
Amazing work — well done Matthew! 👏 #AI #Conservation
Hello Sara, can I also be added please 🤗? thank you !
06.02.2025 08:08 — 👍 1 🔁 0 💬 0 📌 0Hello, can you add me to the pack ? thank you !
02.12.2024 09:22 — 👍 0 🔁 0 💬 1 📌 0
All the data is available online, and the code is on GitHub as notebooks to make it easy to use !
👉 github.com/AIMS-Researc...
This study was part of Kukanya Zondo's research project for his Master's in Mathematical Sciences at AIMS South Africa
, where he graduated with distinction— congratulations! 💪
Transfer learning helps study endangered species with deep learning, using data from different species or humans when specific data is scarce. It works across architectures and allows reuse of online available models , usually provided with the data they were trained on.
26.11.2024 10:32 — 👍 0 🔁 0 💬 1 📌 0
Thanks to Damien Chevallier and the CNRS team, 6 hawksbill turtles were equipped with onboard cameras, accelerometers, gyroscopes, and pressure sensors—enabling accelerometer signal validation. A first for this species!
26.11.2024 10:31 — 👍 1 🔁 0 💬 0 📌 0
Pre-training on data from green turtles or humans boosts accelerometer-based behavior identification for hawksbill turtles. Fine-tuning the model outperforms training solely on hawksbill data.
26.11.2024 10:30 — 👍 0 🔁 0 💬 0 📌 0
🚩 New paper published in JEB !
journals.biologists.com/jeb/article/...
We test transfer learning with deep learning to automatically identify the behaviors of endangered species like Hawksbill sea turtle using accelerometer data.
All the code is available on GitHub => github.com/jeantetloren...
19.11.2024 09:29 — 👍 0 🔁 0 💬 0 📌 0
With minimal preprocessing, F1-score of 81.1% and Global accuracy of 97.2%. The 6 behavioral categories identified: Breathing, Feeding, Gliding, Resting, Scratching, and Swimming.
19.11.2024 09:27 — 👍 0 🔁 0 💬 0 📌 0
🚩 🚩Improving ecological knowledge of sea turtles
V-net : a new method based on deep learning to infer sea turtle behavior from multi-sensor loggers
www.sciencedirect.com/science/arti...
