Hi everyone!
It is time for the inaugural instalment of the monthly paper round-ups for readers of the open source solutions feed.
I will usually share these within the first week or two of the following month to allow search engines to index all the relevant papers.
Some of these articles were available before July, but were published in the July issue of their journal. This is not necessarily an endorsement of any of the presented work and this list is not intended to be comprehensive. If you think I missed something good, please share in the comments.
Now, enjoy the picks for July 2024!
July 2024 paper round-up
ExMove: An open‐source toolkit for processing and exploring animal‐tracking data in R
As the title suggests, ExMove is an open-source R package for handling animal movement data. It allows users to process raw files into cleaned up data sets ready for analysis and sharing. The paper explicitly names supporting the uptake of sharing open and reproducible code as a goal.
ExMove is a project by researchers from the University of Exeter and the Wildfowl and Wetlands Trust in the UK.
Find the project here: https://github.com/ExMove/ExMove
And read the paper here: https://doi.org/10.1111/1365-2656.14111
HawkEar: A bird‐borne visual and acoustic platform for eavesdropping the behaviour of mobile animals
This paper presents HawkEar, a fully open-source design for a lightweight audio and video sensor that can be carried by birds. It can be used to record other animals in the field and offers an alternative to noisy UAVs.
HawkEar is a project by researchers from the University of New Hampshire and the University of Oxford in the UK, as well as researchers from the New Mexico Falconry Association, the University of Cincinnati and the University of Notre Dame in the USA.
Find the project here: https://doi.org/10.5061/dryad.cjsxksncc
Here is the paper: https://doi.org/10.1111/2041-210X.14329
Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation
This paper presents Pytorch-wildlife, based on PyTorch. It is an open-source deep learning platform for large scale wildlife monitoring and has already been shown to have high success rates in the real world for species recognition. The project is still ongoing, so expect more updates and features in the future!
This work is being done by researchers from the Microsoft AI for Good team and the Center for Research and Formation in Artificial Intelligence in Colombia.
Check out the project: https://github.com/microsoft/CameraTraps
Read the paper: https://arxiv.org/abs/2405.12930
FnR - R package for computing inbreeding and numerator relationship coefficients
FnR is an open-source R package for analysing inbreeding rates in populations, an important tool for breeding programmes.
The paper was written by Mohammad Ali Nilforooshan from the Livestock Improvement Corporation in New Zealand.
Find the project here: https://github.com/nilforooshan/FnR
Read the paper here: https://doi.org/10.1186/s12862-024-02285-4
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill
In this paper, researchers used the open-source Video and Image Analytics for a Marine Environment (VIAME) to train a neural network to identify krill in videos taken by penguins in Antarctica.
This work was done by researchers from the National Oceanic and Atmospheric Administration and Kitware Inc. in the USA.
Find all the data here: https://zenodo.org/records/10883788
Check out the paper here: https://doi.org/10.1371/journal.pone.0303633
Add the first post in this thread.