Skip to content

Dataset and videos for the paper "Predicting long-term collective animal behavior with deep learning"

Notifications You must be signed in to change notification settings

epfl-mobots/preddl_2023

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DOI

This repository contains the data used in the manuscript entitled "Predicting long-term collective animal behavior with deep learning"

It contains data of pairs of Hemigrammus rhodostomus (Rummy-nose tetra) swimming in a circular arena (25cm radius).

  • rummy: Contains the pair data for H. rhodostomus
  • generated: contains the data generated by the models presented in "Predicting long-term collective animal behavior with deep learning".

If you are using this dataset you can reference its DOI.

Related work

[1] Disentangling and modeling interactions in fish with burst-and-coast swimming reveal distinct alignment and attraction behaviors

Furthermore, the raw trajectories included in this repository are part of the dataset introduced in "Disentangling and modeling interactions in fish with burst-and-coast swimming reveal distinct alignment and attraction behaviors". Consider citing the paper:

@article{calovi2018disentangling,
  title={Disentangling and modeling interactions in fish with burst-and-coast swimming reveal distinct alignment and attraction behaviors},
  author={Calovi, Daniel S and Litchinko, Alexandra and Lecheval, Valentin and Lopez, Ugo and P{\'e}rez Escudero, Alfonso and Chat{\'e}, Hugues and Sire, Cl{\'e}ment and Theraulaz, Guy},
  journal={PLoS computational biology},
  volume={14},
  number={1},
  pages={e1005933},
  year={2018},
  publisher={Public Library of Science San Francisco, CA USA}
}

and the dataset (segmented in kicks) with DOI: https://doi.org/10.6084/m9.figshare.5687083.v1

@article{Sire2017, 
  author = "Clement Sire", 
  title = "{DATA PLOS.zip}", 
  year = "2017", 
  month = "12", 
  url = "https://figshare.com/articles/dataset/DATA_PLOS_zip/5687083", 
  doi = "10.6084/m9.figshare.5687083.v1" 
} 

[2] A data-driven method for reconstructing and modelling social interactions in moving animal groups

@article{escobedo2020data,
  title={A data-driven method for reconstructing and modelling social interactions in moving animal groups},
  author={Escobedo, R and Lecheval, V and Papaspyros, V and Bonnet, F and Mondada, F and Sire, Cl{\'e}ment and Theraulaz, Guy},
  journal={Philosophical Transactions of the Royal Society B},
  volume={375},
  number={1807},
  pages={20190380},
  year={2020},
  publisher={The Royal Society}
}

About

Dataset and videos for the paper "Predicting long-term collective animal behavior with deep learning"

Resources

Stars

Watchers

Forks

Packages

No packages published