A benchmark for computational analysis of animal behavior, using animal-borne tags
Benjamin Hoffman, Maddie Cusimano, Vittorio Baglione, Daniela Canestrari, Damien Chevallier, Dominic L DeSantis, Lorène Jeantet, Monique A Ladds, Takuya Maekawa, Vicente Mata-Silva, Víctor Moreno-González, Anthony M Pagano, Eva Trapote, Outi Vainio, Antti Vehkaoja, Ken Yoda, Katherine Zacarian, Ari · 2024
Read A benchmark for computational analysis of animal behavior, using animal-borne tags by Benjamin Hoffman, Maddie Cusimano, Vittorio Baglione, Daniela Canestrari, Damien Chevallier, Dominic L DeSantis, Lorène Jeantet, Monique A Ladds, Takuya Maekawa, Vicente Mata-Silva, Víctor Moreno-González, Anthony M Pagano, Eva Trapote, Outi Vainio, Antti Vehkaoja, Ken Yoda, Katherine Zacarian, Ari (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11654173.txt.
Description
Benjamin Hoffman and co-authors built in 2024 a shared yardstick for machine reading of animal behavior from body-worn tags. Tags on wild animals log motion and surroundings, but each lab judges its own models its own way. Their benchmark, BEBE, gathers 1,654 hours of tagged data from 149 animals across nine groups, all labeled by behavior. Set tasks and scores let rival methods face the same test.
Deep networks beat the classic methods on all nine sets. A self-taught approach, adapted from a network trained on human wrist data, won overall and shone most when labeled data ran thin. The team draws firm tips for the field and offers the set in public.
Catalog record
| CREATOR | Benjamin Hoffman, Maddie Cusimano, Vittorio Baglione, Daniela Canestrari, Damien Chevallier, Dominic L DeSantis, Lorène Jeantet, Monique A Ladds, Takuya Maekawa, Vicente Mata-Silva, Víctor Moreno-González, Anthony M Pagano, Eva Trapote, Outi Vainio, Antti Vehkaoja, Ken Yoda, Katherine Zacarian, Ari |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 97 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |