UDTR Global Rights of Nature Radar

Data and scripts underlying the publication: Optimal deep learning activity recognition pipeline using animal bio-logging data

Identification

Public canonical key

radar:r-c8bae8d7b889501fb4c1de3af473b73e

Authors

Jasper A.J. Eikelboom

Reported year

2026

Reported language

en

Source type

dataset

First detected

2026-11-14T02:13:59.096735+00:00

Last metadata observation

2026-11-14T02:13:59.096735+00:00

Last HTTP verification

Not checked

Documentary abstract — original language

These are the scripts and intermediate data for the paper: "Optimal deep learning activity recognition pipeline using animal bio-logging data". In this paper, I systematically gathered publicly available bio-logging data and associated activity labels from 17 studies on a wide range of terrestrial, aquatic and aerial animal species. Then I used a nested 5x2CV training and evaluation protocol with different sensor types, feature sets, window sizes, machine leaning algorithms, and hyperparameter values. I compared the resulting performances from these ~800,000 different models using a generalized linear mixed model, to draw dataset-agnostic conclusions about the interaction between all aforementioned model parameters. Finally, I developed a novel metric (dMedian) that quantifies the diminishing returns in added variation over increasing bio-logging sequence lengths, which can be used to a priori determine a window size that optimizes the trade-off between model performance and temporal resolution. From this followed that small 1D Convolutional Neural Networks with a fixed architecture and hyperparameter values consistently outperformed or performed on-par with the best models from a lengthy hyperparameter tuning process, thereby making feature engineering and hyperparameter optimization obsolete. Furthermore, I demonstrate that model performance increased asymptotically with window size for all datasets and that my dMedian metric strongly correlates with it.

Identifiers

OPENALEX

https://openalex.org/W7161752886

DOI

10.4121/3f96e65a-783b-4c04-9533-c5d351dc8dfa

Documentary context

Documentary family

dataset

Source-reported types

dataset

Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.

Sources

OpenAlex · Record 1

• Document · https://research.wur.nl/en/datasets/data-and-scripts-underlying-the-publication-optimal-deep-learning

Documentary status

Relevance pending

Library

This identity is not yet included in the Legal Library.