Bat feeding Buzz test dataset; Classifier predictions and code

Read full text
Authors: Anonymous
Cited by: 0

Abstract

FeedingBuzz SequenceData - contains all the bat sequences (.wav) used to train/test the classifiers. Sequence_information.csv - contains all necessary information for each wav file, like sequence durations, guild, the grouping to FB/NoFB, and the presence of error labels. predictions_allClassifiers.csv - contains the binary prediction FB/noFB for each classifier and sequence. For FB classifiers producing FB probabilities, the Youden Index was used for binary threshold setting. AcousticIndices_information.csv - Contains the Acoustic indices calculated for each sequence 01.1: R Script for the running the Acoustic Indices & Duration Classifiers 01.2. R Script for running the BuzzFindR classifier 02.: R Script for the calculation of perfomance metrics 03: R Script for analysing classification errors using error models

Fields of Study & Subjects

Bat Biology and Ecology Studies Music and Audio Processing Animal Vocal Communication and Behavior

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
18 February 2026
Language
EN
Document type
Dataset