ItemOpen Access

Validation of the performance of the random forest model for activity classification

dc.contributor.author{"last":"Gottwald","first":"Jannis","affiliation":"Philipps-Universität Marburg","id":"orcid","id_value":"0000-0001-7763-1415"}
dc.date.accessioned2022-03-04T07:20:59Z
dc.date.available2022-03-04T07:20:59Z
dc.descriptionWe applied the trained random forest models to the 50% data withheld for testing to evaluate its performance in classifying bat activity. Similarly, we applied random forest models to the bird and human activity dataset after calculating the same predictor variables as for the bats. We first calculated the true positive rate (TPR) as the ratio of correctly identified incidents by comparing the observed data with the activity class attributed by the trained random forest models for all dataset types (i.e., human activity dataset, woodpecker, and bat video sequences). Next, we calculated the models’ F-score (F1) using the Caret package (Kuhn, 2008). Data and code are stored here.de_DE
dc.description.sponsorship{"funderName":"Hessisches Ministerium für Wissenschaft und Kunst"}
dc.identifier.doihttp://dx.doi.org/10.17192/fdr/82
dc.identifier.urihttps://data.uni-marburg.de/handle/dataumr/151
dc.language.isoengde_DE
dc.publisherJannis Gottwaldde_DE
dc.rightsCreative Commons Attribution 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectMovement ecologyde_DE
dc.subject.classification203-03 Ökologie und Biodiversität der Tiere und Ökosysteme, Organismische Interaktionende_DE
dc.subject.ddc590
dc.titleValidation of the performance of the random forest model for activity classificationde_DE
dc.typeDatasetde_DE
dc.typeInteractive Resourcede_DE
dc.typeOtherde_DE
local.metadata.publicyes
local.umr.fachbereichFB19:Geographiede_DE

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
validation.tar
Size:
42.4 GB
Format:
Unknown data format
Description:

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2022-08-05 13:18:51
1*
2022-03-04 08:20:59
* Selected version