Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorDoell, Michael-
dc.contributor.authorKuehn, Dominik-
dc.contributor.authorSuessle, Vanessa-
dc.contributor.authorBurnett, Matthew J.-
dc.contributor.authorDowns, Colleen T.-
dc.contributor.authorWeinmann, Andreas-
dc.contributor.authorHergenroether, Elke-
dc.contributor.editorSkala, Václav
dc.date.accessioned2024-07-27T17:53:48Z-
dc.date.available2024-07-27T17:53:48Z-
dc.date.issued2024-
dc.identifier.citationWSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 23-32.cs_CZ
dc.identifier.issn2464–4625 (online)-
dc.identifier.issn2464–4617 (print)-
dc.identifier.urihttp://hdl.handle.net/11025/57381-
dc.format10 s.cs_CZ
dc.format.mimetypeapplication/pdf
dc.language.isoencs_CZ
dc.publisherVáclav Skala - UNION Agencycs_CZ
dc.subjectbioakustické monitorovánícs_CZ
dc.subjectdruhová klasifikacecs_CZ
dc.subjectspektrogramycs_CZ
dc.subjectkonvoluční rekurentní neuronová síťcs_CZ
dc.subjectobousměrná GRUcs_CZ
dc.subjectekologiecs_CZ
dc.subjectzachování divoké zvěřecs_CZ
dc.titleAutomated Bioacoustic Monitoring for South African Bird Species on Unlabeled Datacs_CZ
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedAnalyses for biodiversity monitoring based on passive acoustic monitoring (PAM) recordings is time-consuming and chal lenged by the presence of background noise in recordings. Existing models for sound event detection (SED) worked only on certain avian species and the development of further models required labeled data. The developed framework automatically extracted labeled data from available platforms for selected avian species. The labeled data were embedded into recordings, including environmental sounds and noise, and were used to train convolutional recurrent neural network (CRNN) models. The models were evaluated on unprocessed real world data recorded in urban KwaZulu-Natal habitats. The Adapted SED-CRNN model reached a F1 score of 0.73, demonstrating its efficiency under noisy, real-world conditions. The proposed approach to automatically extract labeled data for chosen avian species enables an easy adaption of PAM to other species and habitats for future conservation projects.cs_CZ
dc.subject.translatedbioacoustic monitoringcs_CZ
dc.subject.translatedspecies classificationcs_CZ
dc.subject.translatedspectrogramscs_CZ
dc.subject.translatedCNNscs_CZ
dc.subject.translatedconvolutional recurrent neural networkcs_CZ
dc.subject.translatedbidirectional GRUcs_CZ
dc.subject.translatedecologycs_CZ
dc.subject.translatedwildlife conservationcs_CZ
dc.identifier.doihttps://doi.org/10.24132/10.24132/CSRN.3401.4-
dc.type.statusPeer revieweden
Vyskytuje se v kolekcích:WSCG 2024: Full Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
A17-2024.pdfPlný text5,94 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/57381

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Sborníky ZČU / UWB Proceedings
  4. WSCG: Full Papers
  5. WSCG 2024: Full Papers Proceedings