Visual active learning for labeling: A case for soundscape ecology data

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversity College Cork-
Autor(es): dc.creatorHilasaca, Liz Huancapaza-
Autor(es): dc.creatorRibeiro, Milton Cezar-
Autor(es): dc.creatorMinghim, Rosane-
Data de aceite: dc.date.accessioned2025-08-21T20:35:05Z-
Data de disponibilização: dc.date.available2025-08-21T20:35:05Z-
Data de envio: dc.date.issued2022-05-01-
Data de envio: dc.date.issued2022-05-01-
Data de envio: dc.date.issued2021-07-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.3390/info12070265-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/233242-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/233242-
Descrição: dc.descriptionLabeling of samples is a recurrent and time-consuming task in data analysis and machine learning and yet generally overlooked in terms of visual analytics approaches to improve the process. As the number of tailored applications of learning models increases, it is crucial that more effective approaches to labeling are developed. In this paper, we report the development of a methodology and a framework to support labeling, with an application case as background. The methodology performs visual active learning and label propagation with 2D embeddings as layouts to achieve faster and interactive labeling of samples. The framework is realized through SoundscapeX, a tool to support labeling in soundscape ecology data. We have applied the framework to a set of audio recordings collected for a Long Term Ecological Research Project in the Cantareira-Mantiqueira Corridor (LTER CCM), localized in the transition between northeastern São Paulo state and southern Minas Gerais state in Brazil. We employed a pre-label data set of groups of animals to test the efficacy of the approach. The results showed the best accuracy at 94.58% in the prediction of labeling for birds and insects; and 91.09% for the prediction of the sound event as frogs and insects.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionInstitute of Mathematical and Computer Science ICMC University of São Paulo-
Descrição: dc.descriptionInstituto de Biociências São Paulo State University—UNESP-
Descrição: dc.descriptionSchool of Computer Science and Information Technology University College Cork-
Descrição: dc.descriptionInstituto de Biociências São Paulo State University—UNESP-
Descrição: dc.descriptionFAPESP: 2013/50421-2-
Descrição: dc.descriptionFAPESP: 2020/01779-5-
Descrição: dc.descriptionCNPq: 312045/2013-1-
Descrição: dc.descriptionCNPq: 312292/2016-3-
Descrição: dc.descriptionCNPq: 442147/2020-1-
Idioma: dc.languageen-
Relação: dc.relationInformation (Switzerland)-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectActive learning-
Palavras-chave: dc.subjectClustering-
Palavras-chave: dc.subjectLabeling-
Palavras-chave: dc.subjectSampling-
Palavras-chave: dc.subjectSoundscape ecology-
Palavras-chave: dc.subjectVisualization-
Título: dc.titleVisual active learning for labeling: A case for soundscape ecology data-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.