Arbitrarily shaped spatial cluster detection via reinforcement learning algorithms.

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.creatorOliveira, Dênis Ricardo Xavier de-
Autor(es): dc.creatorMoreira, Gladston Juliano Prates-
Autor(es): dc.creatorDuarte, Anderson Ribeiro-
Data de aceite: dc.date.accessioned2025-08-21T15:56:40Z-
Data de disponibilização: dc.date.available2025-08-21T15:56:40Z-
Data de envio: dc.date.issued2025-08-06-
Data de envio: dc.date.issued2024-
Fonte completa do material: dc.identifierhttps://www.repositorio.ufop.br/handle/123456789/20747-
Fonte completa do material: dc.identifierhttps://doi.org/10.1007/s10651-025-00649-7-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/capes/1028155-
Descrição: dc.descriptionStudies on spatial cluster patterns are of interest in many areas. Spatial scan statistics is the most widespread strategy for studying these patterns. However, scan statistics lose substantial efficiency in situations where candidate clusters can assume irregu- lar shapes. Conversely, other techniques, with the aim of increasing the flexibility of analyzing cluster shapes, have emerged. We present two novel reinforcement learn- ing approaches that use scan spatial statistics to represent the reward function. The novel approaches are explained in detail, and there is an extensive set of computa- tional experiments with controlled synthetic data to verify their functionality and adaptation to the problem of detecting spatial clusters. Our results attest to the qual- ity and applicability of the new techniques for addressing this problem.-
Formato: dc.formatapplication/pdf-
Idioma: dc.languageen-
Direitos: dc.rightsrestrito-
Palavras-chave: dc.subjectIrregular clusters-
Palavras-chave: dc.subjectReinforcement learning-
Palavras-chave: dc.subjectSpatial statistics scan-
Título: dc.titleArbitrarily shaped spatial cluster detection via reinforcement learning algorithms.-
Aparece nas coleções:Repositório Institucional - UFOP

Não existem arquivos associados a este item.