Repositório Institucional da Universidade Federal do Amapá - RIUNIFAP
Bem vindo ao RIUNIFAP!
O RIUNIFAP é uma iniciativa para preservação e disseminação da Produção Intelectual da UNIFAP, compartilhando o Conhecimento produzido na Universidade com a Comunidade.
Comunidades no Repositório Institucional
Selecione uma comunidade para navegar por suas coleções
Últimas publicações
Tipo de item:Item, Caracterização dos conflitos de pesca na zona costeira do Amapá: uma abordagem multidimensional(UNIFAP - Universidade Federal do Amapá, 2024-03-25) SANCHES, Charly Ribeiro; MENDES JÚNIOR, Raimundo Nonato Gomes; CHELALA, Charles Achcar; http://lattes.cnpq.br/4067451199072751; https://orcid.org/0000-0003-3739-2215; http://lattes.cnpq.br/8406536275568373; https://orcid.org/0000-0002-0910-0812Coastal zones are marked by highly complex socio-environmental conflicts involving the use of fishing resources. In coastal areas, artisanal fishing is attached to the objective conditions of social reproduction, access to food and income, and knowledge involving traditional populations. This practice, hence, contrasts with other categories of fishing, such as industrial fishing, leading to fishery conflicts in complex interactions between various social actors. As a highly productive region for fishery, the Amazon coast has a complex context in terms of use and appropriation of fishery resources. We aimed to identify, characterize, and propose an analysis of the conflicts in the Amazon coastal zone within the state of Amapá, Brazil. We identified conflicts in three cities of the coastal region of Amapá: Oiapoque, Calçoene and Amapá. The data was obtained from workshops involving fishermen linked to organized fishermen colonies. We measured the temporal factor of the conflict, the scale of development of the conflict and the social actors involved. Then, we constructed conceptual maps of the actors characterized in each conflict. In addition, considering all the dimensions measured, a PCoA (Principal Coordinates Analysis) analysis was carried out to determine the multidimensional differences in conflicts between cities. Our results point to significant differences in conflicts of the same nature in the different cities of the coastal zone of Amapá state. This information implies that regional actions may not be very effective in resolving conflicts and that local-scale specific solutions are more appropriate, taking into account the singularities of each conflict.Tipo de item:Item, Avaliação da qualidade da água em áreas de recreação: um estudo de caso sobre a balneabilidade do rio Amazonas, Macapá, Amapá(UNIFAP - Universidade Federal do Amapá, 2024-11-06) PEREIRA, Carlos Vitor dos Santos; VALVEDE, Karina Cardoso; SANTOS, Géssica Zila Batista dos; http://lattes.cnpq.br/1894957802286041; https://orcid.org/0000-0003-4821-6567; http://lattes.cnpq.br/4314270496889269; https://orcid.org/0000-0003-4518-8900Tipo de item:Item, Uso do sulfato de alumínio como coagulante na clarificação de água do Rio Amazonas(UNIFAP - Universidade Federal do Amapá, 2025-04-22) BARROS, Bruna de Oliveira; VALVERDE, Karina Cardoso; http://lattes.cnpq.br/4314270496889269; https://orcid.org/0000-0003-4518-8900Tipo de item:Item, Estudo comparativo fonético-fonológico: francês, crioulo guianense e kheuol (karipuna, Oiapoque)(UNIFAP - Universidade Federal do Amapá, 2025-09-26) SILVA, Ene dos Santos; ARAÚJO, Elizângela ManoelaTipo de item:Item, Avaliação de redes neurais convolucionais e monitoramento de fauna urbana na Universidade Federal do Amapá campus Marco Zero: desafios da automação em ambiente de transição amazônico(UNIFAP - Universidade Federal do Amapá, 2026-02-26) OLIVEIRA NETO, Antonio Carvalho de; NORRIS, Darren; http://lattes.cnpq.br/7765798316321443; https://orcid.org/0000-0003-0015-8214The monitoring of stray animals in urban areas is a strategic component of One Health, aiming at zoonosis control and the mitigation of impacts on native biodiversity. However, manual analysis of large volumes of data from camera traps constitutes a methodological bottleneck. This study aimed to develop and evaluate the performance of a Deep Learning prototype, based on the ResNet-50 architecture, for the automated classification of fauna at the Marco Zero campus of the Federal University of Amapá (UNIFAP), comparing it to the established DeepFaune and AddaxAI models. A total of 19,190 images were collected in an Amazonian urban environment. The prototype was implemented via the Torch for R ecosystem using fine-tuning techniques. Results revealed a global accuracy of 29.99% and a Kappa index of 0.0981 for the prototype, while the DeepFaune and AddaxAI models reached accuracy levels of ~65%. The analysis evidenced that the low performance stems from domain shift and the Terra Incognita effect, exacerbated by vegetation density and the loss of chromatic descriptors in nocturnal (infrared) records. In addition to the technological bias, the study identified significant anthropogenic pressure, with 16.68% of records consisting of domestic dogs (Canis lupus familiaris) and cats (Felis catus). It is concluded that, in the current scenario, the full automation of environmental surveillance at UNIFAP is unfeasible, and manual classification by specialists remains a mandatory and indispensable step to ensure data reliability, positioning artificial intelligence as a preliminary screening tool.