Comunidades no DSpace

Selecione uma comunidade para navegar por suas coleções

Agora exibindo 1 - 3 de 3

Submissões Recentes

  • Imagem de Miniatura
    Item type: Item ,
    Mediação e acessibilidade: caminhos para a inclusão da criança cega no âmbito da escola regular
    (2025) Santos, Lilian Cristina dos; Faria, Juliana Guimarães; Soares, Fabrízzio Alphonsus Alves de Melo Nunes
    This article aimed to analyze the pedagogical possibilities that can contribute to teaching mediation and, consequently, to the inclusion of blind children in the context of regular schooling. To this end, the research is characterized as an exploratory study of a qualitative nature, based on authors such as Mantoan (2003), Figueiredo (2019), and Santos (2019). In order to expand the proposed reflections, the exploratory study was combined with a semi-structured interview conducted with a teacher from the Municipal Education Network of Anápolis/GO, based on her experience as a support teacher for a blind child in the context of regular education between 2016 and 2018. The results showed that there are numerous pedagogical possibilities that can significantly contribute to the school inclusion process of blind children. However, for these to be truly effective, it is necessary for the teachers involved to be genuinely open to inclusive mediation, as well as for public authorities to ensure the resources needed to implement this practice in school routines.
  • Imagem de Miniatura
    Item type: Item ,
    Investigação de enviesamento de modelos de aprendizado demáquina para diagnóstico de doenças neurodegenerativasvia registros de marcha e voz
    (2025-12) Chagas, Ana Luísa de Bastos; Bucci, Giordana de Farias Franco Bueno; Félix, Juliana Paula; Salvini, Rogerio Lopes; Nascimento, Hugo Alexandre Dantas do; Soares, Fabrízzio Alphonsus Alves de Melo Nunes
    This paper synthesizes the main findings of a study on biases in machine learning models for diagnosingneurodegenerative diseases through gait and voice analysis. We evaluated how oversampling techniques, such as gaitwindowing and the indiscriminate use of multiple voice samples per person, inflate performance metrics when treatingsamples from the same subject as independent. By comparing protocols that ignore or preserve these dependencies in twodatasets, we observed that disregarding them inflates the metrics, while preserving them provides more reliable assessments.The results emphasize the importance of proper segregation of samples to obtain diagnostic models.
  • Imagem de Miniatura
    Item type: Item ,
    Aplicação da meta-heurística algoritmo genético na solução do Problema da Próxima Versão com modelagem, implementação e análise comparativa
    (2025) Silva, Ana Clara Araújo Gomes da; Camilo Junior, Celso Gonçalves; Teixeira Junior, Gilmar; Martins, Ricardo Manuel Gonçalves; Gama, Thiago Dias de Carvalho Quaresma
    This study explores the application of the Genetic Algorithm metaheuristic to address the complex Next Release Problem (NRP) in software engineering. The proposed approach adapts the Genetic Algorithm to the specific characteristics of this problem and evaluates its performance through experiments conducted on real datasets. The results demonstrate that the method produces efficient and well-balanced solutions aligned with project objectives, providing valuable contributions to requirements management in software development.
  • Imagem de Miniatura
    Item type: Item ,
    Transformer: o poder da atenção no auxílio ao diagnóstico de múltiplas doenças neurodegenerativas
    (2025-07) Bucci, Giordana de Farias Franco Bueno; Chagas, Ana Luísa de Bastos; Félix, Juliana Paula; Nascimento, Hugo Alexandre Dantas do; Soares, Fabrízzio Alphonsus Alves de Melo Nunes
    Neurodegenerative diseases (NDDs) cause, among other symptoms, gait instability, have an incurable nature,and present a long and challenging diagnostic process. For this reason, several studies have investigated gait using artificialintelligence models as an alternative to assist in the diagnosis of these diseases. This study presents the main resultsobtained during an undergraduate research project using an innovative method for detecting NDDs, using an Encoder-OnlyTransformer combined with gait analysis in a multi-class classification task. The results achieve high accuracy values andindicate a promising alternative for NDD identification.
  • Imagem de Miniatura
    Item type: Item ,
    An automatic method for estimating insect defoliation with visual highlights of consumed leaf tissue regions
    (2025) Vieira, Gabriel da Silva; Fonseca, Afonso Ueslei da; Sousa, Naiane Maria de; Ferreira, Júlio César; Félix, Juliana Paula; Cabacinha, Christian Dias; Soares, Fabrízzio Alphonsus Alves de Melo Nunes
    As an essential component of the architecture of a plant, leaves are crucial to sustaining decision-making in cultivars and effectively support agricultural processes. When the leaf area is constantly monitored, a plant’s health and productive capacity can be assessed to foment proactive and reactive strategies. Because of that, one of the most critical tasks in agricultural processes is estimating foliar damage. In this sense, we present an automatic method to estimate leaf stress caused by insect herbivory, including damage in border regions. As a novelty, we present a method with well-defined processing steps suitable for numerical analysis and visual inspection of defoliation severity. We describe the proposed method and evaluate its performance concerning 12 different plant species. Experimental results show high assertiveness in estimating leaf area loss with a concordance correlation coefficient of 0.98 for grape, soybean, potato, and strawberry leaves. A classic pattern recognition approach, named template matching, is at the core of the method whose performance is compared to cutting-edge techniques. Results demonstrated that the method achieves foliar damage quantification with precision comparable to deep learning models. The code prepared by the authors is publicly available.