DSpace Collection:https://repositorio.ufu.br/handle/123456789/179032026-04-06T05:32:12Z2026-04-06T05:32:12ZDocumentação do desenvolvimento de um chatbot como ferramenta de apoio ao desenvolvimento cognitivo de crianças com Transtorno do Espectro Autistahttps://repositorio.ufu.br/handle/123456789/482072026-02-06T06:27:12Z2025-09-24T00:00:00ZTitle: Documentação do desenvolvimento de um chatbot como ferramenta de apoio ao desenvolvimento cognitivo de crianças com Transtorno do Espectro Autista
Abstract: This work presents and documents the development of a web-based chatbot application designed as assistive technology to support cognitive development in children with Autism Spectrum Disorder (ASD). The project was conducted as part of a supervised internship and is built upon a serverless microservices architecture deployed on Amazon Web Services (AWS) infrastructure. The solution integrates several specialized services, including Amazon Lex for natural language processing, Amazon Rekognition for image analysis, Amazon Polly for text-to-speech synthesis, and the OpenAI API for narrative generation. The developed system enables multimodal interactions, allowing children to express emotions and create personalized stories through image uploads or visual card selection. This monograph contributes by proposing a replicable and cost-effective architectural model while demonstrating the practical application of emerging technologies in developing inclusive educational tools.2025-09-24T00:00:00ZAlgoritmo Genético Orientado à Desordem para a Otimização da Exploração de Ambientes por Enxames de Robôshttps://repositorio.ufu.br/handle/123456789/482022026-02-06T06:27:10Z2025-05-15T00:00:00ZTitle: Algoritmo Genético Orientado à Desordem para a Otimização da Exploração de Ambientes por Enxames de Robôs
Abstract: Robotics, as part of the technological landscape, has developed at an accelerated pace.
New approaches are constantly sought to address everyday problems through the use of
robots, which has led to many solutions but also numerous challenges. As demands become more specific and data volumes increase, there is a growing need for systems that are increasingly focused on technical aspects. Within this context, this work proposes the application and adaptation of an evolutionary algorithm to optimize the parameters of the PheroCom robot swarm coordination model. To this end, entropy was adapted to act as an evaluation metric within the algorithm’s fitness function, serving as a multiplicative index in a penalization system during task execution.This approach enables the identification of configurations that promote a more balanced spatial distribution among robots, improving environmental coverage efficiency while avoiding both excessive concentration
and the neglect of certain regions. Experimental results show that entropy, as part of the evaluation criterion, allows for an effective analysis of exploration homogeneity and promotes a more coherent and distributed occupation of space by the robots. Furthermore, the results also demonstrate satisfactory efficiency when compared to ther eference model.2025-05-15T00:00:00ZAplicação web para visualização interativa do método simplex no ensino de programação linearhttps://repositorio.ufu.br/handle/123456789/478852025-12-19T06:17:47Z2025-10-17T00:00:00ZTitle: Aplicação web para visualização interativa do método simplex no ensino de programação linear2025-10-17T00:00:00ZDetecção de imagens geradas por inteligência artificial: um estudo sobre técnicas e desafioshttps://repositorio.ufu.br/handle/123456789/477612025-12-09T06:20:04Z2025-11-05T00:00:00ZTitle: Detecção de imagens geradas por inteligência artificial: um estudo sobre técnicas e desafios
Abstract: This research presents a Systematic Literature Review (SLR) on methods for detecting
images generated by artificial intelligence, focusing on approaches published between 2022
and 2025. A total of 44 articles were analyzed following the PRISMA protocol, allowing
the mapping of the state of the art, the identification of technical advances, and the recognition of persistent challenges. The findings reveal a significant growth in scientific
production in the field, with emphasis on architectures based on Convolutional Neural
Networks (CNNs), Transformers, and hybrid models, as well as techniques related to
cross-domain generalization, latent space exploration, and multi-scale attention mechanisms. In addition to technical aspects, the SLR also identified ethical and social concerns,
including misinformation, privacy risks, and the need for greater transparency and regulatory frameworks. In summary, the review confirms that synthetic image detection is a
rapidly evolving research area, still marked by challenges but showing significant advances
that highlight its scientific and social relevance.2025-11-05T00:00:00Z