DSpace Coleção:https://repositorio.ufms.br/handle/123456789/23422026-04-02T01:32:04Z2026-04-02T01:32:04ZInfraestrutura de Blockchain para Aplicações da Plataforma Pecuária de Baixo Carbono da Embrapahttps://repositorio.ufms.br/handle/123456789/143272026-03-04T17:43:21Z2025-01-01T00:00:00ZTítulo: Infraestrutura de Blockchain para Aplicações da Plataforma Pecuária de Baixo Carbono da Embrapa
Abstract: Livestock farming is one of Brazil's main economic activities. Given growing global concerns about climate change, Embrapa has launched concept brands that function as quality seals to encourage the adoption of more sustainable practices in the sector. This work aimed to develop and evaluate a blockchain infrastructure, as a proof of concept, for decentralized applications aimed at certifying products under the concept brands of Embrapa's Low Carbon Livestock Platform (PBC). The infrastructure was implemented with the Hyperledger Fabric framework on a set of virtual machines hosted on Amazon Web Services (AWS). Its performance was evaluated using Hyperledger Caliper, considering scenarios with different transaction volumes and sizes, as well as variations in the network ordering mechanism. The results indicated that the infrastructure stably supports a continuous write rate of 2250 KB/s. Conversely, average rates of 4500 KB/s exceed the network's capacity, resulting in a backlog of pending transactions. Transaction granularity did not significantly impact performance, while increasing the number of ordering nodes significantly reduced performance. We conclude that the proposed infrastructure is technically feasible to support certification applications linked to PBC brands, offering the potential to contribute to traceability and data reliability in the sustainable livestock production chain.
Tipo: Dissertação2025-01-01T00:00:00Z"Projeto ConsciêncIA: Uma Plataforma para Auxílio no Ensino de Inteligência Artificial na Educação Básica”https://repositorio.ufms.br/handle/123456789/124422025-08-13T17:43:39Z2025-01-01T00:00:00ZTítulo: "Projeto ConsciêncIA: Uma Plataforma para Auxílio no Ensino de Inteligência Artificial na Educação Básica”
Abstract: Artificial Intelligence (AI) has brought changes to several sectors of
society, requiring new skills, especially in the educational field. In Brazil, initiatives
aimed at AI literacy in Basic Education are still scarce, particularly in
teacher training. To address this gap, the web-based educational platform Projeto
ConsciêncIA was developed as part of an extension project of the Faculty
of Computing at UFMS. The platform targets pre-service teacher training, offering
an interactive mini-course on the fundamentals of AI. This study presents
three stages: a Systematic Literature Review (SLR) that theoretically supports
the proposal; the platform development; and its implementation with 148 undergraduate
teaching students. The collected data indicate that participants
held misconceptions about AI, highlighting the importance of introductory educational
initiatives. After completing the mini-course, they reported a greater
understanding of basic AI concepts and increased confidence in addressing the
topic in their future teaching practice. This work serves as an initial experience
in developing educational materials on AI for teacher training in Brazil.
Tipo: Dissertação2025-01-01T00:00:00ZMODELO DE INTELIGÊNCIA ARTIFICIAL PARA IDENTIFICAR MEDICAMENTOS EM PROCESSOS DE JUDICIALIZAÇÃO NO TRIBUNAL DE JUSTIÇA DO ESTADO DE MATO GROSSO DO SULhttps://repositorio.ufms.br/handle/123456789/121362025-07-04T20:42:35Z2025-01-01T00:00:00ZTítulo: MODELO DE INTELIGÊNCIA ARTIFICIAL PARA IDENTIFICAR MEDICAMENTOS EM PROCESSOS DE JUDICIALIZAÇÃO NO TRIBUNAL DE JUSTIÇA DO ESTADO DE MATO GROSSO DO SUL
Abstract: The healthcare judicialization in Brazil has posed significant challenges to the Unified Health System (SUS), especially with respect to the provision of medicines. At the Court of Justice of the State of Mato Grosso do Sul (TJMS), the growing number of lawsuits related to demands for medicines impacts public policies and requires innovative technological solutions. With the consolidation of the electronic case files, there is a wealth of information to be explored in procedural texts which, once extracted and organized, becomes a powerful tool for management and governance. This study aims to apply an artificial intelligence (AI) model capable of automatically identifying medicines names mentioned in the initial petitions of judicial records, using text-mining and machine-learning techniques focused on case files documents written in Portuguese. The model was trained with transformer-based algorithms, particularly BioBERTpt. After generating the data, an interactive computational platform called MED-SUS-MS was implemented to visualize data related to the healthcare judicialization at TJMS, in order to support decision-making in public policies for medicines provision in the State of Mato Grosso do Sul. The methodology involved constructing an anonymized dataset, applying Named Entity Recognition (NER) techniques, and evaluating the model’s performance using metrics such as precision, recall, and F1-score. The results demonstrate the technical feasibility and institutional relevance of the proposed model, enabling greater transparency, agility, and evidence-based formulation of public health policies. The model is aligned with the guidelines and resolutions of the National Council of Justice (CNJ) and TJMS, promoting ethical and secure governance within the Judiciary and directly contributing to Sustainable Development Goals (SDGs) 3 – Good Health and Well-being and 16 – Peace, Justice and Strong Institutions. This research reinforces the potential of artificial intelligence as a strategic tool for the healthcare de-judicialization by transforming judicial data into qualified inputs for public management and governance.
Keywords: artificial intelligence, named entity recognition, medicines mining, healthcare judicialization and unified health system.
Tipo: Dissertação2025-01-01T00:00:00ZAnálise da Compreensão dos Professores dos Institutos Federais sobre a Gamificação e sua Modalidade Desplugadahttps://repositorio.ufms.br/handle/123456789/121262025-07-04T15:05:54Z2025-01-01T00:00:00ZTítulo: Análise da Compreensão dos Professores dos Institutos Federais sobre a Gamificação e sua Modalidade Desplugada
Abstract: Although Gamification is increasingly being researched in the educational context, there are still few studies that investigate teachers' views on the subject. Furthermore, the few studies addressing the topic describe specific initiatives for teacher training with the use of Gamification in different disciplines. To address this challenge and identify teachers' perceptions of Gamification, we conducted a quantitative study with teachers from IFs from all regions of the country. In the study, we mapped the pedagogical practices that involve Gamification and identified that only 17.58\% of the interviewees are familiar with the current concepts related to Gamification, with and without the use of technology, confirming that the topics are still little known.
Tipo: Dissertação2025-01-01T00:00:00Z