Navegando por Orientadores "SERUFFO, Marcos César da Rocha"

Agora exibindo 1 - 7 de 7

Acesso aberto (Open Access)
Ciência de dados e aprendizado de máquina aplicados ao estudo de variáveis epidemiológica hanseníase na Amazônia
(Universidade Federal do Pará, 2024-12-18) FALCÃO, Igor Wenner Silva; CARDOSO, Diego Lisboa; http://lattes.cnpq.br/0507944343674734; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464
Leprosy is a significant public health problem that largely affects low-income populations. Although the World Health Organization (WHO) establishes guidelines for diagnosis, prevention, and treatment, disease detection faces limitations, often resulting in late or inaccurate diagnoses and leading to serious neurological complications and multidrug-resistant cases. Therefore, early diagnosis is essential to reduce the burden of this disease. Machine learning has been widely used in several areas of science and industry, but especially in health, where it plays an essential role in the analysis and treatment of large volumes of data. In this sense, this thesis investigates the application of a model based on Data Science and Machine Learning to act in the specification of the clinical profile of possible leprosy cases in the Amazon Region and, thus, to be able to act preventively in the early diagnosis and treatment of patients under medical followup. The work takes into account clinical data of patients from a non-public dataset, collected between 2015 and 2020 in the North region of Brazil. Therefore, this thesis proposes a learning model to identify groups clinically affected by the disease using Clustering and Random Forest techniques. In the results obtained, the proposed model demonstrated efficiency in evaluating the probability of individuals being ill, achieving an accuracy of 90.39% in the performance evaluation and identifying a probability of 83.46% of an individual being ill, considering a set of epidemiological and non-generic variables. This approach offers a promising vision for the future of health, allowing the formulation of effective strategies for the early identification of possible cases.
Acesso aberto (Open Access)
Deep learning in education 5.0: proposing 3d geometric shapes classification model to improve learning on a metaverse application
(Universidade Federal do Pará, 2024-01-18) SANTOS, Adriano Madureira dos; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
The Brazilian educational system faces significant challenges, as evidenced by low educational development assessment scores. Due to the traditional educational model employed in the country, there are difficulties in the effective transmission of complex content, leading to high rates of academic failure and subsequent school dropout. The lack of innovation, especially in basic education settings, contributes to a scenario of low mathematical proficiency among Brazilian students. In this context, this work arises as a result of an innovation built to enhance the Geometa application, developed by the Inteceleri company, through the integration of Metaverse and Artificial Intelligence technologies to create an immersive and interactive educational environment. The intention is to train Artificial Intelligence for real-time three-dimensional geometric shape recognition from real-world object images. The proposal aims to mitigate challenges faced in Brazilian basic Mathematics education by adopting innovative technological approaches aligned with Education 5.0, which can be replicated for similar technologies involving the Metaverse. Furthermore, it is also intended to create a dynamic and sustainable educational environment that not only facilitates the mathematical concepts understanding but also promotes active student participation, encouraging their creativity and autonomy in the learning process. The method used relies on the ObjectNet dataset image reclassification from objects to three-dimensional geometric shapes. The reclassified images are used to train CNN, MobileNet, ResNet, ResNeXt, ViT and BEiT Deep Learning models, which are subsequently evalua ted through Machine Learning, inference time and dimension performance measures. Thus, the best-performance Artificial Intelligence model is selected for future integration into Geometa. As contributions of this work, the following were accomplished: (i) the defined models were trained for the three-dimensional geometric shapes recognition; (ii) the models were evaluated through Machine Learning, inference time and dimension performance measures; and (iii) the best-performance model was selected considering the highest assertiveness and smoothness based on models performances analysis. Concerning the obtained results, the ResNet surpassed BEiT, which was the second better performance model, in 5% Precision and 5 Inference Per Second. Finally, the ResNet model reached 84% Precision and 9 Inferences Per Second, being observed as the best-performance Artificial Intelligence for Geometa application integration flow.
Acesso aberto (Open Access)
Estudo sobre persistência e evasão escolar em EJA no nordeste, Castanhal-PA: análise e proposições
(Universidade Federal do Pará, 2019-06-27) XAVIER, Maria do Perpétuo Socorro Ramos; PIRES, Yomara Pinheiro; http://lattes.cnpq.br/5304797342599931; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
Youth and adult education is a specific genre in the basic education, which is aimed to the inclusion of a group of people who were away from the educational process during their childhood or adolescence. Thinking about this thematic a study was designed and named “Persistency and school dropout in the EJA (Youth and Adult Education) in the northeast, Castanhal-PA: analysis and propositions”. With it, it was tried to identify factors which contribute for persistency and dropout of these social actors enrolled in the basic teaching in the EJA modality, in the northeast of Pará, in three municipal schools situated in far neighborhoods, which are formed by student from rural areas. The research was made with students, teachers, principals and specialists in education. We started from the hypothesis that the use of the DTICs (Digital Technologies of Information and Communication) and varied methodologies in context at school which offers the EJA tend to decrease school evasion. The theoretical contribution of this study anchored in authors like Arroyo, Bordieu, Freire, Patto and Fazenda, who talk about the actors inserted in various social contexts which are fundamental to resignify human relations, fair and solidary, and Fernandes, Pires, Ramos and Seruffo, who have “designed” a pedagogical practice in the amazon context of the EJA social actors, emphasizing student’s otherness glimpsing social and teaching work in the dynamics of the institutions. The data were acquired by means of quantitative and qualitative research, selected and analyzed, displaying which school presents the highest evasion and/or school persistency indexes. Rede Bayesiana was used while computer intelligence strategy, by which variables are verified which can be taken into consideration to identify successfully the reasons of evasion and/or school persistency of the EJA students in Castanhal-PA. The reached results show factors, which most contribute for the dropout of these actors of EJA at school, like “low grades”, “lack of interest”, “disease” or “work” matters, like the distribution of frequency of the profile of evaluated students, among others. It was noted, also, that the use of different methodologies in an interdisciplinary perspective and the use of the DTICs in the classrooms tend to decrease school dropout, increasing the persistency of students, enabling the conclusion of the studies in the basic education and, thereby, providing them reading and writing development, the ability to solve problem situation and the search for professional qualification and social insertion.
Acesso aberto (Open Access)
Memórias, etnoconhecimentro: diálogos com estudantes sujeitos da EJAI rural em Cipoal e Vila Modelo, São Francisco do Pará/Pa
(Universidade Federal do Pará, 2024-09-09) TABAYARA, Tiago José da Silva; NASCIMENTO, Eula Regina Lima; http://lattes.cnpq.br/0460051621828656; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
Acesso aberto (Open Access)
Modelo de decisão multicritério para classificar municípios quanto ao risco de violência doméstica contra a mulher: um estudo a partir da Amazônia paraense
(Universidade Federal do Pará, 2024-01-19) SOUZA JÚNIOR, João Lúcio de; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
Violence against women (VAW) is one of the most serious local and global public health issues, requiring effective public policies to tackle it. The aim of this project is to present a multi-criteria decision analysis (MCDA) model based on ELECTRE Tri-B to classify municipalities in the state of Pará according to the risk of violence against women in their territories, in order to map them in descending order in terms of this risk. A model is proposed that considers among the criteria for analysis and classification the existence of support and protection facilities for women in these municipalities, called the Assistance and Protection Index (IAP), as well as socio-economic indicators of the municipalities such as Gross Domestic Product (GDP), Human Development Index (HDI) and Degree of Income Concentration (GINI). The results obtained from the multi-criteria decision model reveal interesting patterns: municipalities with a lower risk of violence against women (VCM), protective equipment and good socio-economic indicators, but a high rate of complaints, corroborating the maxim that environments with more mechanisms to protect women lead to a higher number of complaints. Thus, the methodology used allowed for the identification of municipalities where there is a greater risk of VAW, the mapping of these municipalities and regions, enabling targeted actions that are more likely to be effective in combating and preventing VAW.
Acesso aberto (Open Access)
Mulheres em privação de liberdade e ações voltadas para reinserção social no Centro de Reeducação Feminino em Ananindeua-Pará
(Universidade Federal do Pará, 2021-08-25) GOMES, Daiane Ribeiro; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
The general objective of this work is to understand how the actions of reeducation of women in deprivation of liberty aimed at social reintegration are being offered at the Women's Reeducation Center in Ananindeua – Pará. theme, in addition to an analysis of information from the prison system in Pará regarding actions developed in female incarceration. A qualitative approach was also carried out, which inhabits the interface between functional and interpretive methods, as a process of self-transformation of the human being, that is, as a simultaneously productive and formative process. The results show that, in practice, the actions of re-education for social reintegration take place mainly in partnership with the “S” system. The bakery and microcomputer maintenance course are the most preferred, and the waiter, receptionist, ceramic tile applicator, fabric painting, manicure and pedicure courses are less interested in inmates. There are also workshops focused on the idea of bringing fun and care to the inmates, improving skills that help build a professional profile, so that they can get a job when they leave the prison system. It is imperative to promote the debate on social reintegration and highlight the need for public policies to promote the dignity of women in prison, in accordance with human rights and constitutionally guaranteed fundamental guarantees.
Acesso aberto (Open Access)
Rastreamento de experiência de usuário em sistemas interativos Web
(Universidade Federal do Pará, 2021-11-11) SOUZA, Kennedy Edson Silva de; MELLO JUNIOR, Harold Dias de; http://lattes.cnpq.br/3003315337750206; SERUFFO, Marcos César da Rocha; http://lattes.cnpq.br/3794198610723464; https://orcid.org/0000-0002-8106-0560
The concept of User Experience (UX) has been used to achieve improvements in digital informa- tion systems based on how people perceive them. Considering the digital inclusion movement and the consequent growth in the need to provide a satisfactory user experience, research on UX assessment methods becomes essential to keep up with technological changes and promote the necessary adjustments. Despite the advancement of scientific production in the field of UX, there are still relevant gaps that highlight the need to develop new methodologies and tools that aim to provide more accurate UX assessment, given the growing demand for user-friendly applications and learning, resulting from ongoing technological and social transformations. In this context, the present work aims to develop and evaluate a user experience analysis tool capable of providing qualitative and quantitative artifacts, based on the association of interaction tracking data and UX heuristics. The methodology developed for this exploratory research has as main pillars the quantitative and qualitative methods, based on data obtained from interviews, questionnaires, in addition to the analysis of generated documents and artifacts, eye tracking, mouse, keylogging and machine learning. For the execution of the study, the T2-UXT tool (Tracking Techniques User eXperience Tool) was developed, created to perform interaction data collection by multiple data entries, the tool was evaluated in two case study scenarios. distinct areas of knowledge. For the representation of interaction data, two graphic visualization options were developed, in addition to a metrics analysis table and integration with external algorithms, which allowed for more detailed analysis using Artificial Intelligence. From this it was verified that the T2-UXT is able to assist in the evaluation of UX through artifacts that can be used as a reference for modifications and customizations in graphical interfaces.