Dissertações em Computação Aplicada (Mestrado) - PPCA/NDAE/Tucuruí

URI Permanente para esta coleçãohttps://repositorio.ufpa.br/handle/2011/9399

Navegar

Agora exibindo 1 - 10 de 10

Acesso aberto (Open Access)
Aplicação e comparação de técnicas de classificação automática de documentos: um estudo de caso com o dataset do domínio jurídico “Victor”
(Universidade Federal do Pará, 2024-02-01) MARTINS, Victor Simões; SILVA, Cleison Daniel; http://lattes.cnpq.br/1445401605385329; https://orcid.org/0000-0001-8280-2928
The application of Natural Language Processing (NLP) and Artificial Intelligence (AI) in the Brazilian legal context is a rapidly growing area that can alter the way legal professionals work, given the volume of generated text. Among the possible applications of NLP and AI is the automatic classification of documents, which, among other things, can be employed in the automation of the digitization process of Judicial Proceedings that are still in physical form. Therefore, this work applies and compares AI algorithms for the classification of legal documents. The algorithms are divided into two different approaches. The first approach (I) separates the computational representation process of the text from the classifier training itself and applies SVM and Logistic Regression in conjunction with computational representations based on TF-IDF, Word2Vec, FastText, and BERT. The second approach (II) simultaneously performs the computational representation of documents and the training of the classifier, applying Deep Learning algorithms based on recurrent neural networks, specifically ULMFiT (Universal Language Model Fine-tuning), and HAN (Hierarchical Attention Networks). The studied dataset is named VICTOR, composed of documents from the Supreme Federal Court (STF) of Brazil. The research concludes that both approaches can be applied to the classification of legal documents from the employed dataset. Additionally, despite being less computationally expensive, the classification pipelines of Approach I, which use the computational representation of the document with TF-IDF, yield results equivalent to pipelines employing Deep Learning. Furthermore, embedding documents specialization with data from the dataset under study, improves the performance of pipelines that employ Word2Vec, FastText and ULMFiT, compared to pipelines that apply the generic representations of these, i.e., models pre-trained with data from the general context.
Acesso aberto (Open Access)
Aprendizado em conjunto aplicado à classificação da imagética motora
(Universidade Federal do Pará, 2025-01-20) JORGE, Vitor da Silva; SILVA, Cleison Daniel; http://lattes.cnpq.br/1445401605385329; https://orcid.org/0000-0001-8280-2928
Acesso aberto (Open Access)
A comunicabilidade da interação do usuário idoso com o aplicativo WhatsApp
(Universidade Federal do Pará, 2021-10-25) OLIVEIRA, Regina Mares de Souza; FÜLBER, Heleno; http://lattes.cnpq.br/5018616409948511; MERLIN, Bruno; http://lattes.cnpq.br/7336467549495208; https://orcid.org/0000-0001-7327-9960
The advances in digital technologies and the widespread use of smartphones have greatly changed the way people communicate, mainly through social platforms. At the same time, the sharp growth of the elderly population raises the question of the relationship of the elderly and the new digital media, especially with the Covid-19 pandemic that has conditioned social isolation. This research aims to investigate the communicability of the interaction of elderly users with the WhatsApp application. Methodologically, it began with a systematic review of the literature, later, a case study was conducted with a group of 10 elderly, applied the Communicability Evaluation Method of Semiotic Engineering with the objective of knowing and explaining the communicative problems of use and relating them to the characteristics of the elderly. The results indicated interaction problems related to the attribution of meaning, perception, recognition of icons; indicated the most frequent communicability ruptures; indicated low vision as the most common change of aging; presented reports of the experiences of use of the elderly and also regarding the satisfaction and classification of the service.
Acesso aberto (Open Access)
Desenvolvimento de um sistema web para auxílio do processo de ensino-aprendizagem de lógica de programação aplicado ao novo ensino médio
(Universidade Federal do Pará, 2024-06-28) MEDEIROS, Ederson José Andrade; ALVES, Elton Rafael; http://lattes.cnpq.br/8408339809247090; https://orcid.org/0000-0003-2148-8941
Educational technologies have played a crucial role in enhancing the teaching-learning process, offering innovative solutions that contribute to a more dynamic and effective education. Despite the development of various tools aimed at different areas of knowledge, gaps still exist in certain subjects, such as programming logic within the context of the New High School. This study proposes the creation of a web-based system for teaching and learning programming logic, specifically designed for New High School students. The system is intended to be an efficient and accessible tool, capable of facilitating the understanding of complex programming concepts. Based on an educational requirements survey and usability tests, the platform was developed to meet the needs of students, providing an intuitive and interactive learning experience. This study was conducted in the city of Belém do Pará. The results obtained regarding the use of the application by participants show a considerable level of satisfaction (over 60%), demonstrating that the application can be used by any student wishing to learn programming logic both inside and outside the school environment.
Acesso aberto (Open Access)
Experiência na implementação de um modelo de gestão de PD&I em um grupo de empresas paraenses com o uso de ferramentas digitais e práticas ágeis
(Universidade Federal do Pará, 2024-08-05) OLIVEIRA, Aline Santos de; COSTA, Anderson Jorge Serra da; http://lattes.cnpq.br/7707885586024191; REIS, Rodrigo Quites; http://lattes.cnpq.br/9839778710074372; https://orcid.org/0000-0002-3657-4175
This dissertation explores the implementation of a Innovation management model in a group of companies of the Pará state in Brazil, using digital tools and agile practices. The objective of the research is to evaluate the effectiveness of these approaches in improving innovation processes, an essential factor for the economic growth and competitiveness of organizations. The study focused on the application of a methodology compatible with the Brazilian RD&I Management Model (MGPDI, in Portuguese) in three companies selected through a open competition ruled by a Science and Technology Park. The methodology for this research included a systematic literature review, case study, interviews with investors and project leaders, as well as a qualitative analysis of the data collected. The results reveal that the adoption of digital tools such as Trello, Jira, Ocomon and Taiga, combined with agile practices, provides benefits such as greater adaptability, better collaboration, greater transparency and reduced operational costs. However, it should be noted that the implementation of this management model brings challenges, such as organizational resistance to change and the need for continuous training of teams. Therefore, it must be assumed that the integration of digital tools and agile practices in RD&I management can considerably improve companies' innovation capacity, fostering an organizational culture of adaptability and resilience. Thus, the recommendations generated by this research made it possible to prepare an executive summary, describing how the implementation of the MGPDI contributes to sustainability and competitiveness in the business context of the Pará state.
Acesso aberto (Open Access)
Fatores críticos para a implantação de melhorias de serviço de TI: um estudo em instituições públicas de ensino superior
(Universidade Federal do Pará, 2020-12-14) MENEZES, Gilberto Fabricio Malheiros; SANTOS, Viviane Almeida dos; http://lattes.cnpq.br/1489376127395764; REIS, Rodrigo Quites; http://lattes.cnpq.br/9839778710074372; https://orcid.org/0000-0002-3657-4175
This research was dedicated to the Information Technology Services Management (GSTI) area, more specifically in the study of the factors that influence the process of implementing improvements in IT service processes, in view of the growth in the service management area. based on Information Technology (IT). Today, associations are required to continually seek to improve IT services, in order to provide them with quality, and to meet internal and external needs. From the above, the objectives of this study are: 1) basic diagnoses of success (FCS) and resistance (FCR) are crucial for the implementation of IT service improvements; 2) identify the degree of promotion of FCS and FCR within public Higher Education Institutions (HEIs); 3) define strategies for overcoming and / or enhancing the FCS and FCR. In order to achieve these objectives, a three-step survey was developed. The first sought, through a systematic mapping of the literature, aimed to identify which are these FCS and FCR. As a result, 41 FCS and 13 FCR were identified. In the second stage, surveys were carried out with 110 IT professionals from 24 public HEIs in the state of Pará and from the Cooperation Network with the Federal University of Rio Grande do Norte (UFRN). The results reaffirm a cause of the factors: support from senior management (FCS1); alignment between IT and business (FCS9); well-defined processes (FCS2); lack of technical resources and support (FCR2); lack of knowledge and skills (FCR3). The third stage collected data through classification with 11 managers and former IT managers of public HEIs in the North of Brazil to establish which actions can be developed or improved to face the factors. All the discoveries made by the author resulted in the writing of three scientific papers. The results, in short, point to a common perception within the public HEIs about the importance of the studied factors and that coping is possible by a number of strategies: awareness senior management through the exposure of benefits; carrying out training and qualification activities; cultivation of healthy interpersonal relationshipss; process mapping; resource management; use of specific tools; implementation of management techniques.
Acesso aberto (Open Access)
Implementação de modelos computacionais na predição temporal e espaço-temporal de parâmetros de qualidade de água
(Universidade Federal do Pará, 2021-12-14) ALMEIDA, Anderson Francisco de Sousa; MERLIN, Bruno; http://lattes.cnpq.br/7336467549495208; HTTPS://ORCID.ORG/0000-0001-7327-9960; GONZÁLEZ, Marcos Tulio Amaris; http://lattes.cnpq.br/9970287865377659
The quality of water is directy related to is level of pollution caused by anthropic and industrial actions, with a consequent reduction in the availability of quality water. Therefore, limological monitorig of the basic parameters os water quality is carried out, as away of obtaining data that guide the decision-making of water resouces management bodies. In this context, the present study has the implementation of machine learning algorithms to predict temporal and spatiotemporal water quality parameter data. The ML techniques used were linear regression, ramdom forest, MLP and LSTM neural networks. Two collection points from a Water Resources Management Unit in São Paulo, Brazil were used. Models are evaluated using MAPE( mean absolute percentage eror) and RMSE( root mean squared erro) metrics. Therefore, in temporal prediction, the LSTM technique presented the best performace in relation to the other techniques and the data used, as it has the lowest average RMSE result, with 2.47. However, in spatiotemporal prediction, MLP has the best performace both in relation to the other techniques and the data used , as it has the lowest averagee results of MAPE and RMSE, respectively, 5.94% and 1.34. Thus, these performaces of neural networks can be justified by the non-linearity of the parameter data. Other than that, the results of the experiments aim to contribute to the water quality monitorng process and assist in the planning of water management, so that it meets current legislation and enales the indication of public policies, through machine learning models in prediction of water quality parametes.
Acesso aberto (Open Access)
PredictmodelGUI: ferramenta para classificação de genes essenciais através de técnicas de aprendizado de máquina
(Universidade Federal do Pará, 2025-06-06) MOIA, Gislenne da Silva; SILVA, Cleison Daniel; http://lattes.cnpq.br/1445401605385329; HTTPS://ORCID.ORG/0000-0001-8280-2928; VERAS, Adonney Allan de Oliveira; http://lattes.cnpq.br/2201652617167877; https://orcid.org/0000-0002-7227-0590
DNA sequencing technologies have provided significant advances in the understanding of the genetic content of numerous organisms, ranging from microorganisms to humans. Among the analyses performed in the Omics Sciences, Annotation stands out as one of the most important. Conceptually, this process consists of inferring biological information from genomic sequences, which allows researchers to understand the function of genetic products, such as Genes — the Basic Units of Heredity responsible for the physical and hereditary characteristics of an organism. Some Genes perform vital functions by encoding Proteins or RNAs essential for processes such as Cellular Metabolism, which participate in crucial pathways like Glycolysis and the Tricarboxylic Acid Cycle. Sequencing Platforms have started to generate large volumes of data, which has driven advances in the Omics fields and fostered the development of computational methods aimed at diverse analyses. More recently, Machine Learning and Artificial Intelligence techniques have been applied to these data, with studies demonstrating the effectiveness of biology-inspired approaches. These models do not require rule-based programming, although their creation still demands advanced skills in Programming and Computing. To contribute toward solving this challenge, this study presents PredictModelGUI, a graphical interface developed in Python that implements nine models to classify Essential Genes. The interface allows importing datasets, re-training models, and adjusting parameters. The information is stored in the software database, which ensures traceability and provides a simple and intuitive tool to test different configurations. Available
Acesso aberto (Open Access)
Sistematização de um mecanismo de busca especializado em conteúdos das séries iniciais do ensino fundamental: uma abordagem baseada em mineração de texto
(Universidade Federal do Pará, 2021-11-08) PONTIN JUNIOR, Laercio; VERAS, Adonney Allan de Oliveira; http://lattes.cnpq.br/2201652617167877; HTTPS://ORCID.ORG/0000-0002-7227-0590; FÜLBER, Heleno; http://lattes.cnpq.br/5018616409948511
The technology is inserted in the most diverse environments of society, however, at times its use can be improved, as in the case of web search engines. Search tools on the web, when used by elementary school children, can lead to a complex environment that hinders learning. Such an occurrence is due to the little familiarity of children in formulating questions related to what they need to learn and the difficulty in interpreting the results. Due to this difficulty, this work proposes a search engine that improves the search string considering what governs the Base Nacional Comum Curricular. To implement this mechanism, text mining is used, to improve the environment for children's learning. As a form of evaluation, elementary school students were used together with the collaboration of teachers with the same profile. Thus, it is possible to evaluate the use of the tool and conclude the occurrence of improvement in educational search results when using a tool that applies text mining techniques in a search engine.
Acesso aberto (Open Access)
Uso de redes de sensores sem fio no monitoramento do comportamento nictemeral do caranguejo-uçá (Ucides cordatus Linnaeus, 1763)
(Universidade Federal do Pará, 2020-12-18) CARDOSO, Gracielly Costa Fontes; LEMOS, Marcus Vinicius de Sousa; http://lattes.cnpq.br/3407671588647224; FÜLBER, Heleno; http://lattes.cnpq.br/5018616409948511
Wireless Sensor Networks (RSSF) have been applied in environments with dif erent contexts. One of the advantages of its use is low intrusion, made possible by remote monitoring that allows the observation of data without the need for invasion of the habitat of some species. In this article, we present the design and implementation of an RSSF that monitors environmental variables and the behavior of the uçá crab (Ucides cordatus). According to the results obtained in the study, it was identified that the WSN are suitable for collecting data in the mangrove ecosystem ef iciently. Such information can be used in decision-making by regulatory agencies that manage the management of this resource.

Navegar

Navegando Dissertações em Computação Aplicada (Mestrado) - PPCA/NDAE/Tucuruí por CNPq "CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO"