DSpace Communidade:https://repositorio.uema.br/jspui/handle/123456789/19152026-08-13T14:07:39Z2026-08-13T14:07:39ZAcessibilidade Urbana facilitada por um protótipo de sistema para PcDhttps://repositorio.uema.br/jspui/handle/123456789/63532026-08-03T17:44:46Z2024-01-01T00:00:00ZTítulo: Acessibilidade Urbana facilitada por um protótipo de sistema para PcD
Abstact: This work shows results from the development of a prototype system with a focus on
urban accessibility that serves various types of People with Disabilities (PwD), in
addition, an academic research questionnaire was applied aiming to amplify the vision
regarding the main topic addressed, as well how to evaluate the use of the proposed
system solution. The objective of this research is to contribute to society through social
inclusion and applicability of the future solution in smart cities, starting through the
experiment on an academic campus. This article also delves into technological and
social aspects that can serve as a reference for consultations by researchers, public
and private bodies who seek depth in their studies. However, as the topic is of great
relevance, it is clear that this line of research is still little explored, especially in Brazil,
given the limited number of articles available.2024-01-01T00:00:00ZAnálise da robótica educacional como instrumento pedagógico no desenvolvimento escolar do ensino fundamental da rede públicahttps://repositorio.uema.br/jspui/handle/123456789/63432026-07-30T17:14:52Z2024-01-01T00:00:00ZTítulo: Análise da robótica educacional como instrumento pedagógico no desenvolvimento escolar do ensino fundamental da rede pública
Abstact: The present research deals with the analysis of educational robotics as a pedagogical tool in the
school development of 5th-grade students in the public school system of Santa Rita-MA. It
concerns a study project on the combination of educational robotics and its contribution to
Mathematical Logical thinking allied with technology in the early grades of elementary
education. Its objectives are to compare traditional methods of teaching mathematics with
active methodologies that use educational robotics; stimulate students' interest in the proposal;
analyze the problem-solving ability of the presented problems; evaluate students' cognitive
development focused on enhanced mathematics learning with the support of robotics kits, and
identify which Computational Thinking skills (pattern recognition, decomposition, algorithms,
and abstraction) are related to mathematical logic. The investigation has a practical and
exploratory nature, with a qualitative and quantitative approach, of an applied nature, using
procedures such as case studies and action research, through the conduct of classes, workshops,
and the application of evaluative questionnaires in the initial and final phases of the research.
Based on the results and findings, it was observed through the case study that educational
robotics not only stimulates and interests children in mathematics but also significantly
improves academic performance in that area of knowledge. However, it was not possible to
effectively compare traditional methods of teaching mathematics with active methodologies
that use educational robotics. Therefore, the research concludes that educational robotics,
although it promotes various benefits as a practical teaching methodology, requires resources
such as collaborative work, a multidisciplinary team, and adequate funding to have effective
relevance2024-01-01T00:00:00ZAlucinações em modelos de IA Generativa: limitações e desafios na compreensão da linguagem humanahttps://repositorio.uema.br/jspui/handle/123456789/63162026-07-22T14:01:52Z2024-05-31T00:00:00ZTítulo: Alucinações em modelos de IA Generativa: limitações e desafios na compreensão da linguagem humana
Abstact: Chatbots are artificial intelligence systems that simulate human interactions and have been widely used in diverse areas, from customer service to content creation. However, despite advances in technology, chatbots still present limitations and challenges, such as the tendency to make mistakes and the difficulty in dealing with
complex questions and nuances of human language. These errors are known as hallucinations and can be caused by several factors, such as a lack of common sense, biased data and limitations in the models' ability to deal with non-existent or unrepresented information in the data. Chatbot hallucinations can have significant
impacts in several areas, such as education, customer service and content creation. For example, a chatbot that cannot understand the nuances of human language may provide inappropriate or incorrect responses, which can lead to a negative user experience. Additionally, chatbots can perpetuate social bias and discrimination if they are trained on biased data. To deal with these limitations in the educational context, it was proposed the development of a chatbot for teaching programming in Python that uses advanced natural language processing techniques to reduce hallucinations when learning the language.2024-05-31T00:00:00ZEstimativas de arrecadação do ICMS do Estado do Maranhão usando algoritmos de machine learninghttps://repositorio.uema.br/jspui/handle/123456789/62792026-07-08T14:14:01Z2025-01-01T00:00:00ZTítulo: Estimativas de arrecadação do ICMS do Estado do Maranhão usando algoritmos de machine learning
Abstact: Tax collection forecasting is a cornerstone of fiscal planning and efficient public
management. The Tax on Circulation of Goods and Services (ICMS) constitutes the
main source of revenue for Brazilian states, and its accurate projection is crucial
for allocating resources to strategic areas. However, the complexity of its dynamics,
influenced by non-linear macroeconomic variables, and the lack of studies applied
to the reality of the state of Maranhão pose a challenge for public administrators.
This work aims to address this gap by investigating how machine learning
techniques can improve the accuracy of forecasting monthly ICMS revenue in
Maranhão. The overall objective is to develop and validate advanced computational
models using a historical series of economic and social data from January 1997
to April 2024. This quantitative and applied research adopted the CRISP-DM
framework. Data were collected from public sources such as SEFAZ-MA, IBGE,
and the Central Bank. Initially, nineteen independent variables were considered,
and a Multiple Linear Regression model was used to select the most relevant ones,
such as GDP, diesel consumption, and electricity consumption indicators. Four
machine learning algorithms were implemented, compared, and validated:
Random Forest, Decision Tree, Linear Regression, and XGBoost. Performance
evaluation was performed using the RMSE, MAE, MAPE, SMAPE, and R² metrics,
using the k-fold cross-validation technique (with k=10) and a data split of 80% for
training and 20% for testing. This study contributes a practical and validated
model that can be integrated into the state's budget planning process, promoting
more transparent, efficient, and data-driven fiscal management2025-01-01T00:00:00Z