https://ri.ufs.br/jspui/handle/riufs/2557 Sun, 06 Sep 2026 18:09:13 GMT 2026-09-06T18:09:13Z https://ri.ufs.br/jspui/handle/riufs/25851 Título: Análise da inadimplência de Microempreendedores Individuais (MEI) no estado de Sergipe : uma abordagem estatística baseada em aprendizado não supervisionado Autor(es): Ramiro, Willyane Maria da Conceição Abstract: This study analyzed the default rate of Individual Microentrepreneurs (MEIs) in the state of Sergipe, considering the growing economic relevance of MEIs in the Brazilian scenario and the financial impacts resulting from non-compliance with tax and credit obligations. The research aimed to identify socioeconomic, financial, and behavioral patterns associated with the default rate of Sergipe's MEIs, using a statistical approach based on Gower's Distance and the K-Medoids (PAM) clustering technique. Methodologically, the research was characterized as quantitative, descriptive, and applied, using secondary data extracted from the Open Data Portal of the Central Bank of Brazil, referring to the period from January to December 2024. The analyses were performed using RStudio software, involving procedures for processing, normalization, and clustering of qualitative and quantitative variables. The results showed a predominance of males among the analyzed micro-entrepreneurs (MEIs), a higher concentration of default among entrepreneurs with intermediate incomes, and a strong relationship between the use of loans and financing and an increased risk of default. Statistical segmentation allowed the identification of six distinct clusters, demonstrating heterogeneous profiles of financial behavior among micro-entrepreneurs. It is concluded that factors such as poor financial organization, frequent use of credit, and limitations related to economic planning directly influence the levels of default among MEIs in Sergipe, reinforcing the need for actions focused on financial education, strengthening business management, and developing public policies to support small entrepreneurs. Fri, 24 Jul 2026 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/25851 2026-07-24T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/25795 Título: Predição da necessidade de hospitalização em pacientes com Chikungunya utilizando técnicas de aprendizado de máquina no estado de Sergipe Autor(es): Santos, Wanderson Alves dos Abstract: Chikungunya fever is a major public health concern in Brazil, characterized by high incidence rates and the potential for severe clinical outcomes, particularly in the Northeast region. This study aimed to develop predictive models based on machine learning techniques to estimate the need for hospitalization among patients with confirmed chikungunya infection in the state of Sergipe. Secondary data were obtained from the Notifiable Diseases Information System (SINAN), covering the period from 2020 to 2025. The study adopted an observational, retrospective, and quantitative design, analyzing sociodemographic characteristics, clinical manifestations, and pre-existing comorbidities. Given the pronounced class imbalance in the outcome variable, with only 5.1% of confirmed cases resulting in hospitalization, an oversampling technique was applied to mitigate bias during model training. Logistic Regression, Naive Bayes, Decision Tree, Bagging, and Random Forest models were evaluated. The results showed that data balancing substantially improved the identification of the minority class. Among the evaluated models, Logistic Regression and Naive Bayes achieved the best performance, reaching a sensitivity of 0.769 and areas under the receiver operating characteristic curve (AUC) of 0.790 and 0.808, respectively. Additionally, the interpretation of the odds ratios from Logistic Regression allowed the identification of the main factors associated with hospitalization, highlighting leukopenia (OR = 7.47), white race/color (OR = 4.91), black, brown, or indigenous race/color (OR = 3.49), autoimmune diseases (OR = 3.08), hematological diseases (OR = 2.28), as well as the clinical manifestations of vomiting and arthritis. The findings suggest that Logistic Regression is the most suitable approach for the analyzed context, as it combines satisfactory predictive performance with high interpretability. Consequently, it may support the early identification of patients at greater risk of hospitalization and contribute to strengthening epidemiological surveillance and public health decision-making. Wed, 22 Jul 2026 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/25795 2026-07-22T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/24798 Título: Perfil da violência doméstica e familiar contra a mulher em Estância/SE : uma abordagem baseada em Business Intelligence Autor(es): Santos, Diego Silva Barbosa dos Abstract: This study analyzes the profile of domestic and family violence against women in the municipality of Estância, Sergipe, Brazil, aiming to demonstrate the effectiveness of applying Business Intelligence (BI) tools in public security data management. The research is characterized as quantitative and descriptive, based on documentary data collected from the Center for Analysis and Research in Security and Citizenship (NAPSEC) of the Sergipe State Department of Public Security (SSP/SE). The temporal scope covers the historical series from 2019 to 2024 and includes victims who agreed to receive follow-up assistance from the Maria da Penha Patrol. Data processing and visualization were carried out using Microsoft Power BI, enabling the development of interactive dashboards. The results revealed a spatial concentration of incidents in the Cidade Nova and Centro neighborhoods, as well as a predominant profile of victims who self-identify as mixed-race, experience economic vulnerability, and have children with the aggressor. Regarding perpetrators, most were identified as former partners, many with a history of recidivism. A significant increase in the number of cases was also observed in 2024. The study concludes that data structuring through BI provides an accurate diagnostic framework to support the Maria da Penha Patrol and public managers in strategic decision-making and in breaking the cycle of violence. Tue, 03 Mar 2026 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24798 2026-03-03T00:00:00Z https://ri.ufs.br/jspui/handle/riufs/24796 Título: Análise e previsão da taxa de ocupação hospitalar em um hospital privado de Sergipe Autor(es): Cunha, Jacinto Michael Menezes Abstract: This study analyzes and forecasts the hospital occupancy rate in a private hospital in Sergipe, Brazil, using patient-day and bed-day data from 2022 to 2025. The monthly series are segmented by accommodation type (Private Room, Ward, and ICU). The research adopts a quantitative approach, is applied in nature, and follows an observational, retrospective, and documentary design. Data were extracted from the TASY electronic health record (EHR) system, followed by ETL (Extract, Transform, Load) stages and exploratory analysis to characterize the patient occupancy profile by accommodation type. Subsequently, monthly time series of the occupancy rate were constructed for each category. The study performed stationarity tests, decomposition, and autocorrelation analysis, fitting classical time series models (ARIMA and additive ETS/Holt-Winters) alongside an XGBoost machine learning model. The models were evaluated using MAE, RMSE, and MAPE metrics on training and test sets, and compared in consolidated tables by accommodation type for the 2022–2025 period. The results indicate that XGBoost generally yields a lower MAPE for Private Rooms and the ICU, while the ETS(A,N,A) model proved more suitable for the Ward series regarding projection behavior. Forecasts for 2026 suggest that occupancy levels will remain similar to those observed at the end of 2025, with moderate seasonal variation. The study concludes that the combination of classical time series and XGBoost is useful for supporting tactical bed and resource planning, allowing for the anticipation of periods of high clinical demand, reducing the risks of overcrowding or idle capacity, and providing a basis for management decisions based on the local reality of the analyzed hospital. Wed, 04 Mar 2026 00:00:00 GMT https://ri.ufs.br/jspui/handle/riufs/24796 2026-03-04T00:00:00Z