http://repositorio.ufc.br/handle/riufc/71 Wed, 17 Jun 2026 11:32:49 GMT 2026-06-17T11:32:49Z http://repositorio.ufc.br/handle/riufc/86795 Título: Aprimoramento do método de análise de componentes principais para matrizes com dados intervalares Autor(es): Monte, Lucas Gonçalves Abstract: Principal Component Analysis (PCA) is a multivariate statistical technique that performs a linear transformation on a data set composed of observations and interrelated variables, which forms a new data set. This new set has uncorrelated or less correlated variables, and its dimension may be smaller than the original set. The main objectives of the PCA technique are: (i) to extract more relevant information from the observed set; (ii) to compress this set; and (iii) to simplify the description of the data set. It is a technique widely used in several contexts, such as the development of psychometric scales, neuroscience, identification of process failures, grouping or classification of information, among others. However, in everyday life, it is common to encounter situations in which the data set has uncertain values. So, the Classical PCA method will have difficulty in providing a satisfactory solution without adequate treatment from uncertain data, which may be dealt with by using interval mathematics. Thus, it is interesting to develop techniques for PCA in its interval context so that uncertainty can be considered in its data analysis, and this needs to be done without increasing the dimension of the data matrix in order to avoid a large increase in computational cost. Therefore, a new modeling of the interval data matrix is proposed to find the appropriate covariance matrix and, from this, apply the methods to find interval eigenvalues and eigenvectors in such a way that a linear transformation can be applied and interval principal components obtained. Tipo: Dissertação Wed, 01 Jan 2025 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86795 2025-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86136 Título: Algorítimo de busca em vizinhança com q-learning para a resolução do no-idle flow shop para minimização do atraso total Autor(es): Ramos, Diego Guilherme Ferreira Abstract: This work addresses the No-Idle Permutation Flow Shop Problem (NIPFSP) to Minimize Total Tardiness. Initially, a Mixed Integer Linear Programming (MILP) model and a Mixed-Integer Quadratically Constrained Programming (MIQCP) model were proposed, aiming to structure the modeling foundations of the problem. The MILP and MIQCP models were computationally implemented, and their characteristics were validated. Exact experiments revealed the effectiveness of the MILP model in producing high-quality solutions for instances with the number of jobs ranging between 20 and 100 and with up to 5 machines. However, for problems with 10, 15, and 20 machines, the MILP model was unable to prove optimality within the established time limit, pointing to the need for approximate methods. Therefore, a hybrid metaheuristic was proposed that combines intensive local search with reinforcement learning (Q-learning) to adaptively explore the solution space in more difficult instances, named Iterated Noisy Local Search Q-learning (INLSQL), which was compared with other existing heuristic algorithms. Substantial performance gains were achieved through the Q-learning-guided strategy compared to the main algorithms reported in the reviewed literature. Tipo: Dissertação Sun, 01 Mar 2026 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86136 2026-03-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86088 Título: Uma visão sobre a gestão escolar no desempenho educacional no Ceará: uma análise quantitativa da evolução do SAEB (2005-2023) e do ICG (2023) Autor(es): Maia, Priscila de Sousa Cunha Abstract: This dissertation investigates the relationship between school performance indicators and the characteristics associated with school management in the state of Ceará, based on data from the Basic Education Assessment System (SAEB) and the School Census from 2005 to 2023, as well as the School Management Complexity Indicator (ICG), used exclusively for the year 2023. The study seeks to understand how effective management practices, aligned with public policies focused on learning, influence the results of Portuguese Language and Mathematics tests, considering the proficiency averages of municipal networks in SAEB basic education. A quantitative approach is adopted, with analysis of secondary data extracted from the National Institute for Educational Studies and Research Anísio Teixeira (INEP), applying descriptive statistics, correlations, analysis of variance (ANOVA), and least significant difference (LSD). The analysis highlights the municipality of Fortaleza, enabling comparisons with other municipal networks in Ceará. The results indicate that although Ceará has shown significant progress—possibly driven by programs such as the Literacy at the Right Age Program (PAIC)—Fortaleza performed below the state average. Conversely, smaller unicipalities, including those in rural areas, achieved higher averages, demonstrating that a well-structured pedagogical management can offset limitations related to scale and resources. The analysis of variance (ANOVA) reinforced the lower internal inequality in Ceará compared with the national pattern, while Fortaleza showed better performance in low-complexity schools. These findings suggest that improvements in learning are associated with pedagogical leadership, systematic monitoring of results, and management capacity responsive to the school context, providing concrete insights for public school systems seeking to promote equity and quality in education. Tipo: Dissertação Wed, 01 Jan 2025 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86088 2025-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/85562 Título: Uma proposta metodológica para distribuição de recursos do PDDE a partir de critérios de eficiência e necessidade com aplicação de análise envoltória de dados Autor(es): Fossile, Marcelo Gomes Abstract: This study proposes a methodology for the allocation of resources from the Programa Dinheiro Direto na Escola (PDDE) among Brazilian states, guided by criteria of technical efficiency and need, using Data Envelopment Analysis (DEA) as a supporting tool for measuring relative performance. The analysis considers a financial input and two sets of outputs: structural variables expressed in absolute values, which reflect the installed capacity of education systems, and educational indicators expressed as ratios, which capture performance outcomes. The models were implemented in Python using the Pyomo library and solved with the GLPK solver. Based on the efficiency scores, the potential savings associated with projecting units onto the efficient frontier are estimated and used as a reference for defining the amount of resources to be allocated, which may be adjusted according to criteria established by public managers. In the subsequent stage, a parametric model is developed that combines relative efficiency with a need index composed of eight indicators, weighted by the parameter λ ∈ [0,1], allowing the simulation of scenarios ranging from efficiency-oriented allocation to greater emphasis on vulnerability. The results reveal distinct territorial patterns in both efficiency and levels of need, highlighting how different weighting choices between these two dimensions affect the final allocation of resources. The proposed approach provides a transparent quantitative tool to support public policy decisions aimed at optimizing federal investments in basic education. Tipo: Dissertação Thu, 01 Jan 2026 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/85562 2026-01-01T00:00:00Z