https://tede.unioeste.br/handle/tede/5723 Mon, 18 May 2026 13:59:38 GMT 2026-05-18T13:59:38Z https://tede.unioeste.br/handle/tede/8355 Title: Elaboração e avaliação de um catálogo de requisitos não-funcionais em um contexto de domínio de aplicação de diplomas digitais Autor: GILNEK, Vitor Luiz Caldeira Primeiro orientador: Santander, Victor Francisco Araya Abstract: The adoption of the Digital Diploma in Brazil has created a context in which issuance and registration systems must comply with particularly rigorous quality standards. However, there is a lack of a systematized and structured definition of non-functional requirements (NFRs) for this domain, which hinders consistent specification and compromises well-founded architectural decision-making. This work addresses this gap by proposing a systematized catalog of NFRs for the Digital Diploma domain, motivated by the need to guide the development of more robust solutions aligned with regulatory requirements. The objective of this research was to design, model, and validate a catalog based on the NFR Framework, represented through Softgoal Interdependency Graphs(SIGs).Themethodologycombinedlegislativeanalysis,anobservational study of a real-world system, a Systematic Literature Review, application of the ATAM method, SIG modeling, expert validation through a survey, and a Proof of Concept to assess practical applicability. The results indicate that the catalog is comprehensive, technically consistent, and considered useful by specialists, while also demonstrating applicability in real-world scenarios. The proposed operationalizations showed potential to support architectural decision-making and inspire functionalities in other systems. Thus, this work delivers an updated and applicable artifact that contributes to the development of more secure and interoperable Digital Diploma systems. Publisher: Universidade Estadual do Oeste do Paraná Tipo do documento: Dissertação Thu, 18 Dec 2025 00:00:00 GMT https://tede.unioeste.br/handle/tede/8355 2025-12-18T00:00:00Z https://tede.unioeste.br/handle/tede/8301 Title: OntoMI: Uma Ontologia Fundamentada na Teoria das Inteligências Múltiplas para Classificação Semântica de Recursos Educacionais Autor: SPECK, Jefferson Rodrigo Primeiro orientador: Andrade, Sidgley Camargo de Abstract: The formal and explainable representation of educational theories in computational systems remains a challenge for teaching-personalization initiatives, especially when the goal is to trace inferences back to observable textual evidence. In this context, this study investigates the potential of an ontological and computational approach to classify and semantically represent textual educational resources, adopting the Theory of Multiple Intelligences as the pedagogical reference for instantiation. The research was conducted under the Design Science Research paradigm, integrating a systematic literature review, ontology engineering methods through Ontology Development 101 and SABiOx, and a proof of concept. As results, a pedagogical practices guide, the OntoMI ontology, and the Intelli3 computational model were produced. OntoMI structured the link between linguistic evidence and inferred categories, promoting traceability and support for explainability. Intelli3 generated vector-based profiles from the instantiated knowledge and enabled the ranking of instructional materials according to multiple-intelligence profiles. Empirical tests indicated stability and precision in differentiating profiles, supporting the technical feasibility of semantic classification when computational inference is grounded in explicitly stated evidence. It is concluded that the ontology serves as the formalization core and mediation layer between pedagogical theory and computational operationalization, supporting teacher decision-making without replacing the educator’s interpretive role. Publisher: Universidade Estadual do Oeste do Paraná Tipo do documento: Dissertação Fri, 20 Feb 2026 00:00:00 GMT https://tede.unioeste.br/handle/tede/8301 2026-02-20T00:00:00Z https://tede.unioeste.br/handle/tede/8206 Title: Pós-edição humana apoiada por anotações de erro: um estudo de caso para textos científicos de português brasileiro para inglês Autor: Nürmberg, Rodrigo Schmidt Primeiro orientador: Spanhol, Fabio Alexandre Abstract: The internet and globalization have boosted the demand for translation services. In this scenario, the automated translation of texts, by means of computer programs, aims to meet part of this demand and improve the productivity of translators. However, problems with the quality of automated translation are accentuated in specific contexts, due to the characteristics of the domain, such as the translation of scientific texts, an area in which more than 80% of all world publications are in English. The improvement in the fluency of automated translations makes it difficult to identify such errors, demanding additional attention from proofreaders. A case study was conducted to investigate whether error annotations, generated by quality estimation models of automated translations, can support translators in the post-editing of scientific texts, translated from Brazilian Portuguese into English, with a view to increasing the productivity and quality of translations. No evidence of increased productivity was found, associated exclusively with the presence of highlights. The quality assessments are still under analysis and their results will be communicated in due course. Although translators in the highlighted modalities corrected 1.5 times more critical errors than those in the No highlighted modality, no significant differences were found in quality averages between the modalities. In terms of usability, participants acknowledged the influence of highlights on post-editing, but their perception of its usefulness was mixed. Keywords: machine translation; scholarly communication; quality estimation; Publisher: Universidade Estadual do Oeste do Paraná Tipo do documento: Dissertação Fri, 12 Sep 2025 00:00:00 GMT https://tede.unioeste.br/handle/tede/8206 2025-09-12T00:00:00Z https://tede.unioeste.br/handle/tede/8205 Title: Uma aplicação de visão computacional para detecção automática de defeitos em pavimentação asfáltica urbana no Brasil Autor: Borges, Marcos Augusto Primeiro orientador: Spanhol, Fabio Alexandre Abstract: Road infrastructure maintenance is a cornerstone of well-functioning cities, as it directly influences urban mobility, traffic safety, and the efficiency of transporting people and goods. However, the natural deterioration of pavements—compounded by increasing traffic and the lack of adequate preventive maintenance—leads to recurrent damage that affects both users and public management. In this context, efficient monitoring methods are indispensable to ensure roadway quality and to reduce costs associated with emergency interventions. This work aims to develop an automated system for detecting damage in asphalt pavements using computer vision and deep learning techniques. Among the principal challenges addressed are the accurate identification and classification of different defect types: fissures (cracks), deformations, ravelling (surface wear), potholes, and patches. We present a publicly available dataset of high-resolution digital images of urban pavements, structured in accordance with Brazilian standards and accompanied by per-image annotations curated by a technical committee. The study also proposes an efficient methodology for automated roadway condition assessment based on images collected with a smartphone mounted on the bumper of a passenger vehicle. The model trained with YOLOv5 achieved an mAP@50 of 84.4%. These results are intended to support public administrations in making decisions about maintenance and interventions, leading to improvements in the quality and safety of road infrastructure. Publisher: Universidade Estadual do Oeste do Paraná Tipo do documento: Dissertação Fri, 03 Oct 2025 00:00:00 GMT https://tede.unioeste.br/handle/tede/8205 2025-10-03T00:00:00Z