https://repositorio.ufu.br/handle/123456789/18921 2026-06-20T17:47:10Z 2026-06-20T17:47:10Z https://repositorio.ufu.br/handle/123456789/48753 2026-06-13T06:18:59Z 2026-05-06T00:00:00Z

Title: ARCADE: uma metodologia orientada a dados para modelagem e aprimoramento da cobertura de redes celulares Abstract: The evolution of mobile networks and the increasing complexity of their management have made fine-tuning the RF environment progressively more challenging. As a result, standardization bodies and industry players have been investing in the automation of labor-intensive and complex processes, particularly the improvement of RAN coverage in cellular systems. Some proposals, such as the MDT functionality introduced in recent 3GPP releases, aim to collect raw network data to enable the development of tools that automate tasks previously carried out by specialized engineers. However, as observed in practice, RF coverage data are often sparse and do not by themselves provide comprehensive information about cell coverage, making systematic and thorough analysis difficult. The main problems leading to coverage efficiency loss are known as overshooting, where a cell covers more area than intended, interfering with and reducing the capacity of neighboring cells, and undershooting, where coverage falls well short of the intended area, causing service gaps and underutilization of network resources. This work proposes the Adaptative Radio Coverage Analysis through Data-driven Evolution (ARCADE) methodology, which, drawing on RF data obtained by any means (such as MDT, drive tests, or crowdsourcing), enables the determination of an improved network coverage configuration through an evolutionary process, designed to be eventually automated within the system itself. The proposal also assumes that no design data are available (such as tower heights, antenna orientation, or antenna models, or terrain databases), allowing a self-contained implementation within the cellular system itself. This eliminates dependence on the reliability and accuracy of such data and the need to acquire and integrate these databases, simplifying solution deployment, while also avoiding the deviations inherent in the various theoretical mathematical propagation prediction models commonly used today. This work can be divided into two distinct problems to be investigated sequentially. The first arises from the need for adequate modeling of the RF environment based on data that are often sparse, depending on the volume of users participating in the feature or application. It must also be considered that the data will contain outlier points, stemming from reading or processing errors, or from highly sporadic measurements outside the intended context (such as those from user devices located on high rooftops), which can radically distort coverage modeling if not discarded. Furthermore, the samples may also contain anomalies arising from design faults, such as overshooting or undershooting cells, and these anomalies must be correctly represented in the model. The second problem, after the RF environment has been mapped, is the determination of a set of network parameter adjustments in order to achieve better coverage efficiency with quality -- that is, carrier coverage with effective dominance over interference -- in the system. In this context, this thesis proposes a methodology encompassing all stages of a network coverage improvement process that is self-contained within the network context and follows a data-driven approach -- that is, one that does not rely on mathematical modeling (e.g., radio frequency propagation models). This methodology is proposed end-to-end, beginning with an examination of the data acquisition stage (focused on a practical crowdsourcing implementation as an alternative to drive test), proceeding through RF environment modeling via data extrapolation methods that exclude outliers while preserving representations of network anomalies, and finally proposing a cluster coverage improvement method that yields a network configuration with superior performance relative to the initial configuration. Results show that both the modeling methodology is well-suited to the proposed problem and the coverage improvement method achieved significant gains in coverage quality, with cell power adjustments (increases or reductions) within the cluster improving both the covered area and the area with single-server dominance -- the ideal condition for interference reduction in a cellular system.

2026-05-06T00:00:00Z https://repositorio.ufu.br/handle/123456789/48745 2026-06-10T06:19:42Z 2025-12-17T00:00:00Z

Title: Um framework apoiado por inteligência artificial para análise de aprendizagem autorregulada de estudantes em ambientes virtuais de aprendizagem Abstract: The advancement of digital technologies has transformed teaching and learning processes, making Virtual Learning Environments and Intelligent Learning Environments central spaces for investigating student behavior. These environments generate large volumes of interaction data that enable the analysis of how students plan, monitor, and evaluate their study strategies, which are fundamental dimensions of self-regulated learning. However, transforming these records into valid, interpretable, and pedagogically meaningful indicators still represents a challenge for educational research. This thesis proposes and validates the EDM Framework, a methodological model grounded in Educational Data Mining, developed to identify and analyze self-regulated learning behaviors based on interaction data. The framework systematically organizes the stages of data collection, preprocessing, mining, and interpretation, integrating principles from educational psychology, with emphasis on Zimmerman’s self-regulated learning model, and unsupervised clustering techniques. Throughout the research, the K-Means, HDBSCAN, and Agglomerative Clustering algorithms were tested and compared across four articulated case studies, which evolved from a proof of concept to practical application in a real educational context. In the final case study, conducted in a real “Introduction to Python Language” course, both hierarchical (Agglomerative) and non-hierarchical (K-Means) clustering approaches were applied using a parsimonious two-cluster solution to detect low and high self-regulated learning profiles over the duration of the course. The results showed that students with higher levels of self-regulated learning exhibited more consistent engagement patterns with educational resources and achieved better academic performance. Statistically significant differences between the identified profiles were observed at multiple points throughout the course, reinforcing the consistency of the proposed approach. Overall, the findings confirm that it is possible to identify consistent evidence of self-regulated learning from interaction data in virtual learning environments, demonstrating the effectiveness of clustering algorithms in forming profiles aligned with the theoretical dimensions of self-regulated learning. This thesis contributes to the advancement of the state of the art by offering a methodological process that integrates theoretical foundations and computational procedures, supporting the development of more adaptive, personalized educational systems that are sensitive to students’ self-regulatory strategies.

2025-12-17T00:00:00Z https://repositorio.ufu.br/handle/123456789/48732 2026-06-03T06:19:51Z 2025-12-11T00:00:00Z

Title: Pedagogical AI-based architecture for encouraging self-regulated learning behavior in students Abstract: With the advancement of educational technologies, Virtual Learning Environments have become essential for promoting new teaching and learning methods, especially in distance education and hybrid contexts. These environments allow students to access content, complete activities, and interact with peers and instructors in a flexible and personalized manner. In this scenario, Self-Regulated Learning stands out as a key com- petency, as it enables learners to autonomously manage, monitor, and direct their own learning process. This study proposes and validates an Artificial Intelligence - supported Pedagogical Architecture to foster SRL in VLEs, aiming to enhance students’ autonomy and engagement. Initially, a systematic literature review was conducted, which identified research gaps and guided the PA design. Subsequently, Proofs of Concept were carried out using data from the Open University Learning Analytics Dataset and from Moodle at IFSULDEMINAS – Campus Carmo de Minas, applying Educational Data Mining tech- niques and clustering algorithms. These analyzes allowed the identification of behavioral patterns, SRL profiles, and significant correlations between engagement and academic performance. In the final stage, the PA was implemented and evaluated in the context of an online Introduction to Python Programming course. Among the resources integrated into the VLE, the Time Tracker SRL plugin stands out, developed to monitor the time dedicated to learning activities and provide automated feedback. Other plugins, such as Configure Reports, Completion Progress, Analytics Graphs, and OpenAI Chat, were also employed to support the self-regulation process. The results showed that the PA had a significant impact in promoting SRL, with a positive correlation between engagement and academic performance. The triangulation of evidence—based on VLE log analysis, self-regulation questionnaires, and focus group interviews—confirmed the effectiveness of the PA, validating its potential to develop SRL skills, foster autonomy, and improve stu- dent performance. Thus, the proposed approach constitutes an innovative, scalable, and adaptable solution to support and personalize learning in VLEs.

2025-12-11T00:00:00Z https://repositorio.ufu.br/handle/123456789/48693 2026-05-13T06:23:42Z 2026-01-27T00:00:00Z

Title: Ponto de Troca de Internet do Futuro (FIXP) - habilitando Interconexão de arquiteturas de internet do futuro Abstract: The Internet was designed to meet needs different from those of today. Current applications impose new demands on the network that it cannot meet, given its limitations. One of the difficulties of the Internet is the lack of flexibility to deploy new network-layer services, which limits its evolution. This scenario motivated the development of several Future Internet Architectures (FIAs). These are disjoint architectures that propose, through their designs, to offer mechanisms that advance various aspects of communication, such as flexibility in the network layer, mobility, multicasting, quality of service (QoS), connectivity, quality of experience (QoE), security, among others. Despite the demand, the lack of implementation of these new architectures in high-performance networks makes it difficult to assess the maturity of their communication characteristics for specific scenarios and applications. On the other hand, due to the ubiquity of the traditional Internet, replacing the TCP/IP architecture is impractical. A single communication network or logical exchange point that integrates FIAs and the TCP/IP architecture without compromising its architectural principles (resources and mechanisms) is a promising approach to meeting the demands of current and future applications. This work presents the Future Internet Exchange Point (FIXP) and positions it as a candidate for this single network or logical exchange point that allows the coexistence of different Internet architectures; it also provides qualitative and quantitative analysis of FIXP: its capacity for evolution and incorporation of new architectures, the feasibility of implementing FIXP in the current networks, and the performance of application communication of IP and ETArch architectures in the FIXP infrastructure, taking into account the quality of user experience. Evaluations demonstrate the FIXP architecture conceptually by executing selected use cases in which applications from different FIAs coexist in the same communication environment. In addition, the work presents the details of the integration of the ETArch and IP architectures in the FIXP network, aiming to facilitate, in the future, the incorporation of other Internet architectures in this infrastructure. Regarding related work, the collection allows comparison with these works and with FIXP, positioning it as the state of the art, as the only infrastructure that does not add overhead to switching devices through interoperability processes and/or protocol stack development. Furthermore, its architectural principles differ from those of related work; therefore, the difficulty of integrating new FIAs into FIXP is low to medium relative to that of related work. These two facts, the lack of data plan overhead and the low or medium difficulty level of integrating new FIAs, facilitate the implementation of FIXP in current networks. The work also presents FIXP’s view of multi-architecture applications. These applications use different Internet architectures for their services. The use cases that demonstrate FIXP’s support for these applications simulate the execution of microservices within the same application or virtual machine, which is common nowadays. The difference is that microservices in a multi-architecture application can use frameworks from different FIAs. Notes: O documento inclui um apêndice (Apêndice A) que apresenta parte da implementação dos switches FIXP.

2026-01-27T00:00:00Z