https://ri.ufs.br/jspui/handle/riufs/2495 2026-10-01T23:51:04Z 2026-10-01T23:51:04Z Castro, Gil Gleitson Santos Evangelista de https://ri.ufs.br/jspui/handle/riufs/26163 2026-09-24T19:47:31Z 2026-08-21T00:00:00Z

Título: Uma extensão do algoritmo RRT para a representação compacta do espaço de configurações em alta dimensionalidade Autor(es): Castro, Gil Gleitson Santos Evangelista de Abstract: Path planning in high-dimensional spaces is one of the main challenges in modern robotics, due to the complexity of the con guration space (Cspace) and the high computational cost associated with its exploration. Sampling-based probabilistic methods, such as the Rapidly-exploring Random Tree (RRT), stand out for their ability to handle these scenarios. However, when employed with the objective of extensively exploring the space, they tend to exhibit a loss of e ciency due to the excessive generation of redundant nodes, which entails higher computational and storage costs. Unlike the classical RRT approach, essentially focused on nding paths between speci c con gurations, this work investigates the use of the algorithm as a tool to build a compact representation of the free con guration space, focusing on maximizing coverage and computational e ciency. In this context, this dissertation proposes an extension of the RRT-Edge algorithm through an n-dimensional continuous polarization mechanism strictly independent of discretization. The approach introduces a strategy based on the analytical de nition of an exploration region around nodes and edges, coupled with a polarized sampling process guided by an exponential distribution. It guides sample generation toward promising regions of the space, reducing the incidence of redundant expansions and promoting a more e cient and structurally organized exploration of the environment. Additionally, an evaluation metric based on the Monte Carlo method is proposed to quantify the space exploration rate, allowing consistent comparative analyses across di erent dimensions. The developed method, referred to as RRT-Edge Continuous Polarization (RRT-EdgeCP), presents a generalized formulation of the polarization strategy for n-dimensional con guration spaces. The approach is validated in this research through experiments in d e two- and three-dimensional environments, used as a proof of concept. These scenarios allow the exploratory behavior of the tree to be analyzed, its structural dispersion and redundancy to be evaluated, and the proposed approach to be compared with di erent RRT variants. The experimental results demonstrated that the proposed approach achieved greater coverage of the explored space, particularly during the initial stages of exploration. A reduction in structural redundancy was also observed, associated with directing expansions toward regions not yet represented by the tree. Thus, the proposed approach contributes to the development of strategies for the exploration and representation of n-dimensional con guration spaces, providing a continuous polarization approach that is independent of spatial discretization. The results indicate the potential of the strategy for constructing compact representations of the free space while maintaining the exibility required for its application across di erent dimensions and robotic exploration scenarios.

2026-08-21T00:00:00Z Bezerra, Vitor Magno de Oliveira Santos https://ri.ufs.br/jspui/handle/riufs/26156 2026-09-24T19:38:37Z 2026-08-20T00:00:00Z

Título: Sobre a dependência estatística entre MFCCs e a combinação de energia e frequência fundamental Autor(es): Bezerra, Vitor Magno de Oliveira Santos Abstract: Mel-frequency cepstral coefficients (MFCCs) are a key feature in speech processing. This study investigates the assumption that MFCC values are independent of the combination of energy and fundamental frequency, which carry prosodic information. This investigation is conducted by developing a null hypothesis test to assess the statistical significance of the independence hypothesis between these two sources of information. The results demonstrate that it is statistically implausible for MFCCs to be independent of the combination of energy and fundamental frequency. Furthermore, replicating a speaker recognition system from the literature provides practical evidence of this implausibility, as the results suggest that these two types of features do not complement each other in terms of performance gains.

2026-08-20T00:00:00Z Bastos, Gabriel Francisco Alves https://ri.ufs.br/jspui/handle/riufs/26147 2026-09-21T15:13:10Z 2026-08-18T00:00:00Z

Título: Agregação de variáveis nas redes neurais artificiais baseada em medidas de informação mútua Autor(es): Bastos, Gabriel Francisco Alves Abstract: Artificial neural networks constitute a class of models that lies at the core of mo dern machine learning. A notable attribute of these models is, in many applications, their large number of parameters, which gives rise to the need for either implicit or explicit regularization in order to achieve strong predictive performance. One way to incorporate implicit regularization is by constraining which variables are allowed to interact within artificial neurons, as exemplified by the convolutional and the pooling layers of convolutio nal neural networks (CNNs), where each variable interacts only with its spatial neighbors. Within this context, the central hypothesis motivating this dissertation is that, in certain scenarios, it is beneficial to impose such constraints so that computations performed over subsets of the input variables involve those exhibiting high statistical dependence. In this regard, one of the main contributions of this dissertation is a proof of concept demonstra ting that conventionally defined CNNs provide a practical example of the application of this principle. Furthermore, experimental evidence is presented showing that extending this principle to tabular data through the use of locally connected layers is a promising approach for representation learning and autoencoding. Throughout the dissertation, it is frequently necessary to quantify the statistical dependence between pairs of variables using mutual information measures. Accordingly, this document also presents an in-depth study of the mutual information estimation problem, which remains an active research hotspot. As a result, the outcomes of this study include the proposal of a novel estima tion method for discrete variables and the adoption of a mutual information estimator for continuous sources, which is employed throughout the dissertation.

2026-08-18T00:00:00Z Nogueira, Paulo Gabriel Barreto https://ri.ufs.br/jspui/handle/riufs/25888 2026-09-01T12:46:14Z 2026-03-06T00:00:00Z

Título: Modelagem por equivalente elétrico para dispositivos a onda acústica de superfície Autor(es): Nogueira, Paulo Gabriel Barreto Abstract: Surface Acoustic Wave (SAW) devices find extensive application in telecommunications as delay lines and highly selective filters, and they also operate as high-sensitivity sensors. This versatility arises from their ability to convert electrical signals into acoustic waves through interdigital transducers and from the strong interaction between these waves and physical or chemical perturbations in the propagation medium. Engineers typically characterize these devices using vector network analyzers, which restrict field applications and complicate integration with systems and wireless sensor networks. These limitations motivate the implementation of approaches based on open- and closed-loop electronic oscillators. However, the development of such systems faces constraints related to the acquisition of SAW devices and to their direct use in circuit simulators. As a result, researchers employ equivalent electrical models, particularly those based on resonator crystals. An extensive literature review reveals that currently available models, although simple and physically implementable, diverge in their representation of the electrical coupling between SAW ports. This aspect plays a critical role in the performance and stability of closed-loop oscillators, especially under uncontrolled environmental conditions. In this context, this work proposes the development of an equivalent electrical circuit model for SAW devices based on a resonator crystal with adjustable parameters. The proposed model more accurately represents the coupling between ports and supports applications in the calibration of SAW-based systems, integration with electronic oscillators, and laboratory testing. This approach reduces dependence on real devices and increases the feasibility of field measurements. The study derives the model from an adapted resonator crystal representation and incorporates dedicated blocks to adjust input and output impedances as well as transmission magnitude.

2026-03-06T00:00:00Z