Jonathan de Matos

A utilização de ferramentas de Inteligência Artificial (IA) e podcasts no ensino de sistemas multimídia tem se mostrado uma abordagem eficaz para promover o aprendizado dinâmico e colaborativo. Este estudo relata a experiência realizada na disciplina de Sistemas Multimídia do curso de Engenharia de Software da Universidade Estadual de Ponta Grossa (UEPG), onde os alunos desenvolveram podcasts sobre temas variados, utilizando ferramentas de IA como ChatGPT, ElevenLabs, Amazon Polly e Midjourney. A atividade teve como objetivo principal integrar IA ao processo de criação multimídia, além de incentivar uma reflexão crítica sobre as implicações éticas do uso dessas tecnologias. O desenvolvimento de podcasts permitiu aos alunos aprimorarem suas habilidades técnicas em edição de áudio e roteirização, enquanto a IA facilitou o processo criativo e aumentou o engajamento dos estudantes. Os resultados indicam que a atividade promoveu a colaboração entre os estudantes, permitindo uma participação mais equitativa e ampliando o pensamento crítico sobre o impacto social da IA. Desafios relacionados à curva de aprendizado das ferramentas e à gestão do tempo foram superados com suporte pedagógico adequado. O estudo conclui que a integração de IA e podcasts é uma estratégia promissora para o ensino superior, com grande potencial de ser replicada em diferentes contextos acadêmicos.

Information from an image occurs over multiple and distinct spatial scales. Image pyramid multiresolution representations are a useful data structure for image analysis and manipulation over a spectrum of spatial scales. This paper employs the Gaussian–Laplacian pyramid to separately treat different spatial frequency bands of a texture. First, we generate three images corresponding to three levels of the Gaussian–Laplacian pyramid for an input image to capture intrinsic details. Then, we aggregate features extracted from gray and color texture images using bioinspired texture descriptors, information-theoretic measures, gray-level co-occurrence matrix feature descriptors, and Haralick statistical feature descriptors into a single feature vector. Such an aggregation aims at producing features that characterize textures to their maximum extent, unlike employing each descriptor separately, which may lose some relevant textural information and reduce the classification performance. The experimental results on texture and histopathologic image datasets have shown the advantages of the proposed method compared to state-of-the-art approaches. Such findings emphasize the importance of multiscale image analysis and corroborate that the descriptors mentioned above are complementary.

This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The core of such an approach is a loss function that computes the distances between instances of interest and support vectors. The objective is to update the weights of CLs iteratively to learn a representation with a large margin between classes. Each iteration results in a large-margin discriminant model represented by support vectors based on such a representation. The advantage of the proposed approach w.r.t. convolutional neural networks (CNNs) is two-fold. First, it allows representation learning with a small amount of data due to the reduced number of parameters compared to an equivalent CNN. Second, it has a low training cost since the backpropagation considers only support vectors. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.

Histopathological images (HIs) are the gold standard for evaluating some types of tumors for cancer diagnosis. The analysis of such images is time and resource-consuming and very challenging even for experienced pathologists, resulting in inter-observer and intra-observer disagreements. One of the ways of accelerating such an analysis is to use computer-aided diagnosis (CAD) systems. This paper presents a review on machine learning methods for histopathological image analysis, including shallow and deep learning methods. We also cover the most common tasks in HI analysis, such as segmentation and feature extraction. Besides, we present a list of publicly available and private datasets that have been used in HI research.

In this paper, we propose the use of a black-box optimization method called deterministic Mesh Adaptive Direct Search (MADS) algorithm with orthogonal directions (Ortho-MADS) for the selection of hyperparameters of Support Vector Machines with a Gaussian kernel. Different from most of the methods in the literature that exploit the properties of the data or attempt to minimize the accuracy of a validation dataset over the first quadrant of (C, gamma), the Ortho-MADS provides convergence proof. We present the MADS, followed by the Ortho-MADS, the dynamic stopping criterion defined by the MADS mesh size and two different search strategies (Nelder-Mead and Variable Neighborhood Search) that contribute to a competitive convergence rate as well as a mechanism to escape from undesired local minima. We have investigated the practical selection of hyperparameters for the Support Vector Machine with a Gaussian kernel, i.e., properly choose the hyperparameters gamma (bandwidth) and C (trade-off) on several benchmark datasets. The experimental results have shown that the proposed approach for hyperparameter tuning consistently finds comparable or better solutions, when using a common configuration, than other methods. We have also evaluated the accuracy and the number of function evaluations of the Ortho-MADS with the Nelder-Mead search strategy and the Variable Neighborhood Search strategy using the mesh size as a stopping criterion, and we have achieved accuracy that no other method for hyperparameters optimization could reach.