Abstract
Knowledge models often use hierarchical structures, which help break down complex data into manageable components. This enables better understanding and aids in reasoning and decision-making. Hierarchical structures are effective in organizing, managing, and processing complex information. Traditional Self-Organizing Maps are typically flat, two-dimensional grids for visualizing and grouping data. They can be shaped into hierarchical structures, offering benefits such as improved data representation, scalability, enhanced grouping and visualization, and hierarchical feature extraction while preserving data topology. This paper introduces a self-organizing hierarchical map with an appropriate topology and a suitable learning mechanism for retaining information in an organized way. In this conceptual model, information is selectively absorbed in each layer. These characteristics make the Hierarchical Self-organising Maps a powerful non-linear classifier. Simulations are conducted to test and evaluate the performance of this neural structure as a classifier. © 2024 IEEE.

Abstract
The step response of first-order systems is vital in control systems and electronics. Understanding this behaviour is key but often challenging. This article uses Arduino with PWM to teach the step response in RC circuits, since Arduino enables real-time data acquisition and visualisation, connecting theory to practice. The research seeks to illustrate the step response of an RC circuit using Arduino, deepen knowledge of first-order systems, and offer a technique for collecting experimental data. All of this, since combining practical experiments with theoretical concepts boosts student involvement and understanding of dynamic systems. The work includes theoretical foundations, experimental procedures, and a brief discussion on the educational value of these activities.

Abstract
The resting brain has been extensively investigated for low frequency synchrony between brain regions, namely Functional Connectivity. However the other main stream of the brain connectivity analysis that seeks causal interactions between brain regions, Effective Connectivity, has been still little explored. Inherent complexity of brain activities in resting-state, as observed in Blood Oxygenation-Level Dependant fluctuations, calls for exploratory methods for characterizing these causal networks [1]. To determine the structure of the network that causes this dynamics, it is developed a method of identification based on least squares, which assumes knowledge of the signals of brain activity in different regions. As there is no access to functional Magnetic Resonance Imaging, data it is developed a model to obtain the Blood Oxygenation Level Dependent signals and it is implemented a reverse hemo-dynamic function. To assess the performance of the created model Monte Carlo simulations have been used. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

Abstract
This article addresses the problem of wheelchair path planning. In particular, to minimize the length of the trajectory within an environment containing a variable number of obstacles. The positions and quantities of these obstacles are pre-determined. To tackle this challenge, we present a methodology that integrates optimisation techniques and heuristic algorithms to find trajectories both optimal and collision-free. The effectiveness of this methodology is illustrated through a practical example, demonstrating how it successfully generates a collision-free trajectory, even when a large number of obstacles is present in the workspace. In the future, we intend to continue investigating the same problem, taking into account energy consumption as well as time minimisation. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

Abstract
This work focuses on the application of image processing techniques to segment and analyze images of brain sections with the aim of facilitating early diagnosis of brain tumors. The aim is to delineate specific regions of the brain, such as the cranial, intracranial, and encephalic regions, for subsequent geometric analysis. The process involves image pre-processing, conversion to polar coordinates, determination of contour points, Fourier Series approximation, and the use of the Least Square Method to obtain accurate representations of the regions. The proposed approach was tested on Magnetic Resonance Images of three different brains, showing its capability to accurately delineating the targeted regions. The results highlight the potential of signal processing techniques for analyzing brain images and provide insights for further research in this area. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

Abstract
Solar wind forecasting is a core component of Space Weather, a field that has been the target of many novel machine-learning approaches. The continuous monitoring of the Sun has provided an ever-growing ensemble of observations, facilitating the development of forecasting models that predict solar wind properties on Earth and other celestial objects within the solar system. This enables us to prepare for and mitigate the effects of solar wind-related events on Earth and space. The performance of some simulation-based solar wind models depends heavily on the quality of the initial guesses used as initial conditions. This work focuses on improving the accuracy of these initial conditions by employing a Recurrent Neural Network model. The study's findings confirmed that Recurrent Neural Networks can generate better initial guesses for the simulations, resulting in faster and more stable simulations. In our experiments, when we used predicted initial conditions, simulations ran an average of 1.08 times faster, with a statistically significant improvement and reduced amplitude transients. These results suggest that the improved initial conditions enhance the numerical robustness of the model and enable a more moderate integration time step. Despite the modest improvement in simulation convergence time, the Recurrent Neural Networks model's reusability without retraining remains valuable. With simulations lasting up to 12 h, an 8% gain equals one hour saved per simulation. Moreover, the generated profiles closely match the simulator's, making them suitable for applications with less demanding physical accuracy.