Abstract
The correction of artifacts in Magnetic Resonance Imaging (MRI) is increasingly relevant as voluntary and involuntary artifacts can hinder data acquisition. Reverting from corrupted to artifact-free images is a complex task. Deep Learning (DL) models have been employed to preserve data characteristics and to identify and correct those artifacts. We propose MOANA, a novel DL-based solution to correct artifacts in multi-contrast brain MRI scans. MOANA offers two models: the simulation and the correction models. The simulation model introduces perturbations similar to those occurring in an exam while preserving the original image as ground truth; this is required as publicly available datasets rarely have motion-corrupted images. It allows the addition of three types of artifacts with different degrees of severity. The DL-based correction model adds a fourth contrast to state-of-the-art solutions while improving the overall performance of the models. MOANA achieved the highest results in the FLAIR contrast, with a Structural Similarity Index Measure (SSIM) of 0.9803 and a Normalized Mutual Information (NMI) of 0.8030. With this, the MOANA model can correct large volumes of images in less time and adapt to different levels of artifact severity, allowing for better diagnosis.

Abstract
In the current context of smart grids, microgrids have proven to be an effective solution to meet the energy needs of neighborhoods and collective buildings. This study investigates the voltage behavior and other critical parameters within a direct current (DC) microgrid to enhance system efficiency, stability, and reliability. The dynamic performance of a DC microgrid is analyzed under varying load and generation conditions, with particular emphasis on the voltage response and load-sharing mechanisms required to ensure stable operation. The findings indicate that specific control strategies, particularly droop methods, are effective in mitigating voltage fluctuations, enhancing power quality, and ensuring proper load distribution across multiple sources. This study also addresses significant challenges, including voltage regulation and fault resilience, to provide guidelines for designing robust and efficient DC microgrids. These insights are essential to inspire further advancements in control strategies and facilitate the practical deployment of DC microgrids as a sustainable solution for distributed energy systems, especially in scenarios prioritizing high DC load penetration and renewable energy integration.

Abstract
Increasing the number of Electric Vehicles (EVs) imposes several challenges in power distribution networks. Developed Electric Vehicle Supply Equipment (EVSE) provides fast and efficient charging of EVs at the Public Charging Stations (PCS). These chargers benefit from balanced three-phase chargers with considerable power consumption. Hence, the optimal management and task scheduling for EVSE should be arranged in such a way as to avoid overloading network infrastructure or imposing new peaks on the distribution networks. On the other hand, energy management in the presence of high renewable energy penetration due to installed Photovoltaic (PV) panels at the low-voltage (LV) distribution network should be elaborated to minimize the renewable power curtailment. Hence, this paper presents a novel model to address the optimal scheduling of charging stations availability and unlocking the Demand Response (DR) potentials at the distribution networks with highly penetrated PV panels. The energy management model is represented as a standard Mixed-Integer Linear Programming (MILP) problem which can be solved by open-source solvers. The proposed model is tested for a real case study in Portugal to demonstrate the functionality of the developed tool. © 2024 IEEE.

Abstract
Illegal landfills are a critical issue due to their environmental, economic, and public health impacts. This study leverages aerial imagery for environmental crime monitoring. While advances in artificial intelligence and computer vision hold promise, the challenge lies in training models with high-resolution literature datasets and adapting them to open-access low-resolution images. Considering the substantial quality differences and limited annotation, this research explores the adaptability of models across these domains. Motivated by the necessity for a comprehensive evaluation of waste detection algorithms, it advocates cross-domain classification and super-resolution enhancement to analyze the impact of different image resolutions on waste classification as an evaluation to combat the proliferation of illegal landfills. We observed performance improvements by enhancing image quality but noted an influence on model sensitivity, necessitating careful threshold fine-tuning.

Abstract
The congress which ISPGAYA organized in Vila Nova de Gaia, Portugal, on 26 and 27 October 2023 is based on the theme of sustainability, meeting the current academic, social, and political agenda. The congress is based on the theme of digital sustainability, meeting the current academic, social, and political agenda. This event brings together the different scientific areas of ISPGAYA and seeks to highlight the set of interdisciplinary and multilevel efforts to change the existing reality, supported by the affinity of ideas and attitudes, knowledge, and practices. Contributions from different institutions, national and international, that make up the technological and scientific system, asserting the concertation of strategies at local, regional, and global levels, and the interconnection between synergistic contributions of the living forces to mobilize toward to consolidate planetary sustainability over the next few decades. The scope of this book comprehends manuscripts submitted under the various thematic: Industrial Automation; Energy Efficiency; Information Technology & Cybersecurity; Management & Administration; Marketing; Tourism & Leisure; Education. All these scientific areas are connected by the main issue sustainability. Researchers, professionals, and students from different areas participate in this sharing of knowledge, suggesting a reticular logic and partnerships in the approach to sustainability. The publication of this book of proceedings intends to increase and dynamize investigation linking theory and practice, always pointing to innovative approaches, and mainly, involve as many people and institutions as possible in the direction of a smart national and global development model, meeting the intentions of the 2030 agenda outlined by the United Nations. We lift the veil on responsible innovation including technology innovation and entrepreneurship toward innovation for sustainable development and make positive impact in the ongoing paradigm shift from a same development model to building a safe operating space for a SMART Earth3 model, comprising Local Sustainable Development Goals.

Abstract
AbstractThe correction of artifacts in Magnetic Resonance Imaging (MRI) is crucial due to physiological phenomena and technical issues affecting diagnostic quality. Reverting from corrupted to artifact-free images is a complex task. Deep Learning (DL) models have been employed to preserve data characteristics and to identify and correct those artifacts. We proposeMAC, a novel DL-based solution to correct artifacts in multi-contrast brain MRI scans.MACoffers two models: the simulation and the correction models. The simulation model introduces perturbations similar to those occurring in an exam while preserving the original image as ground truth; this is required as publicly available datasets rarely have motion-corrupted images. It allows the addition of three types of artifacts with different degrees of severity. The DL-based correction model adds a fourth contrast to state-of-the-art solutions while improving the overall performance of the models.MACachieved the highest results in the FLAIR contrast, with a Structural Similarity Index Measure (SSIM) of 0.9803 and a Normalized Mutual Information (NMI) of 0.8030. Moreover, the model reduced training time by 63% compared to its predecessor.MACmodel can correct large volumes of images faster and adapt to different levels of artifact severity than current state-ofthe-art models, allowing for better diagnosis.