Abstract
This study explores models for synthetic data generation of time series. In order to improve the achieved results, i.e., the data generated, new ways of improvement are explored and different models of synthetic data generation are compared. The model addressed in this work is the Generative Adversarial Networks (GANs), known for generating data similar to the original basis data through the training of a generator. The GANs are applied using the datasets of Quinta de Santa Barbara and the Pinhao region, with the main variables being the Average temperature, Wind direction, Average wind speed, Maximum instantaneous wind speed and Solar radiation. The model allowed to generate missing data in a given period and, in turn, enables to analyze the results and compare them with those of a multiple linear regression method, being able to evaluate the effectiveness of the generated data. In this way, through the study and analysis of the GANs we can see if the model presents effectiveness and accuracy in the synthetic generation of meteorological data. With the proper conclusions of the results, this information can be used in order to improve the search for different models and the ability to generate synthetic time series data, which is representative of the real, original, data.

Abstract
The Haka'a'Museum workshop in Madeira explores how augmented reality (AR) enhances marine conservation education. This one-day, hands-on experience engages participants in co-creating AR experiences that make complex environmental issues more accessible. Following a structured approach, participants explore museum exhibits, collaborate on AR concepts, implement content using no-code tools, and evaluate their experiences. Leveraging Madeira's unique marine ecosystem, the workshop addresses ocean pollution, climate change, and sustainability. Data from AR interactions will inform the best practices for museum education. Ultimately, the workshop fosters awareness and action for ocean sustainability, redefining how museums educate through immersive technology.

Abstract

Abstract
The electrification of transportation and the increased adoption of decentralized renewable energy generation have added complexity to managing Renewable Energy Communities (RECs). Integrating Electric Vehicle (EV) charging with building energy systems like heating, ventilation, air conditioning (HVAC), photovoltaic (PV) generation, and battery storage presents significant opportunities but also practical challenges. Reinforcement learning (RL), particularly Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithms, have shown promising results in simulation, outperforming heuristic control strategies. However, translating these successes into real-world deployments faces substantial challenges, including incomplete and noisy data, integration of heterogeneous subsystems, synchronization issues, unpredictable occupant behavior, and missing critical EV state-of-charge (SoC) information. This paper introduces a framework designed explicitly to handle these complexities and bridge the simulation-to-reality gap. The framework incorporates EnergAIze, a MADDPG-based multi-agent control strategy, and specifically addresses challenges related to real-world data collection, system integration, and user behavior modeling. Preliminary results collected from a real-world operational REC with four residential buildings demonstrate the practical feasibility of our approach, achieving an average 9% reduction in daily peak demand and a 5% decrease in energy costs through optimized load scheduling and EV charging behaviors. These outcomes underscore the framework's effectiveness, advancing the practical deployment of intelligent energy management solutions in RECs. © 2025 IEEE.

Abstract
Deep Learning (DL) has emerged as a powerful tool for vulnerability detection, often outperforming traditional solutions. However, developing effective DL models requires large amounts of real-world data, which can be difficult to obtain in sufficient quantities. To address this challenge, DiverseVul dataset has been curated as one of the largest datasets of vulnerable and non-vulnerable C/C++ functions extracted exclusively from real-world projects. Its goal is to provide high-quality, large-scale samples for training DL models. Nevertheless, during our study several inconsistencies were identified in the raw dataset while applying pre-processing techniques, highlighting the need for a refined version. In this work, we present a refined version of DiverseVul dataset, which is used to fine-tune a large language model, LLaMA 3.2, for vulnerability detection. Experimental results show that the use of pre-processing techniques led to an improvement in performance, with the model achieving an F1-Score of 66%, a competitive result when compared to our baseline, which achieved a 47% F1-Score in software vulnerability detection.

Abstract
The Internet of Things (IoT) enables everyday objects to connect and communicate remotely, transforming areas such as smart homes and industrial automation. IoT systems can be standalone or interconnected in a System of Systems, where multiple devices work together towards a common goal. A key application is Energy Monitoring Systems (EMS), which track energy use within communities, using energy production and consumption. Designing this type of IoT systems remains complex and requires careful consideration of heterogeneous devices, their limitations, software, communication protocols, data management, and security. This paper presents a design approach for EMS communities, with a focus on house-level IoT systems. We introduce a model-driven development methodology, a holistic and flexible framework for designing IoT systems across the development and operations lifecycle. Especially, the concept of projectors enables an easy shift between domain assets and provide automation support. The approach is validated with a real-life use case, for which an analysis phase was developed, showing the benefits of using our approach for managing EMS and the automation of the analysis configuration. © 2025 by SCITEPRESS - Science and Technology Publications, Lda.