Abstract
Socioeconomic growth and population increase are driving a constant global demand for energy. Renewable energy is emerging as a leading solution to minimise the use of fossil fuels. However, renewable resources are characterised by significant intermittency and unpredictability, which impact their energy production and integration into the power grid. Forecasting models are increasingly being developed to address these challenges and have become crucial as renewable energy sources are integrated in energy systems. In this paper, a comparative analysis of forecasting methods for renewable energy production is developed, focusing on photovoltaic and wind power. A review of state-of-the-art techniques is conducted to synthesise and categorise different forecasting models, taking into account climatic variables, optimisation algorithms, pre-processing techniques, and various forecasting horizons. By integrating diverse techniques such as optimisation algorithms and pre-processing methods and carefully selecting the forecast horizon, it is possible to highlight the accuracy and stability of forecasts. Overall, the ongoing development and refinement of forecasting methods are crucial to achieve a sustainable and reliable energy future.

Abstract

Abstract
This paper focuses on the creation and evaluation of synthetic data to address the challenges of imbalanced datasets in machine learning applications (ML), using fake news detection as a case study. We conducted a thorough literature review on generative adversarial networks (GANs) for tabular data, synthetic data generation methods, and synthetic data quality assessment. By augmenting a public news dataset with synthetic data generated by different GAN architectures, we demonstrate the potential of synthetic data to improve ML models’ performance in fake news detection. Our results show a significant improvement in classification performance, especially in the underrepresented class. We also modify and extend a data usage approach to evaluate the quality of synthetic data and investigate the relationship between synthetic data quality and data augmentation performance in classification tasks. We found a positive correlation between synthetic data quality and performance in the underrepresented class, highlighting the importance of high-quality synthetic data for effective data augmentation.

Abstract
This paper reports on the development and validation of a formal model for an automotive adaptive exterior lights system (ELS) with multiple variants in Alloy 6, which is the most recent version of the Alloy lightweight formal specification language that supports mutable relations and temporal logic. We explore different strategies to address variability, one in pure Alloy and another through an annotative language extension. We then show how Alloy and its Analyzer can be used to validate systems of this nature, namely by checking that the reference scenarios are admissible, and to automatically verify whether the established requirements hold. A prototype was developed to translate the provided validation sequences into Alloy and back to further automate the validation process. The resulting ELS model was validated against the provided validation sequences and verified for most of requirements for all variants.

Abstract
In this paper, we evaluate the performance and analyze the explainability of machine learning models boosted by feature selection in predicting COVID-19-positive cases from self-reported information. In essence, this work describes a methodology to identify COVID-19 infections that considers the large amount of information collected by the University of Maryland Global COVID-19 Trends and Impact Survey (UMD-CTIS). More precisely, this methodology performs a feature selection stage based on the recursive feature elimination (RFE) method to reduce the number of input variables without compromising detection accuracy. A tree-based supervised machine learning model is then optimized with the selected features to detect COVID-19-active cases. In contrast to previous approaches that use a limited set of selected symptoms, the proposed approach builds the detection engine considering a broad range of features including self-reported symptoms, local community information, vaccination acceptance, and isolation measures, among others. To implement the methodology, three different supervised classifiers were used: random forests (RF), light gradient boosting (LGB), and extreme gradient boosting (XGB). Based on data collected from the UMD-CTIS, we evaluated the detection performance of the methodology for four countries (Brazil, Canada, Japan, and South Africa) and two periods (2020 and 2021). The proposed approach was assessed in terms of various quality metrics: F1-score, sensitivity, specificity, precision, receiver operating characteristic (ROC), and area under the ROC curve (AUC). This work also shows the normalized daily incidence curves obtained by the proposed approach for the four countries. Finally, we perform an explainability analysis using Shapley values and feature importance to determine the relevance of each feature and the corresponding contribution for each country and each country/year.

Abstract
Objectives: The purpose of this study was to field-test a recently developed AR-based serious game designed to promote SSE self-efficacy, called Spot. Methods: Thirty participants played the game and answered 3 questionnaires: a baseline questionnaire, a second questionnaire immediately after playing the game, and a third questionnaire 1 week later (follow-up). Results: The majority of participants considered that the objective quality of the game was high, and considered that the game could have a real impact in SSE promotion. Participants showed statistically significant increases in SSE self-efficacy and intention at follow-up. Of the 24 participants that had never performed a SSE or had done one more than 3 months ago, 12 (50.0%) reported doing a SSE at follow-up. Conclusions: This study provides supporting evidence to the use of serious games in combination with AR to educate and motivate users to perform SSE. Spot seems to be an inconspicuous but effective strategy to promote SSE, a cancer prevention behavior, among healthy individuals. Practice implications: Patient education is essential to tackle skin cancer, particularly melanoma. Serious games, such as Spot, have the ability to effectively educate and motivate patients to perform a cancer prevention behavior.