Abstract
In healthcare, diagnoses usually rely on physician expertise. However, complex cases may benefit from consulting similar past clinical reports cases. In this paper, we present MedLink (http://medlink.inesctec.pt), a tool that given a free-text medical report, retrieves and ranks relevant clinical case reports published in health conferences and journals, aiming to support clinical decision-making, particularly in challenging or complex diagnoses. To this regard, we trained two BERT models on the sentence similarity task: a bi-encoder for retrieval and a cross-encoder for reranking. To evaluate our approach, we used 10 medical reports and asked a physician to rank the top 10 most relevant published case reports for each one. Our results show that MedLink’s ranking model achieved NDCG@10 of 0.747. Our demo also includes the visualization of clinical entities (using a NER model) and the production of a textual explanation (using a LLM) to ease comparison and contrasting between reports.

Abstract
Conventional localization systems typically rely on fixed transmission parameters and signal types, limiting their effectiveness in variable and dynamic underwater environments. The present work investigates the potential of adaptable transmission strategies to enhance signal detection estimation for localization purposes. Two widely used signal types, Linear Frequency Modulated (LFM) chirps and BPSK-modulated Msequences, are selected due to their strong autocorrelation properties and robustness to noise. A matched-filter detection approach based on peak correlation is implemented and evaluated. The analysis examines the impact of varying transmission parameters, namely transmission power and signal duration, on detection performance, which inherently influences time-based localization. Results demonstrate that reconfiguring signal parameters significantly reduces estimation dispersion. Moreover, the optimal signal type is shown to depend on the acoustic scenario, with no single waveform consistently outperforming the other. These findings highlight the value of reconfigurable acoustic systems capable of adapting acoustic systems characteristics based on environmental or system feedback, thereby improving localization performance in navigation tasks and dynamic underwater conditions. © 2025 Marine Technology Society.

Abstract
The growing adoption of electric vehicles (EVs) requires strategic planning of charging infrastructures to ensure greater efficiency and accessibility. In this context, forecasting EV trips becomes essential to identify travel patterns, anticipate demand for charging in different locations and strategically optimize the distribution of charging stations. This study proposes the use of Artificial Intelligence (AI) techniques to analyze mobility patterns and predict demand for charging in different locations. Three AI techniques will be explored: Fuzzy Logic, to deal with uncertainties associated with driver behavior; Supervised Machine Learning, encompassing Artificial Neural Networks (ANN), Support Vector Machine (SVM) and Linear Regression, to model and predict travel patterns; and Reinforcement Learning (RL), applied to the dynamic optimization of charging station distribution. The combination of these techniques aims to provide an intelligent and adaptive system for managing charging stations, contributing to sustainable mobility and the energy efficiency of the network.

Abstract

Abstract
With the growing need for AI-driven solutions in power grid management, this work addresses the challenge of creating realistic synthetic operating scenarios essential for developing, testing, and validating AI-based decision-making systems. It uses spatial-temporal noise functions, predefined patterns, and optimal power flow to model renewable energy and conventional power plant generation, load, and losses. Quantitative and visual key performance indicators are proposed to evaluate the quality of the generated operating scenarios, and the validation highlights the framework's ability to emulate diverse and practical operating scenarios, bridging gaps in AI-driven power system research and real-world applications.

Abstract
This chapter explores the critical role of derivatives in optimizing cost functions and driving the backpropagation algorithm in neural networks, emphasizing their applications in the education field. The study examines the use of derivatives in personalized learning systems, particularly within the Khan Academy platform, and evaluates their impact on scalability, bias, and efficiency. Five research questions guide the analysis, ranging from environmental impact to fairness in AI- driven education. Employing methods like Experimental Performance Evaluation and Comparative Analysis, the study offers both technical insights and ethical considerations. While derivatives enable precise optimization, the chapter highlights how they can unintentionally reinforce biases in training data, raising critical concerns about fairness and representation in educational technologies. © 2025 Elsevier B.V., All rights reserved.