Abstract
Federated Learning (FL) enables decentralized model training while preserving data privacy but remains susceptible to poisoning attacks. Malicious clients can manipulate local data or model updates, threatening FL’s reliability, especially in privacy-sensitive domains like healthcare and finance. While client-side optimization algorithms play a crucial role in training local models, their resilience to such attacks is underexplored. This study empirically evaluates the robustness of three widely used optimization algorithms: SGD, Adam, and RMSProp—against label-flipping attacks (LFAs) in image classification tasks using Convolutional Neural Networks (CNNs). Through 900 individual runs in both federated and centralized learning (CL) settings, we analyze their performance under Independent and Identically Distributed (IID) and Non-IID data distributions. Results reveal that SGD is the most resilient, achieving the highest accuracy in 87% of cases, while Adam performs best in 13%. Additionally, centralized models outperform FL on CIFAR-10, whereas FL excels on Fashion-MNIST, highlighting the impact of dataset characteristics on adversarial robustness. © 2025 Elsevier B.V., All rights reserved.

Abstract
Underwater environments pose unique challenges to optical systems due to physical phenomena that induce severe data degradation. Current imaging sensors rarely address these effects comprehensively, resulting in the need to integrate complementary information sources. This article presents a multimodal data fusion approach to combine information from diverse sensing modalities into a single dense and accurate tridimensional representation. The proposed fusiNg tExture with apparent motion information for underwater Scene recOnstruction (NESO) encoder-decoder network leverages motion perception principles to extract relative depth cues, fusing them with textured information through an early fusion strategy. Evaluated on the FLSea-Stereo dataset, NESO outperforms state-of-the-art methods by 58.7%. Dense depth maps are achieved using multi-stage skip connections with attention mechanisms that ensure propagation of key features across network levels. This representation is further enhanced by incorporating sparse but millimeter-precise depth measurements from active imaging techniques. A regression-based algorithm maps depth displacements between these heterogeneous point clouds, using the estimated curves to refine the dense NESO prediction. This approach achieves relative errors as low as 0.41% when reconstructing submerged anode structures, accounting for metric improvements of up to 0.1124 m relative to the initial measurements. Validation at the ATLANTIS Coastal Testbed demonstrates the effectiveness of this multimodal fusion approach in obtaining robust tri-dimensional representations in real underwater conditions.

Abstract
When directional data fall in the positive orthant of the unit hypersphere, a folded directional distribution is preferred over a simple directional distribution for modeling the data. Since directional data, especially axial data, can be modeled using a Watson distribution, this paper considers a folded Watson distribution for such cases. We first address the parameter estimation of this distribution using maximum likelihood, which requires a numerical algorithm to solve the likelihood equations. We use the Expectation-Maximization (EM) algorithm to obtain these estimates and to analyze the properties of the concentration estimator through simulation. Next, we propose the Bayes rule for a folded Watson distribution and evaluate its performance through simulation in various scenarios, comparing it with the Bayes rule for the Watson distribution. Finally, we present examples using both simulated and real data available in the literature.

Abstract
Personal data privacy is fundamental in human activity and health monitoring systems, with additional challenges posed by the integration of AI tools. For monitoring to be effective, the user needs to trust on the system, adopt and use it frequently. Besides data privacy requirements and regulatory compliance, transparency, explainability and accountability matter. By incorporating Privacy by Design principles into AI-driven systems to ensure GDPR alignment, this paper proposed a simple approach for embedding privacy-preserving mechanisms throughout the data lifecycle, from design to deployment and continuous monitoring and illustrate it with two use cases developing AI-Driven Systems for human activity and health monitoring in different contexts. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract

Abstract
Providing healthcare professionals with quick access to structured standardized information enables comprehensive analysis and improves clinical decision-making. However, an important part of the records in health institutions is in the form of free text. This paper proposes a pipeline that automatically extracts medical information from Electronic Medical Records (EMRs), based on large language models (LLMs) and a domain ontology defined and validated in collaboration with a medical expert. The output is a knowledge graph of clinical narratives that can be used to search through repositories of EMRs or discover new facts. To promote the standardization of the extracted medical terms, we link them to existing international coding systems using biomedical repositories (UMLS - Unified Medical Language System and BioPortal - Biomedical Ontology Repository). We showcase our approach on a set of Portuguese clinical texts of cases of Acute Myeloid Leukemia (AML) guided by one medical expert. We evaluate the quality of the extraction and of the knowledge graph. © 2025 Elsevier B.V., All rights reserved.