Abstract
Insomnia and obstructive sleep apnea (OSA) are common sleep disorders that often co-occur as comorbid insomnia and sleep apnea (COMISA), worsening health outcomes. This study characterized and compared the physiological and sleep profiles of insomnia, OSA and COMISA in population-based datasets from Portugal (n = 147) and Spain (n = 264), excluding patients with cardiovascular disease. Classification followed clinical guidelines, and analyses included polysomnography and heart rate variability (HRV) data. Conventional HRV metrics in the time and frequency domains, along with condition-specific frequency bands (BWMS, BWOSA, BWCOMISA, BWRes) were compared alongside demographic and clinical variables. The Portuguese and Spanish datasets differed significantly in gender distribution, daytime sleepiness, sleep efficiency and apnea-hypopnea index (AHI), with Spanish patients showing a higher severity of AHI and a predominantly male composition. COMISA patients were older, had higher BMI, and showed a hypopnea-dominant respiratory profile in both datasets. Classical HRV indices did not differ significantly between groups, although trends suggested decreased parasympathetic activity in OSA. Condition-specific bands were largely non-discriminative in Portugal, while BWOSA emerged as a significant marker of respiratory burden in Spain. When the populations were analysed jointly, age and obesity remained significant risk factors and COMISA maintained its hypopnea-dominant profile. The combined dataset revealed significant differences in several HRV features. OSA and COMISA patients exhibited a higher cardiovascular burden and autonomic imbalance (lower HF, higher LF/HF and LFn), while condition-specific bands all showed discriminatory power across groups. BWOSA may represent a useful spectral biomarker for OSA, although population and methodological factors strongly influence discriminative power.

Abstract
The European Project Semester (EPS) at the Instituto Superior de Engenharia do Porto (ISEP) is a challenge-based learning frame-work in which engineering students from various majors and nationalities collaborate to solve real-world problems. EPSAISEP projects provide a context for teams to jointly acquire and apply new knowledge and skills during the design, development, and testing of a proof-of-concept prototype. In spring 2025, the LeftLovers team tackled the challenge of creating an accessible, economical, ecological, and odourless kitchen food waste disposal solution for apartment dwellers. LeftLovers aimed to raise awareness of the benefits of composting food waste, educate about composting, convert food waste into compost, and use the compost to grow plants at home. The proposed Loopbin concept consists of a device and an application. The device has four vertically stacked bins: a small garden for direct compost use at the top, two compost bins in the middle, and a compost storage bin at the bottom. The compost bins are equipped with handles to turn the contents and pins to open the trap doors between connected bins. A smart system monitors the composting process, controls automatic ventilation, and communicates with the app, which displays the composting status and provides instructions to produce high-quality compost. This solution stands out for its accessibility, affordability, and inclusion of a vegetable garden.

Abstract
The increasing reliance on Networked Microgrids (NMGs) for decentralized energy management introduces unprecedented cybersecurity risks, particularly in the context of False Data Injection Attacks (FDIA). While traditional FDIA studies have primarily focused on network-based intrusions, this work explores a novel cyber-physical attack vector leveraging Uncrewed Aerial Vehicles (UAVs) to execute sophisticated cyberattacks on microgrid operations. UAVs, equipped with communication jamming and data spoofing capabilities, can dynamically infiltrate microgrid communication networks, manipulate sensor data, and compromise power system stability. This paper presents a multi-objective optimization framework for UAV-assisted FDIA, incorporating Non-dominated Sorting Genetic Algorithm III (NSGA-III) to maximize attack duration, disruption impact, stealth, and energy efficiency. A comprehensive mathematical model is formulated to capture the intricate interplay between UAV operational constraints, cyberattack execution, and microgrid vulnerabilities. The model integrates flight path optimization, energy consumption constraints, signal interference effects, and adaptive attack strategies, ensuring that UAVs can sustain long-duration cyberattacks while minimizing detection risk. Results indicate that UAV-assisted cyberattacks can induce power imbalances of up to 15%, increase operational costs by 30%, and cause voltage deviations exceeding 0.10 p.u.. Furthermore, analysis of attack success rates vs. detection mechanisms highlights the limitations of conventional rule-based anomaly detection, reinforcing the need for adaptive AI-driven cybersecurity defenses. The findings underscore the urgent necessity for advanced intrusion detection systems, UAV tracking technologies, and resilient microgrid architectures to mitigate the risks posed by airborne cyber threats.

Abstract
Breast cancer patients often face difficulties when choosing among diverse surgeries. To aid patients, this paper proposes ACID-GAN (Anatomically and Clinically Informed Deep Generative Adversarial Network), a conditional generative model for predicting post-operative breast cancer outcomes using deep learning. Built on Pix2Pix, the model incorporates clinical metadata, such as surgery type and cancer laterality, by introducing a dedicated encoder for semantic supervision. Further improvements include colour preservation and anatomically informed losses, as well as clinical supervision via segmentation and classification modules. Experiments on a private dataset demonstrate that the model produces realistic, context-aware predictions. The results demonstrate that the model presents a meaningful trade-off between generating precise, anatomically defined results and maintaining patient-specific appearance, such as skin tone and shape.

Abstract
We study the optimal online service for grocery retailers operating both physical and online stores. The challenge lies in optimizing the size of the online assortment and the delivery fees to maximize profitability across channels, while considering customer, operational, and market dynamics. Using transaction data from a major grocery retailer, we employ an alternative-specific conditional logit model to investigate how delivery fees, assortment size, network characteristics, and customer needs influence store choice and spending across physical and online channels. We develop a profitability model that incorporates online service variables, customer behavior, and operational costs, enabling us to explore optimal strategies under various conditions. By identifying favorable conditions for the online store and analyzing optimal service variables, we provide actionable insights for retailers. Our findings challenge common practices in omnichannel retail. We show that delivery fees should not merely cover costs but can be strategically set higher, particularly for retailers with strong offline presence. Additionally, while reducing fulfillment costs improves profitability, its impact is smaller than expected. Multichannel retailers can offset these costs by passing them on to customers, with minimal overall demand loss, as some customers opt to shop in physical stores rather than abandoning the retailer entirely. Lastly, maximizing the online assortment may not always be optimal, particularly if the operational inefficiencies and costs outweigh the value customers place on variety. Our methodological framework provides retailers the opportunity to align their online services with customer preferences and operational constraints and to leverage customer data in shaping their omnichannel strategies. © 2026 The Author(s)

Abstract
This work addresses the challenge of stabilizing a vessel-mounted parallel mechanism (3-RPU) to mitigate wave-induced roll and pitch motions during UAV-USV cooperative operations, a critical requirement for safe take-off and landing in dynamic maritime environments. A hierarchical control architecture is proposed to decouple high-level kinematic stabilization from low-level actuator dynamics, which are managed by high-precision closed-loop digital drivers. Multiple control strategies are evaluated ranging from classical reactive approaches, to model predictive control (MPC) frameworks, and finally, advanced deep reinforcement learning (DRL) methods: Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC), trained and tested in a high-fidelity simulation environment modeling realistic ocean waves and vessel-fluid interactions. Among the controllers, the SAC-trained agent achieves the best performance, reducing wave-induced platform motion by up to 89.8%, compared to 77.2% for MPC, while also delivering 8.6 & times; lower inference time (0.161 vs 1.383 ms). The framework's feasibility is further validated through Hardware-in-the-Loop (HiL) testing, demonstrating an 85.8% stabilization efficiency and confirming a minimal simulation-to-reality gap. These results demonstrate that DRL can provide robust, low-latency motion compensation, while outperforming conventional methods in complex maritime scenarios.