Abstract
The effectiveness of optimizing complex problems is closely linked to the configuration of parameters in search algorithms, especially when considering metaheuristic optimization models. Although various automated methods for algorithm configuration have been proposed to alleviate users from manually tuning parameters, there is still unexplored potential in dynamically adjusting certain algorithm parameters during execution, which can lead to enhanced performance. The main objective is to comparatively analyze the effectiveness of manual parameter tuning compared to a dynamic online configuration approach based on reinforcement learning. To this end, the State-Action-Reward-State-Action (SARSA) algorithm is adapted to adjust the parameters of a genetic algorithm, namely population size, crossover rate, mutation rate, and number of generations. Tests are conducted with these two methods on benchmark functions commonly used in the literature. Additionally, the proposed model has been evaluated in a practical problem of optimizing energy trading portfolios in the electricity market. Results indicate that the reinforcement learning-based algorithm tends to achieve seemingly better results than manual configuration, while maintaining very similar execution times. This result suggests that online parameter tuning approaches may be more effective and offer a viable alternative for optimization in metaheuristic algorithms.

Abstract
Purpose - This study, grounded in social cognitive career theory, aims to investigate the effects of the change to remote work during the COVID-19 pandemic on job security and job quality in Portugal. Design/methodology/approach - It adopts a quantitative methodology by conducting a nationwide geographical study. The sample consists of 2,001 employees working in companies registered in Portugal. It explores the impact of the change to remote work on job quality and job security. In addition, it explores the relevance of demographic, organizational and social factors to explain this relationship. Findings - The fi ndings reveal that the change to remote work has influenced the perception of job quality but not job security. Furthermore, demographic, organizational and social variables are factors that influence this perception. Research limitations/implications - Implications that digitalization can have on job security and quality, especially among the population with lower levels of education and more precarious working conditions, should be explored. It is also important to replicate this study in other countries, especially in emerging economies. Practical implications - By investigating job security, the study offers insights into the stability and predictability of employment during crises and disruptive events. By examining job quality, it delves into the multifaceted nature of work satisfaction, including factors like work-life balance, autonomy and fulfilment. Practically, the study provides valuable guidance for policymakers, organizations and individuals navigating remote work environments. Social implications - Understanding the implications for job security allows policymakers to design supportive policies and interventions to mitigate potential negative impacts on employment stability.Originality/value - This study uses a sufficiently comprehensive national sample to determine the impact of COVID-19 on employment. It offers both theoretical and practical contributions to increase knowledge about the phenomenon and provides a relevant guide for policymakers to adopt measures to mitigate the effects of the transition to remote work.

Abstract
Abstract Immunohistochemistry (IHC) is crucial for the clinical categorisation of breast cancer cases. Deep generative models may offer a cost-effective alternative by virtually generating IHC images from hematoxylin and eosin samples. This review explores the state-of-the-art in virtual staining for breast cancer biomarkers (HER2, PgR, ER and Ki-67) and benchmarks several models on public datasets. It serves as a resource for researchers and clinicians interested in applying or developing virtual staining techniques.

Abstract
Stroke significantly impacts both survivors and their caregivers, who face numerous challenges in providing care, including emotional distress, physical strain, and a lack of adequate training. While mobile health applications offer some support, they often focus on knowledge dissemination rather than practical skill development, and fail to address the unique, culturally specific needs of caregivers. Furthermore, technical limitations, such as poor internet connectivity and unclear interfaces, hinder the effectiveness of these tools. This research explores the use of gamification as an innovative solution to improve caregiver training and support. Through a systematic literature review following the PRISMA guidelines, studies related to caregiver challenges and existing mobile applications for stroke management were examined. The review highlights the need for comprehensive, tailored training programs, and suggests that gamified interventions could enhance caregiver engagement, motivation, and knowledge retention, ultimately improving both caregiver preparedness and patient outcomes. The findings emphasize the potential of gamification to bridge gaps in current caregiver training solutions, addressing both practical caregiving skills and emotional support needs.

Abstract
This paper presents an indoor benchmarking study of state-of-the-art 3D LiDAR-based Simultaneous Localization and Mapping (SLAM) algorithms using the newly developed IILABS 3D - iilab Indoor LiDAR-based SLAM 3D dataset. Existing SLAM datasets often focus on outdoor environments, rely on a single type of LiDAR sensor, or lack additional sensor data such as wheel odometry in ground-based robotic platforms. Consequently, the existing datasets lack data diversity required to comprehensively evaluate performance under diverse indoor conditions. The IILABS 3D dataset fills this gap by providing a sensor-rich, indoor-exclusive dataset recorded in a controlled laboratory environment using a wheeled mobile robot platform. It includes four heterogeneous 3D LiDAR sensors - Velodyne VLP-16, Ouster OS1-64, RoboSense RS-Helios-5515, and Livox Mid-360 - featuring both mechanical spinning and non-repetitive scanning patterns, as well as an IMU and wheel odometry for sensor fusion. The dataset also contains calibration sequences, challenging benchmark trajectories, and high-precision ground-truth poses captured with a motion capture system. Using this dataset, we benchmark nine representative LiDAR-based SLAM algorithms across multiple sequences, analyzing their performance in terms of accuracy and consistency under varying sensor configurations. The results provide a comprehensive performance comparison and valuable insights into the strengths and limitations of current SLAM algorithms in indoor environments. The dataset, benchmark results, and related tools are publicly available at https://jorgedfr.github.io/3d_lidar_slam_benchmark_at_iilab/

Abstract
The mobility sector is expected to significantly impact the power system by deploying battery electric vehicles (BEV) and fuel cell vehicles (FCEV). This work improves CEVESA, a market model for the long-term planning and operation of the Iberian Electricity Market, by modelling FCEV as an alternative to BEV and internal combustion vehicles (ICEV), and its impact on the H-2 demand and storage. The mobility and H-2 economy models interact with the power system through the electricity needs and price. CEVESA is then applied to estimate potential expansion paths of ICEV, BEV and FCEV mobility alternatives considering the total system costs and the EU decarbonization strategy. The findings suggest that if FCEVs technology matures, it could rival BEVs, offering greater system flexibility via electrolyzers and extended driving ranges for users.