Abstract
This study analyzes forest cover change patterns, agricultural expansion, and economic growth in Mozambique from 2001 to 2024, using remote sensing data from Global Forest Watch and socioeconomic indicators from the World Bank and FAO. Mozambique lost approximately 4.6 million hectares of forest during the analyzed period, with agriculture accounting for 97.4% of total deforestation. GDP per capita increased by 90.5%, while cultivated area expanded by 116.4%. However, agricultural productivity declined by 25.3%, revealing a paradox: production growth relied on extensive land expansion rather than intensification. Statistical analysis of three 8-year sub-periods identified significant differences in GDP per capita, agricultural GDP per capita, population, and agricultural employment (p < 0.001), but agricultural deforestation remained statistically stable (p = 0.065). This pattern suggests premature decoupling between economic growth and deforestation at income levels (USD 604) substantially below historical Environmental Kuznets Curve thresholds (USD 8000-10,000). However, this decoupling is fragile, driven by capital-intensive extractive sectors that generate GDP growth without absorbing rural populations. The persistence of extensive agricultural expansion, combined with weak governance, demographic pressures, and climate variability, indicates that observed stabilization represents an initial, vulnerable phase requiring structural transformation through agricultural intensification, inclusive industrialization, land tenure reform, and climate resilience building.

Abstract
High-throughput plant phenotyping (HTPP) enhances the throughput, resolution, and dimensionality of conventional manual phenotyping techniques. However, existing platforms face significant challenges, including high acquisition and maintenance costs, limited adaptability to field conditions, and inadequate data management capabilities. This paper introduces GREENTRIBE, an open-source, multi-sensor HTPP architecture that integrates Internet of Things sensing devices and robotics to collect, process, and manage comprehensive phenotypic and environmental data. GREENTRIBE features a multiscale sensing network, built on a sensor-independent communication protocol. An ontology-driven data management layer was designed in accordance with common standards and metadata guidelines, ensuring FAIR (Findable, Accessible, Interoperable, and Reusable) (meta)data. The architecture combines Computer Vision and Artificial Intelligence data analysis pipelines with a process-based crop model for data assimilation, allowing the quantitative traits derived from the sensing layer to be linked to contextual data (genotype, environment, and management conditions). The architecture and performance indicators are presented, demonstrating efficient data collection, processing, and management. Phenotyping is the cornerstone of GREENTRIBE, offering a valuable platform for generating data-rich, reproducible workflows, multimodal datasets, and analysis systems with high impact on Precision Agriculture, improving real-time monitoring, input application, and environmental impacts assessment towards maximized crop productivity, quality, and sustainability.

Abstract
Shipping container unloading is a physically demanding task often carried out under challenging conditions, which motivates the use of automation. However, automating this process is complex due to the unpredictable sizes and quantities of each shipment. Existing solutions tend to be task-specific, rely on closed software stacks, and offer limited information on performance in non-controlled environments, which restricts their adaptability. We present CARGO, a modular pipeline that enables a mobile manipulator equipped with regular sensors and actuators to unload containers autonomously. The pipeline employs a predefined, layered workflow composed of reconfigurable modules that can be adapted to various robots, ensuring that all boxes in a stack are systematically handled. In simulation, the pipeline successfully unloaded a full container without collisions, thereby validating the complete workflow. Laboratory tests further confirmed these results, with the mobile manipulator successfully unloading boxes across multiple trials, with a success rate of 97%. These results demonstrate that a versatile mobile manipulator can handle mixed box sizes and chaotic layouts using a generic, modular pipeline, highlighting a promising direction for flexible container-unloading automation. © 2026 IEEE.

Abstract
The limited availability and high cost of acquiring real-world image data impacts the creation of high-quality datasets, hindering the development of robust machine learning models, particularly in complex visual domains. This paper investigates the feasibility of enhancing image classification performance by incorporating balanced synthetic data into existing datasets. Three distinct machine learning tasks—image classification, instance detection, and image segmentation—were explored across diverse image domains. Synthetic images were generated to complement real-world data, and various testing scenarios were conducted, adjusting the relative weights of real and synthetic samples. The results demonstrate that balanced datasets, comprising an equitable mix of real and synthetic images, consistently yielded the highest performance metrics across all tasks. It was also observed that even a small introduction of synthetic data can improve performance over real data alone. The 50–50 split showed to optimally balance the realism of real data and the variability of synthetic data. Real data ensures that the model learns accurate representations of objects, while synthetic data enriches the training process with additional variations, reducing overfitting to specific real-world examples. The proposed approach highlights the potential of strategically integrating synthetic data to improve model accuracy and robustness, particularly in scenarios where real-world data is limited or challenging to acquire. © 2025 Elsevier B.V., All rights reserved.

Abstract
In the context of the diversity and complexity of laboratory processes, it is crucial to address the vulnerabilities associated with healthcare. Proper risk management becomes essential to ensure quality and safety in this environment. In this sense, the application of risk management tools and methodologies plays a crucial role in the identification, assessment and mitigation of potential risks present in laboratory processes performed, especially in a hospital environment. The present work addresses the theme of risk and safety management in a hospital environment, with the aim of promoting a safe environment for this community. The Healthcare Failure Mode and Effect Analysis methodology was applied to identify and mitigate the risks associated with medical equipment used in a medical genetics laboratory. The methodology included data collection, failure analysis, risk quantification, decision tree application and risk evaluation. Among the 19 failures analyzed none demonstrated a Risk Priority Number (RPN) greater than 8, suggesting that the equipment operates within acceptable risk thresholds. The results highlighted the importance of the safety of healthcare professionals and the proper functioning of equipment to ensure patient safety. The study contributed to the development of preventive and corrective actions, as well as providing future improvements and implementation of the methodology in other services of the hospital. © 2025 Elsevier B.V., All rights reserved.

Abstract
Stroke is a leading cause of long-term disability worldwide, with survivors often facing significant challenges in regaining upper-limb functionality. In response, robotic rehabilitation systems have emerged as promising tools to enhance post-stroke recovery by delivering precise, adaptable, and patient-specific therapy. This paper presents a review of robotic interfaces developed specifically for upper-limb rehabilitation. It analyses existing exoskeleton- and end-effector-based systems, with respect to three core design pillars: assistance types, control philosophies, and actuation methods. The review highlights that most solutions favor electrically actuated exoskeletons, which use impedance- or electromyography-driven control, with active assistance being the predominant rehabilitation mode. Resistance-providing systems remain underutilized. Furthermore, no hybrid approaches featuring the combination of robotic manipulators with actuated interfaces were found. This paper also identifies a recent trend towards lightweight, modular, and portable solutions and discusses the challenges in bridging research prototypes with clinical adoption. By focusing exclusively on upper-limb applications, this work provides a targeted reference for researchers and engineers developing next-generation rehabilitation technologies.