Abstract
The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model's ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model's decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.

Abstract
Accurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.

Abstract
The impacts of the e-commerce growth have increased the urgency in designing and adopting new alternative delivery strategies. In this context, it is important to consider the particularities of each city like its terrain conditions. This article aims at exploring the impact of road slopes on parcel delivery operations, and how they condition the adoption and implementation of alternative, more sustainable delivery strategies. To this end, a microscopic traffic simulator was used to evaluate different delivery strategies including ICE vans, electric vans, and cargo bikes in three different slope scenarios. This evaluation was based on a medium-sized European city and conducted by comparing the same parcel delivery route at three levels: operational (route length, duration, and waiting time), energy consumption, and emissions. The results revealed that as the road slopes increased, more time was needed to deliver all packages, waiting times grew longer, and vehicles' energy consumption and emissions levels intensified. From the flat terrain to the most sloped terrain, there was an increase in duration of around 5% for traditional and electric vans, 35% for large cargo bikes, and 14% for small cargo bikes. The ICE van suffers a 105% increase in waiting time; the electric van 71%; the large cargo bike 68% and the small cargo bike 52%. Energy consumption also varied, with ICE vans and small cargo bikes consuming nearly 30% more energy, while electric vans and large cargo bikes consumed 4% and 60% more energy, respectively. The ICE van's emissions of CO, HC, PMx, NOx, and CO2 are 13%, 10%, 1%, 20%, and 29% higher, respectively. Moreover, in flatter terrains, the better strategies are the electric van or a large cargo bike, while in more sloped terrains, the most adequate one is the electric van. These findings suggest that the electric van is the best overall strategy for different terrains and different decision-making profiles, ranking first in more than 70% of the profiles across all three terrains.

Abstract

Abstract
This paper explores the use of Robotics and decentralized Multi-Agent Reinforcement Learning (MARL) for side-by-side navigation in Intelligent Wheelchairs (IW). Evolving from a previous work approach using traditional single-agent methodologies, it adopts a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to provide control input and enable a pair of IW to be deployed as decentralized computing agents in real-world environments, discarding the need to rely on communication between each other. In this study, the Flatland 2D simulator, in conjunction with the Robot Operating System (ROS), is used as a realistic environment to train and test the navigation algorithm. An overhaul of the reward function is introduced, which now provides individual rewards for each agent and revised reward incentives. Additionally, the logic for identifying side-by-side navigation was improved, to encourage dynamic alignment control. The preliminary results outline a promising research direction, with the IWs learning to navigate in various realistic hallways testing scenarios. The outcome also suggests that while the MADDPG approach holds potential over single-agent techniques for the decentralized IW robotics application, further investigation are needed for real-world deployment.

Abstract
Understanding geometric and biophysical characteristics is essential for determining grapevine vigor and improving input management and automation in viticulture. This study compares point cloud data obtained from a Terrestrial Laser Scanner (TLS) and various UAV sensors including multispectral, panchromatic, Thermal Infrared (TIR), RGB, and LiDAR data, to estimate geometric parameters of grapevines. Descriptive statistics, linear correlations, significance using the F-test of overall significance, and box plots were used for analysis. The results indicate that 3D point clouds from these sensors can accurately estimate maximum grapevine height, projected area, and volume, though with varying degrees of accuracy. The TLS data showed the highest correlation with grapevine height (r = 0.95, p < 0.001; R2 = 0.90; RMSE = 0.027 m), while point cloud data from panchromatic, RGB, and multispectral sensors also performed well, closely matching TLS and measured values (r > 0.83, p < 0.001; R2 > 0.70; RMSE < 0.084 m). In contrast, TIR point cloud data performed poorly in estimating grapevine height (r = 0.76, p < 0.001; R2 = 0.58; RMSE = 0.147 m) and projected area (r = 0.82, p < 0.001; R2 = 0.66; RMSE = 0.165 m). The greater variability observed in projected area and volume from UAV sensors is related to the low point density associated with spatial resolution. These findings are valuable for both researchers and winegrowers, as they support the optimization of TLS and UAV sensors for precision viticulture, providing a basis for further research and helping farmers select appropriate technologies for crop monitoring.