Abstract

Abstract

Abstract
Public transport systems worldwide experienced significant declines in usage during the COVID-19 pandemic due to lockdowns and work-from-home mandates. While numerous studies have examined these phenomena, there is still a need for empirical evidence that not only documents what occurred but also provides actionable insights for future transport planning. This study aims to enhance understanding of public transport passengers' mobility behaviors during different stages of the pandemic, using the Metropolitan Area of Porto, Portugal, as a case study. Automated Fare Collection data from 2020 were analyzed and compared with data from the pre-pandemic year of 2019. The analysis included temporal, spatial, spatio-temporal, and sociodemographic dimensions. Key patterns and trends identified include a rapid recovery of ridership post-restriction easing, homogenized daily travel patterns, varied impacts on different transport modes, and significant shifts in demographic travel behaviors. These findings highlight the resilience of public transport demand and suggest that adaptive scheduling, enhanced safety measures, targeted support for vulnerable groups, promotion of off-peak travel, investment in bus infrastructure, and encouragement of multi-modal transport are essential strategies. Implementing these strategies can help improve public transport planning and mitigate the adverse effects of future crises.

Abstract
Since the advent of agriculture, humans have considered phytopharmaceutical products to control pests and reduce losses in farming. Sometimes some of these products, such pesticides, can potentially harm the soil life. In the literature there is evidence that AI and image processing can have a positive contribution to reduce phytopharmaceutical losses, when used in variable rate sprayers. However, it is possible to improve the existing sprayer system's precision, accuracy, and mechanical aspects. This work proposes spraying solution called GraDeS solution (Grape Detection Sprayer). GraDeS solution is a sprayer with two degrees of freedom, controlled by a AI-based algorithm to precisely treat grape bunches diseases. The experiments with the designed sprayer showed two key points. First, the deep learning algorithm recognized and tracked grape bunches. Even with structure movement and bunch covering, the algorithm employs several strategies to keep track of the discovered objects. Second, the robotic sprayer can improve precision in specified areas, such as exclusively spraying grape bunches. Because of the structure's reduced size, the system can be used in medium and small robots.

Abstract
This work proposes the use of a deep learning-based adversarial diffusion model to address the translation of contrast-enhanced from non-contrast-enhanced computed tomography (CT) images of the heart. The study overcomes challenges in medical image translation by combining concepts from generative adversarial networks (GANs) and diffusion models. Results were evaluated using the Peak signal to noise ratio (PSNR) and structural index similarity (SSIM) to demonstrate the model's effectiveness in generating contrast images while preserving quality and visual similarity. Despite successes, Root Mean Square Error (RMSE) analysis indicates persistent challenges, highlighting the need for continuous improvements. The intersection of GANs and diffusion models promises future advancements, significantly contributing to clinical practice. The table compares CyTran, CycleGAN, and Pix2Pix networks with the proposed model, indicating directions for improvement.

Abstract
Static source code analysis techniques are gaining relevance in automated assessment of programming assignments as they can provide less rigorous evaluation and more comprehensive and formative feedback. These techniques focus on source code aspects rather than requiring effective code execution. To this end, syntactic and semantic information encoded in textual data is typically represented internally as graphs, after parsing and other preprocessing stages. Static automated assessment techniques, therefore, draw inferences from intermediate representations to determine the correctness of a solution and derive feedback. Consequently, achieving the most effective semantic graph representation of source code for the specific task is critical, impacting both techniques' accuracy, outcome, and execution time. This paper aims to provide a thorough comparison of the most widespread semantic graph representations for the automated assessment of programming assignments, including usage examples, facets, and costs for each of these representations. A benchmark has been conducted to assess their cost using the Abstract Syntax Tree (AST) as a baseline. The results demonstrate that the Code Property Graph (CPG) is the most feature -rich representation, but also the largest and most space -consuming (about 33% more than AST).