Abstract
This paper addresses the problem of maximizing the expected size of a matching in the case of unreliable vertices and/or edges. The assumption is that the solution is built in several steps. Ina given step, edges with successfully matched vertices are made permanent; but upon edge or vertex failures, the remaining vertices become eligible for reassignment. This process maybe repeated a given number of times, and the objective is to end with the overall maximum number of matched vertices. An application of this problem is found in kidney exchange programs, going on in several countries, where a vertex is an incompatible patient-donor pair and an edge indicates cross-compatibility between two pairs; the objective is to match these pairs so as to maximize the number of served patients. A new scheme is proposed for matching rearrangement in case of failure, along with a prototype algorithm for computing the optimal expectation for the number of matched edges (or vertices), considering a possibly limited number of rearrangements. Computational experiments reveal the relevance and limitations of the algorithm, in general terms and for the kidney exchange application.

Abstract
Efficient public transportation management is essential for the development of large urban centers, providing several benefits such as comprehensive coverage of population mobility, reduction of transport costs, better control of traffic congestion, and significant reduction of environmental impact limiting gas emissions and pollution. Realizing these benefits requires a deeply understanding the population and transit patterns and the adoption of approaches to model multiple relations and characteristics efficiently. This work addresses these challenges by providing a novel dataset that includes various public transportation components from three different systems: regular buses, subway, and BRT (Bus Rapid Transit). Our dataset comprises daily information from about 700,000 passengers in Salvador, one of Brazil's largest cities, and local public transportation data with approximately 2,000 vehicles operating across nearly 400 lines, connecting almost 3,000 stops and stations. With data collected from March 2024 to March 2025 at a frequency lower than one minute, SUNT stands as one of the largest, most comprehensive, and openly available urban datasets in the literature.

Abstract
Management and reuse of wood waste can be a challenging process due to the frequent presence of hazardous contaminants. Conventional detection methods are often limited by the need for excessive sample preparation and lengthy and expensive analysis. Laser-induced Breakdown Spectroscopy (LIBS) is a rapid and micro- destructive technique that can be a promising alternative, providing in-situ and real-time analysis, with minimal to no sample preparation required. In this study, LIBS imaging was used to analyze wood waste samples to determine the presence of contaminants such as As, Ba, Cd, Cr, Cu, Hg, Pb, Sb, and Ti. For this analysis, a methodology based on detecting three lines per element was developed, offering a screening method that can be easily adapted to perform qualitative analysis in industrial contexts with high throughput operations. For the LIBS experimental lines selection, control and reference samples, and a pilot set of 10 wood wastes were analysed. Results were validated by two different X-ray Fluorescence (XRF) systems, an imaging XRF and a handheld XRF, that provided spatial elemental information and spectral information, respectively. The results obtained highlighted LIBS ability to detect highly contaminated samples and the importance of using a 3-line criteria to mitigate spectral interferences and discard outliers. To increase the dataset, a LIBS large-scale study was performed using 100 samples. These results were only corroborated by the XRF-handheld system, as it provides a faster alternative. In particular cases, ICP-MS analysis was also performed. The success rates achieved, mostly above 88 %, confirm the capability of LIBS to perform this analysis, contributing to more sustainable waste management practices and facilitating the quick identifi- cation and remediation of contaminated materials.

Abstract
Deep learning techniques have demonstrated significant potential in computer-assisted diagnosis based on medical imaging. However, their integration into clinical workflows remains limited, largely due to concerns about interpretability. To address this challenge, we propose Efficient-Proto-Caps, a lightweight and inherently interpretable model that combines capsule networks with prototype learning for lung nodule characterization. Additionally, an innovative Davies-Bouldin Index with multiple centroids per cluster is employed as a loss function to promote clustering of lung nodule visual attribute representations. When evaluated on the LIDC-IDRI dataset, the most widely recognized benchmark for lung cancer prediction, our model achieved an overall accuracy of 89.7 % in predicting lung nodule malignancy and associated visual attributes. This performance is statistically comparable to that of the baseline model, while utilizing a backbone with only approximately 2 % of the parameters of the baseline model’s backbone. State-of-the-art models achieved better performance in lung nodule malignancy prediction; however, our approach relies on multiclass malignancy predictions and provides a decision rationale aligned with globally accepted clinical guidelines. These results underscore the potential of our approach, as the integration of lightweight and less complex designs into accurate and inherently interpretable models represents a significant advancement toward more transparent and clinically viable computer-assisted diagnostic systems. Furthermore, these findings highlight the model’s potential for broader applicability, extending beyond medicine to other domains where final classifications are grounded in concept-based or example-based attributes. © 2013 IEEE.

Abstract
Medical image captioning is an essential tool to produce descriptive text reports of medical images. One of the central problems of medical image captioning is their poor domain description generation because large pre-trained language models are primarily trained in non-medical text domains with different semantics of medical text. To overcome this limitation, we explore improvements in contrastive learning for X-ray images complemented with soft prompt engineering for medical image captioning and conditional text decoding for caption generation. The main objective is to develop a softprompt model to improve the accuracy and clinical relevance of the automatically generated captions while guaranteeing their complete linguistic accuracy without corrupting the models’ performance. Experiments on the MIMIC-CXR and ROCO datasets showed that the inclusion of tailored soft-prompts improved accuracy and efficiency, while ensuring a more cohesive medical context for captions, aiding medical diagnosis and encouraging more accurate reporting. © 2025 Elsevier B.V., All rights reserved.

Abstract
In online three-dimensional packing problems where items are received one by one and require immediate packing decisions without prior knowledge of upcoming items, considering the static stability constraint is crucial for safely packing each arriving item in real time. Unstable loading patterns can result in risks of potential damage to items, containers, and operators during loading/unloading operations. Nevertheless, static stability constraints have often been neglected or oversimplified in existing online heuristic methods in the literature, undermining the practical implementation of these methods in real-world scenarios. In this study, we analyze how different static stability constraints affect solutions' efficiency and cargo stability, aiming to provide valuable insights and develop heuristic algorithms for real-world online problems, thus increasing the applicability of this research field. To this end, we embedded four distinct static stability constraints in online heuristics, including full-base support, partial-base support, center-of-gravity polygon support, and novel partial-base polygon support. Evaluating the impact of these constraints on the efficiency of a wide range of heuristic methods on real instances showed that regarding the number of used bins, heuristics with polygon- based stabilities have superior performance against those under full-base and partial-base support stabilities. The static mechanical equilibriumapproach offers a necessary and sufficient condition for the cargo static stability, and we employed it as a benchmark in our study to assess the quality of the four studied stability constraints. Knowing the number of stable items under each of these constraints provides valuable managerial insight for decision-making in real-world online packing scenarios.