Abstract
Networks appear across various domains, and identifying central nodes in temporal networks is more challenging than in static networks. Temporal betweenness centrality is the widely used method to assess the importance of the nodes. This method is based on shortest temporal path calculations. However, computing this centrality metrics value is computationally intensive, especially for large-scale networks. Various approximation algorithms exist, but they often lack efficiency or accuracy. We introduce TGNN-Bet, a temporal graph neural network model, to approximate temporal betweenness centrality. In TGNN-Bet, each node gathers features from multi-hop neighbors, enabling the model to simulate paths and capture the reachability of nodes. The model's effectiveness is validated using the Spearman correlation (?) performance metric and comparing system runtimes with the existing temporal betweenness centrality method. Experimental results on six real-world temporal networks demonstrate that TGNN-Bet strongly correlates with existing temporal betweenness centrality methods. The proposed TGNN-Bet model achieves an average computation time reduction of 94.216% compared to conventional temporal betweenness centrality methods. © 2025 IEEE.

Abstract
Building rehabilitation is a reality; all rehabilitation work phases must be efficient and sustainable and promote healthy living places. Current procedures for assessing construction conditions are time-consuming, labour-intensive, and costly. They can threaten engineers' health and safety, especially when inspecting hard-to-reach and high-altitude sites. At the initial stage, a survey of the condition of the building is conducted, which later implies the preparation of a report on the existing pathologies, intervention solutions and associated costs. This procedure involves an inspection of the site (through photographs and videos). In addition, biological growths can threaten the health of those who frequent these places. The World Health Organization states that the most important effects are the increased prevalence of respiratory symptoms, allergies, asthma, and immune system disorders. This work aims to raise awareness of this fact and contribute to the identification of an automatic form of biological growth-type defects in images of buildings. To make this possible, we need a dataset of imaging building components with and without biological growths. Subsequently, deep learning methods are applied to allow the automatic identification of this type of defect in the images, and the results are analysed. A pre-trained VGG16 model was used. The dataset was annotated and divided into groups for training, validation, and testing. The model achieved an overall accuracy of 90%. This work demonstrates the potential of using Deep Learning (DL) in the maintenance and rehabilitation of urban infrastructures, highlighting the efficiency and sustainability of these processes and the importance of adjustments to ensure the stability of AI models. © 2025 The Author(s).

Abstract
Hyperbolic Metamaterials (HMM) are a class of photonic metamaterials exhibiting hyperbolic dispersion due to strong anisotropy. This work presents a numerical analysis and experimental characterization of a hyperbolic multilayer structure supporting surface plasmon polaritons for refractometric sensing applications. The device consists of a multilayer HMM composed of alternate Au and TiO2 layers, and the interaction of different plasmonic modes at each interface of the HMM is reported to enhance light- matter coupling, leading to an increased refractometric sensitivity. The hyperbolic dispersion and its effects on sensor performance are numerically investigated using the Effective Medium Theory (EMT) and validated through the Transfer Matrix Method (TMM). A fair match was obtained between EMT and TMM simulated spectra, validating the EMT approach for simulation of the optical properties of multilayer HMMs. Despite not predicting figures of merit (FOM) accurately, both the TMM and EMT approaches closely replicated the obtained experimental refractometric sensitivity.

Abstract
We studied the characteristics, regions of existence, and stability of different types of solitons for a distributed model of a mode-locked laser whose dispersion is purely quartic and normal. Among the different types of solitons, we identified three main branches that are named according to their different amplitude: low, medium, and high amplitude solitons. It was found that the first solitons are always unstable while the latter two exist and are stable in relatively large regions of the parameter space. Moreover, the stability regions of medium and high amplitude solitons overlap over a certain range of parameters, manifesting effects of bistability. The energy of high amplitude solitons increases quadratically with their width, whereas the energy of medium amplitude solitons may decrease or increase with the width depending on the parameter region. Furthermore, we have investigated the long term evolution of the continuous-wave solutions under modulational instability, showing that medium amplitude solitons can arise in this scenario. Additionally, we assessed the effects of second- and third-order dispersion on medium and high amplitude solitons and found that both remain stable in the presence of these terms.

Abstract
Missing data is characterized by the presence of absent values in data (i.e., missing values) and it is currently categorized into three different mechanisms: Missing Completely at Random, Missing At Random, and Missing Not At Random. When performing missing data experiments and evaluating techniques to handle absent values, these mechanisms are often artificially generated (a process referred to as data amputation) to assess the robustness and behavior of the used methods. Due to the lack of a standard benchmark for data amputation, different implementations of the mechanisms are used in related research (some are often not disclaimed), preventing the reproducibility of results and leading to an unfair or inaccurate comparison between existing and new methods. Moreover, for users outside the field, experimenting with missing data or simulating the appearance of missing values in real-world domains is unfeasible, impairing stress testing in machine learning systems. This work introduces mdatagen, an open source Python library for the generation of missing data mechanisms across 20 distinct scenarios, following different univariate and multivariate implementations of the established missing mechanisms. The package therefore fosters reproducible results across missing data experiments and enables the simulation of artificial missing data under flexible configurations, making it very versatile to mimic several real-world applications involving missing data. The source code and detailed documentation for mdatagen are available at https://github.com/ArthurMangussi/pymdatagen.

Abstract
Algorithmic bias in healthcare mirrors existing data biases. However, the factors driving unfairness are not always known. Medical devices capture significant amounts of data but are prone to errors; for instance, pulse oximeters overestimate the arterial oxygen saturation of darker-skinned individuals, leading to worse outcomes. The impact of this bias in machine learning (ML) models remains unclear. This study addresses the technical challenges of quantifying the impact of medical device bias in downstream ML. Our experiments compare a perfect world, without pulse oximetry bias, using SaO(2) (blood-gas), to the actual world, with biased measurements, using SpO(2) (pulse oximetry). Under this counterfactual design, two models are trained with identical data, features, and settings, except for the method of measuring oxygen saturation: models using SaO(2) are a control and models using SpO(2) a treatment. The blood-gas oximetry linked dataset was a suitable testbed, containing 163,396 nearly-simultaneous SpO(2) - SaO(2) paired measurements, aligned with a wide array of clinical features and outcomes. We studied three classification tasks: in-hospital mortality, respiratory SOFA score in the next 24 h, and SOFA score increase by two points. Models using SaO(2) instead of SpO(2) generally showed better performance. Patients with overestimation of O-2 by pulse oximetry of >= 3% had significant decreases in mortality prediction recall, from 0.63 to 0.59, P < 0.001. This mirrors clinical processes where biased pulse oximetry readings provide clinicians with false reassurance of patients' oxygen levels. A similar degradation happened in ML models, with pulse oximetry biases leading to more false negatives in predicting adverse outcomes.