Abstract
Retailers offering Attended Home Delivery (AHD) struggle with thin profit margins due to high delivery costs and constrained routing flexibility. AHD requires retailers and customers to agree on specific time windows, limiting operational efficiency and increasing fleet requirements, particularly when customer preferences tend to cluster around peak times. While retailers have some ability to influence customer choices through pricing and availability strategies, failing to account for fleet costs and delivery constraints can lead to inefficient operations and reduced profitability. This study introduces an integrated approach to fleet sizing and time-window pricing for price-sensitive customers. We propose a Mixed Integer Programming (MIP) model that maximizes profit by balancing revenue and delivery costs, leveraging a nonparametric rank-based choice model to capture customer behavior while explicitly considering routing constraints and fleet ownership expenses over multiple periods. Using computational experiments on small-sized instances inspired by real-world data, we evaluate the impact of explicitly modeling routing costs, compare different pricing strategies, examine the effects of multi-period fleet planning, and assess sensitivity to varying customer and cost conditions. Results show that explicitly modeling routing constraints reduces profit loss by 29% compared to traditional cost approximations but increases computational complexity. To address this, we develop a Fix & Optimize (F&O) matheuristic approximate solution method that enables the application of our model to larger instances. Our findings emphasize the need for retailers to integrate demand management and fleet planning to optimize operational profitability.

Abstract
The rapid expansion of offshore wind farms and the development of energy islands for green hydrogen production have introduced futuristic off-grid systems. These systems can experience total shutdowns, necessitating black start solutions to ensure reliable restoration capabilities for isolated offshore wind farms. This paper investigates a grid-forming converter sizing strategy to enable black start capabilities in off-grid offshore wind farms. The study evaluates the impact of different energization strategies on battery energy storage system (BESS) sizing, focusing on soft energization with droop control in wind turbines and electrolyzers, the effects of wind turbine ramp rates on BESS requirements, and the role of switchable shunt reactors at the offshore substation for reactive power management. A comparative analysis is conducted between soft + hard and pure soft energization sequences to assess their impact on BESS converter sizing. Results demonstrate that the combined soft + hard energization strategy significantly reduces BESS converter size, offering a more cost-effective black start solution compared to pure soft energization.

Abstract
Hierarchical document classification is essential for structuring large-scale textual corpora in domains such as digital libraries and academic repositories. While recent advances in large language models (LLMs) have opened new possibilities for text classification, their applicability to hierarchical settings under real-world constraints remains underexplored. This study investigates both generative and discriminative transformer-based models, evaluating their effectiveness across multiple inference strategies: zero-shot baseline, local fine-tuning, and a global approach using category-specific models. Experiments on two real-world hierarchical datasets provide a comprehensive comparison of classification accuracy, F1-macro scores, and inference times. The results highlight that, although generative LLMs can deliver competitive (yet variable) performance at higher levels of the hierarchy, their high inference costs hinder their use in time-sensitive applications. In contrast, fine-tuned discriminative models—particularly BERT-based architectures—consistently offer a more favorable trade-off between performance and efficiency. © 2025 Elsevier B.V., All rights reserved.

Abstract
This research addresses the challenge of generating synthetic data that resembles real-world data while preserving privacy. With privacy laws protecting sensitive information such as healthcare data, accessing sufficient training data becomes difficult, resulting in an increased difficulty in training Machine Learning models and in overall worst models. Recently, there has been an increased interest in the usage of Generative Adversarial Networks (GAN) to generate synthetic data since they enable researchers to generate more data to train their models. GANs, however, may not be suitable for privacy-sensitive data since they have no concern for the privacy of the generated data. We propose modifying the known Conditional Tabular GAN (CTGAN) model by incorporating a privacy-aware loss function, thus resulting in the Private CTGAN (PCTGAN) method. Several experiments were carried out using 10 public domain classification datasets and comparing PCTGAN with CTGAN and the state-of-the-art privacy-preserving model, the Differential Privacy CTGAN (DP-CTGAN). The results demonstrated that PCTGAN enables users to fine-tune the privacy fidelity trade-off by leveraging parameters, as well as that if desired, a higher level of privacy.

Abstract
Our team previously introduced an innovative concept for an "invisible" Electrocardiography (ECG) system, incorporating electrodes and sensors into a toilet seat design to enable signal acquisition from the thighs. Building upon that work, we now present a novel dataset featuring real-world, single-lead ECG signals captured at the thighs, offering a valuable resource for advancing research on thigh-based ECG for cardiovascular disease assessment. To our knowledge, this is the first dataset of its kind. The tOLIet dataset comprises 149 ECG recordings collected from 86 individuals (50 females, 36 males) with an average age of 31.73 ± 13.11 years, a mean weight of 66.89 ± 10.70 kg, and an average height of 166.82 ± 6.07 cm. Participants were recruited through direct contact with the Principal Investigator at Centro Hospitalar Universitario de Lisboa Central (CHULC) and via clinical consultations conducted at the same institution. Each recording includes four differential signals acquired from electrode pairs embedded in the toilet seat, with reference signals obtained from a standard 12-lead hospital ECG system.

Abstract
Traditional machine learning techniques assume that data is drawn from a stationary source. This assumption is challenged in contexts with data streams for presenting constant and potentially infinite sequences whose distribution is prone to change over time. Based on these settings, detecting changes (a.k.a. concept drifts) is necessary to keep learning models up-to-date. Although state-of-the-art detection methods were designed to monitor the loss of predictive models, such monitoring falls short in many real-world scenarios where the true labels are not readily available. Therefore, there is increasing attention to unsupervised concept drift detection methods as approached in this paper. In this work, we present an unsupervised and interpretable method based on Radial Basis Function Networks (RBFN) and Markov Chains (MC), referred to as RMIDDM (Radial Markov Interpretable Drift Detection Method). In our method, RBF performs, in the intermediate layer, an activation process that implicitly produces groups of observations collected over time. Simultaneously, MC models the transitions between groups to support the detection of concept drifts, which happens when the active group changes and its probability exceeds a given threshold. A set of experiments with synthetic datasets and comparisons with state-of-the-art algorithms demonstrated that the proposed method can detect drifts at runtime in an efficient, interpretable, and independent way of labels, presenting competitive results and behavior. Additionally, to show its applicability in a real-world scenario, we analyzed new COVID-19 cases, deaths, and vaccinations to identify new waves as concept drifts and generate Markov models that allow understanding of their interaction.