Abstract
Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machine Learning (ML) model is deployed. However, examining a model's decision boundaries and identifying potential vulnerabilities typically requires access to the training and testing datasets, which may pose risks to data privacy and confidentiality. To improve transparency in organizations that handle confidential data or manage critical infrastructure, it is essential to allow external verification and validation of Al without the disclosure of private datasets. This paper presents Systematic Pattern Analysis (SPATA), a deterministic method that converts any tabular dataset to a domain-independent representation of its statistical patterns, to provide more detailed and transparent data cards. SPATA computes the projection of each data instance into a discrete space where they can be analyzed and compared, without risking data leakage. These projected datasets can be reliably used for the evaluation of how different features affect ML model robustness and for the generation of interpretable explanations of their behavior, contributing to more trustworthy AI.

Abstract
The increasing energy demand in seaport operations, driven by electrification and decarbonisation targets, requires enhanced tools for operational planning and flexibility management. This paper proposes a novel centralised Energy Management System designed for seaports, which, unlike previous approaches that mainly focused on cost minimisation jointly optimises Battery Energy Storage System scheduling, energy and reserve market participation, and carbon-intensity reduction. A key contribution of this work is the integration of CO\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_2$$\end{document} emission forecasts and day-ahead market data into a multi-objective formulation, allowing the Energy Management System not only to minimise operational costs but also to reduce indirect emissions. Additionally, a Traffic Light system is proposed to support operators' decision-making by providing actionable flexibility guidelines. A case study based on real-world data from the Port of Sines shows that this method achieves at least an 17% reduction on an annual basis compared to baseline operations, while ensuring cost efficiency. Results highlight the Energy Management System's potential as a decision-support tool for port authorities seeking to align operational efficiency with sustainability goals.

Abstract
The robot's energy efficiency can often be optimized during the early stage of robot design. The robot's speed highly influences its energy consumption, in particular, a robot's reference speed strongly influences the trade-off between energy consumption and mission duration, yet it is commonly selected as a fixed parameter, independently on the path geometry. An extensive offline simulation has been conducted at different speeds (0.3 ~m/s-1.1 ~m / s) to collect performance data for a Mecanum-wheeled robot. After a Pareto front analysis, an offline method based on a Random Forest Regressor has been developed to dynamically adjust the optimal reference speed for each path. The H8 controller has been preferred for its robustness and disturbance rejection for a range of speeds. The proposed approach was first evaluated on a held-out test set and subsequently assessed on a multi-goal navigation task comprising 15 sequential objectives. Comparative results against several fixed speed baselines demonstrate that the proposed speed selector achieves a favorable energy-time compromise. In particular it reduced total energy consumption by 7% at the cost of a minor increase in execution time of about 2% compared to a constant speed reference of 0.70 ~m/s, a speed that was identified as optimal for 45% of the studied paths.

Abstract
When the available data for a target domain is limited, transfer learning (TL) methods leverage related data-rich source domains to train and evaluate models, before deploying them on the target domain. However, most TL methods assume fixed levels of labeled and unlabeled target data, which contrasts with real-world scenarios where both data and labels arrive progressively over time. As a result, evaluations based on these static assumptions may not reflect how methods perform in practice. To support a more realistic assessment of TL methods in dynamic settings, we propose an evaluation framework that (1) simulates varying data availability over time, (2) creates multiple domains via resampling of a given dataset and (3) introduces inter-domain variability through controlled transformations, e.g., including time-dependent covariate and concept shifts. These capabilities enable the systematic simulation of a large number of variants of the experiments, providing deeper insights into how algorithms may behave when deployed. We demonstrate the usefulness of the proposed framework by performing a case study on a proprietary real-world suite of card payment datasets. To support reproducibility, we also apply the framework on the publicly available Bank Account Fraud (BAF) dataset. By providing a methodology for evaluating TL methods over time and in different data availability conditions, our framework supports a better understanding of model behavior in real-world environments, which enables more informed decisions when deploying models in new domains.

Abstract

Abstract