The efficient management of power systems requires balancing electricity generation costs with associated environmental emissions under dynamically varying demand. This paper proposes a two-stage approach that combines machine learning (ML) with a metaheuristic optimization algorithm to address the dynamic economic–environmental load dispatch (DEELD) challenge. In the first stage, electricity consumption data are enriched with temporal features to capture demand patterns and enable accurate forecasting. In the second stage, the daily scheduling horizon is divided into multiple periods, and dispatch solutions are generated sequentially while enforcing ramp-rate constraints. To enhance operational realism, a priority-based generator scheduling mechanism is explicitly introduced, enforcing hierarchical unit commitment and reflecting practical dispatch policies. Rather than focusing on a single optimal solution, the proposed framework generates multiple feasible dispatch solutions and evaluates them using economic, environmental, and operational performance indicators. These solutions are then ranked according to predefined decision profiles, enabling system operators to select dispatch strategies that align with specific priorities. This transforms the dispatch process into a flexible decision-support tool capable of addressing diverse real-world requirements.

The rapid digitalization of financial services has transformed mobile peer-to-peer (P2P) payments, exemplified by Bizum in Spain, into a critical area for understanding and shaping consumer behavior. This paper examines the application of machine learning (ML) techniques for predicting individual adoption of P2P mobile payments, with a particular focus on the practical utility of predictions for FinTech companies and financial institutions, rather than solely on forecasting performance. It evaluates a range of individual classifiers alongside two ensemble learning methods - Hard Voting and a Weighted Average method - those aggregates predictions according to the strengths of each individual model. The results show that the ensemble learning methods not only improve forecast reliability but also bring practical operational value to FinTech stakeholders.

Employee attrition remains a persistent organizational challenge due to its economic cost, loss of accumulated knowledge, and impact on workforce stability. While extensive research has focused on predicting attrition using machine learning, effective retention decisions require more than accurate risk estimation. Organizations must prioritize limited intervention efforts by integrating heterogeneous assessments from different organizational units and accounting for contextual and policy-driven constraints. This paper proposes a cooperative and context-aware decision approach for employee attrition intervention prioritization. Multiple decision components, each reflecting a distinct organizational perspective and trained on different subsets of employee attributes, produce partial risk assessments. These assessments are aggregated through confidence-weighted integration and modulated by factors that may influence context encoding organizational priorities. Rather than competing with predictive performance benchmarks, this work demonstrates how heterogeneous automated assessments can be structured into a transparent and adaptable prioritization mechanism. The approach is evaluated on a public employee attrition dataset as a methodological testbed for cooperative, context-aware decision-making under constrained resources.

The 2030 Agenda for Sustainable Development, adopted by all United Nations Member States in 2015, has at its core the so called 17 Sustainable Development Goals (SDGs). The degree of achievement of the SDGs by a country is measured by a SDG Index: a value between 0 and 100, calculated from the aggregation and average of up to 251 indicators.Due to the information imprecision, which in many cases is of fuzzy nature, a fuzzy score FuSDG index was previously proposed to assess the degree of achievement of the SDGs of a particular country in a given year.As such achievement is measured over time, the aim of this contribution is to propose a three-step strategy to derive the basic components for a linguistic description of such evolution (starting from a given sequence of FuSDG values) to facilitate its understanding and make the potential analysis. The proposed strategy first requires the definition of linguistic labels for which two scenarios are proposed: a context-independent and a context-dependent one with their corresponding domains. Secondly, a label assignment method is proposed and finally a consolidation stage summarizes time periods with equal behavior followed by a confidence level calculation.An example is provided with information from the so-called BRICS countries to illustrate how the proposal works, the derived information, its potential and the future research topics that could be explored.

Automated Decision-Making (ADM) systems are increasingly deployed in complex socio-technical environments where decisions emerge from the interaction of multiple, heterogeneous automated systems rather than from a single system. Classical theories of decision-making, while insightful, provide limited guidance on how such systems can cooperate, manage uncertainty, and adapt their outputs to contextual constraints. Recently, the Cooperative Automated DEcision-MAking (CADEMA) framework was developed to address this gap and operationalize cooperative automated decision-making. In this paper, we briefly describe the CADEMA framework and illustrate a basic CADEMA-like system for solving fuzzy multi-objective optimization problems subject to contextual constraints.

The growing ubiquity of data and artificial intelligence has made it increasingly easy to construct decision models that automate or assist human decision-making. As organizations and infrastructures rely on multiple, heterogeneous Automated Decision-Making (ADM) systems, a new challenge emerges: how to integrate and reconcile their outputs into coherent, explainable, and context-aware collective decisions. This paper proposes a new conceptual and architectural framework, the Cooperative Automated Decision-Making System (CADEMAS), as a foundation for the study and design of cooperative decision architectures. CADEMAS formalizes the interaction among individual ADM systems through an Input Manager, an Output Manager, and a Context Model, allowing the transformation and aggregation of either homogeneous or heterogeneous decision outputs. CADEMAS generalizes cooperation across potentially heterogeneous decision agents, data types and goals, going beyond ensemble learning schemes, which combine homogeneous models over identical data. We argue that CADEMAS represents a necessary paradigm shift: from building isolated decision models to engineering cooperative ecosystems of decision-making entities. This paper outlines the theoretical basis, architectural elements, and implications for future research.

This work proposes a novel methodology for estimating time-dependent internal heat sources in bioheat transfer problems relevant to induced hyperthermia treatments. The approach is based on the Generalized Integral Transform Technique (GITT), with the transformed potential field solved using the Adomian Decomposition Method (ADM), thereby enabling an entirely mesh-free solution framework. The inverse formulation assumes that the source term can be expressed as a modified time-dependent Fourier expansion, with its coefficients estimated directly through a regularized Gauss-Newton procedure. Notably, under certain conditions such as temperature independent perfusion the method achieves convergence in a single iteration. The inverse analysis is conducted using synthetic skin-surface temperature data, representative of noninvasive measurements obtainable via infrared thermography. To assess the methodology's accuracy and robustness, simulations are performed for multilayer biological tissues with two different source profiles, considering both measurement noise and parametric uncertainties. Results demonstrate that the proposed technique accurately reconstructs the source intensity and temporal dynamics, even under challenging noise and uncertainty conditions, making it a promising tool for real-time thermal control in hyperthermia applications.

Performance evaluation is ubiquitous nowadays. A fundamental approach to assessing alternatives (e.g., students, employees, universities, countries) involves weighting criteria to calculate their final scores. Determining these weights is crucial, especially when alternatives are evaluated individually and without comparison with others. In such cases, achieving consensus on weights among evaluators is vital for fairness. In the context of students’ evaluation from a university course, this initial study analyzes whether different weight assignments significantly alter final scores and identifies which of those assignments lead to the highest scores. The data consists of 53 students across seven assignments, and a bootstrap analysis is performed for validation. Results indicate statistically significant score variations compared to predetermined weights, with the ’Sum of Ranks’ approach resulting in the highest scores over 90

This paper presents a novel methodology for estimating space- and time-dependent source terms in heat and mass diffusion problems. The approach combines classical integral transform techniques (CITTs) with the least squares optimization method, enabling an efficient reconstruction of source terms. The method employs a double expansion framework, using both spatial eigenfunction and temporal expansions. The new presented idea assumes that the source term can be expressed as a spatial expansion in eigenfunctions of the eigenvalue problem, and then each transient function associated with each term of spatial expansion is rewritten as an additional expansion, where the unknown coefficients approximating the transformed source enable the direct use of the solution in the objective function. This, in turn, results in a linear optimization problem that can be quickly minimized. Numerical experiments, including one-dimensional and two-dimensional scenarios, demonstrate the accuracy of the proposed method in the presence of noisy data. The results highlight the method’s robustness and computational efficiency, even with minimal temporal expansion terms.

The paper introduces PyLexFLP: an implementation of the lexicographic method for fuzzy linear programming (FLP) in the Python programming language. We first describe the types of FLP problems that can be solved with PyLexFLP, briefly comment on its basic features, and then illustrate it with a numerical example.

The present work presents two different approaches for an epidemic disease spreading process based on the already established SIR Model, the first approach uses a cellular automata approach to simulate an epidemy, the second approach usea a biflux spatial diffusion equation, based on the model developed by Bevilacqua and Galeão to simulate the same phenomena.The results are shown in figures and briefly commented.The goal is to present those two approaches that might allow for a better representation of the phenomena.

Multicriteria decision-making (MCDM) often involves evaluating or ranking alternatives on multiple attributes, a process that is far from trivial due to flexible preferences and uncertainty in the criteria importance. The recently proposed Weightless, Interval-Based Approach (WIBA) tackles these issues by relying on an ordering of the criteria (according to their relevance) instead of explicit weights and using interval scores to evaluate alternatives. Although originally proposed for selecting solutions of interest in the context of multi-objective and many objective optimization problems, it can be adapted to rank such solutions. However, the robustness of WIBA rankings has not been studied, and sensitivity analysis approaches based on perturbations of the weights cannot be applied. Furthermore, there is no friendly environment for exploring WIBA properties. This paper addresses these gaps by (1) introducing a novel local sensitivity analysis technique to explore how small perturbations in the order of criteria affect rankings, and (2) presenting WIBApp, a freely available visual software tool that implements WIBA features, including the proposed sensitivity analysis. Using a case study on the selection of technical universities, the paper first illustrates WIBA's flexibility and utility in real-world decision scenarios, enabling decision makers to effectively deal with uncertainty and complexity, and second shows how WIBApp simplifies data management, enhances analysis and facilitates comparisons among rankings. By advancing the theoretical foundations of WIBA and providing a practical implementation, this work contributes to providing decision makers with a robust framework for handling multi-criteria problems, enhancing the reliability of rankings and supporting informed decisions.

University ranking systems play a crucial role in assessing and comparing the performance of higher education institutions worldwide. These systems typically rely on weighted sum models to compute university scores across various criteria, such as teaching quality, research output, and international engagement. However, the imprecision inherent in some input data and in the assignment of weights often complicates the evaluation process. This paper addresses this issue by exploring the concept of imprecise scores, which avoids the assignment of explicit weights by using a ranking of criteria to generate intervals of possible scores for each university. Using this approach, this study demonstrates the value of preserving imprecision throughout the evaluation process, offering a more transparent and robust method for university ranking. The paper also shows a high agreement between rankings derived from imprecise scores with one from traditional fixed-weight ranking. Through this analysis, we aim to highlight the practical benefits of using imprecise scores in university evaluations and suggest potential avenues for future research.

Route personalization is essential for designing tourist trips, but incorporating all influencing factors into mathematical models is challenging. An alternative is to obtain a diverse set of high-quality routes in advance and rank them a posteriori based on user profiles, simplifying the models and enabling straightforward solutions. This paper examines the combined use of the Modeling to Generate Alternatives (MGA) technique and route similarity measures in a Tourist Trip Design Problem (TTDP) for the generation of diverse routes. Two MGA approaches were compared to a basic evolutionary algorithm (EA) that does not prioritize diversity. Results show that while the basic EA yields solutions with higher average tourist interest, the MGA methods yield more diverse solutions with acceptable tourist interest levels. Statistically significant differences in solution diversity were found between the MGA variants, but differences were not significant in terms of the tourist interest or when different route similarity measures were considered.

One of the crucial aspects of solving robust optimization over time (ROOT) problems is to efficiently approximate the robustness of the solutions. However, current progress in this area has been scarce to date. To help bridge this gap, this paper proposes an alternative approach to one of the predominant frameworks in this field. Specifically, we decouple the fit and prediction of future environments that occur for each fitness evaluation by just evaluating previously fitted surrogate models. In this way, we globally approximate the robustness of the solutions by learning fitness functions, rather than point-wise predicting values during the execution of the algorithm. Preliminary results obtained from computational experiments indicate that this approach can achieve significantly superior performances to the existing framework, especially for specific surrogate model configurations. Furthermore, we show that in certain cases where our algorithms are less efficient than the existing approach, such inefficiency is compensated by improvements in error.

Tourist trip design is a fast-growing area of research. Tourist interest, budget, travel style, safety, and the existence of travelers with special needs (for example, wheelchair accessibility) are some of the elements to consider for obtaining personalized routes. Including these elements in a single mathematical model can considerably complicate the solution process. Also, route decision-making is affected by the context (health, social, political, economic, etc.) in which decisions are made. In this paper, the first aim is to propose a three-step methodology to obtain contextualized solutions to a tourist trip design problem (TTDP) with time-dependent recommendation factors. The methodology consists of (1) providing a basic TTDP model that avoids the complexity of including contextual information, (2) obtaining a set of solutions to the problem using a Modeling to Generate Alternatives (MGA) approach, and (3) using a recently developed a posteriori method to include the contextual information through fuzzy propositions. The second aim of the paper is to evaluate three algorithmic strategies for the MGA step. Lastly, considering a context for people with mobility impairments, an example is solved using real data. The results show the usefulness of the proposed methodology in solving the TTDP with contextual information.

Automated Decision-Making Systems (ADS) have become pervasive across various fields, activities, and occupations, to enhance performance. However, this widespread adoption introduces potential risks, including the misuse of ADS. Such misuse may manifest when ADS is employed in situations where it is unnecessary or when essential requirements, conditions, and terms are overlooked, leading to unintended consequences. This research paper presents a thorough examination of the implications, distinctions, and ethical considerations associated with digitalization, digital transformation, and the utilization of ADS in contemporary society and future contexts. Emphasis is placed on the imperative need for regulation, transparency, and ethical conduct in the deployment of ADS.

The recently proposed Fuzzy Levenberg-Marquardt Damping Factor Updating Strategy (FLM) is used along with Tikhonov Regularization (TR) in order to solve a coupled conduction-radiation function estimation inverse problem. FLM consists of updating the Levenberg-Marquardt (LM) damping factor with the assist of Fuzzy Logic. To test the FLM algorithm combined with TR, a conduction-radiation problem is addressed, and it serves as test bed to the numerical experiments, where the objective is to obtain estimatives of parameters, such as the spatially variable scattering albedo, the thermal conductivity and the optical thickness, simultaneously, which is often performed separately. Two main test cases are presented, one considering only the radiation problem, used as benchmark, in order to investigate noise levels and hyperparameters. The second main test case deals with the coupled conduction-radiation heat transfer problem for different functional forms of the spatially variable scattering albedo. For all presented numerical experiments, good estimates were achieved for the sought functions and parameters. These results demonstrate that the methodology presented in this work, through the combination of the Fuzzy LM dampting factor updating strategy and the Tikhonov regularization scheme, may provide valuable tools for inverse heat transfer problems.

The cornerstone of the 2030 Agenda for Sustainable Development are the 17 Sustainable development goals (SDGs). These goals are measured through 109 indicators and, in very basic terms, the degree of achievement of the 17 SDGs for a country, the so called SDG Index, is calculated with a weighted sum without taking into account any priorities among the goals. Besides this, several facts are not considered: the different situations and priorities of every country, the different relevance that can be given to the SDGs and the potential imprecision in the data. Here we propose a fuzzy alternative to the SDG Index, called FuSDG, having two main features: 1) it does not require an explicit set of weights to model priorities among SDGs, 2) it implicitly considers the imprecision in the input data, and explicitly in the output value. A FuSDG value will be modelled with a triangular fuzzy number due to the reduced number of parameters required and the easy interpretation of its meaning. We illustrate the application of FuSDG over recent data, and we discuss potential issues.

Decisions made in areas such as economics, engineering, industry, and medical sciences are usually based on finding and interpreting solutions to optimization problems. When modeling an optimization problem, it should be clear that people do not make decisions in a vacuum or in isolation from the reality. So, there is always a decision-making context that, in addition to the natural constraints of the problem, acts as a filter on the candidate solutions available. If this fact is omitted, optimal but useless solutions to the problem can be obtained. In this article, we propose a systematic way of modeling contexts based on fuzzy propositions and two approaches (a priori and a posteriori) for solving optimization problems under their influence. In the proposed a priori approach, the context is explicitly included in the mathematical model of the problem. As this approach may have a limited application due to the increasing number of constraints and their nature, an a posteriori approach is proposed, in which a set of solutions, obtained by any means (like exact algorithms, simulation, or metaheuristics), are checked for their suitability to the context by using a multicriteria decision-making methodology. A simple fish harvesting problem in a sustainability context and a tourist trip design problem in a pandemic context were solved for illustration purposes. Our results provide researchers and practitioners with a methodology for more effective optimization and decision making.