Percorrer por autor "Freitas, Diogo Nuno Teixeira"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Nature-inspired algorithms for solving some hard numerical problemsPublication . Freitas, Diogo Nuno Teixeira; Lopes, Luiz Carlos Guerreiro; Dias, Fernando Manuel Rosmaninho Morgado FerrãoOptimisation is a branch of mathematics that was developed to find the optimal solutions, among all the possible ones, for a given problem. Applications of optimisation techniques are currently employed in engineering, computing, and industrial problems. Therefore, optimisation is a very active research area, leading to the publication of a large number of methods to solve specific problems to its optimality. This dissertation focuses on the adaptation of two nature inspired algorithms that, based on optimisation techniques, are able to compute approximations for zeros of polynomials and roots of non-linear equations and systems of non-linear equations. Although many iterative methods for finding all the roots of a given function already exist, they usually require: (a) repeated deflations, that can lead to very inaccurate results due to the problem of accumulating rounding errors, (b) good initial approximations to the roots for the algorithm converge, or (c) the computation of first or second order derivatives, which besides being computationally intensive, it is not always possible. The drawbacks previously mentioned served as motivation for the use of Particle Swarm Optimisation (PSO) and Artificial Neural Networks (ANNs) for root-finding, since they are known, respectively, for their ability to explore high-dimensional spaces (not requiring good initial approximations) and for their capability to model complex problems. Besides that, both methods do not need repeated deflations, nor derivative information. The algorithms were described throughout this document and tested using a test suite of hard numerical problems in science and engineering. Results, in turn, were compared with several results available on the literature and with the well-known Durand–Kerner method, depicting that both algorithms are effective to solve the numerical problems considered.
- User profiling with feature selection and explainability: essays on three case studies across different domainsPublication . Freitas, Diogo Nuno Teixeira; Teixeira Freitas, Diogo Nuno; Dias, Fernando Manuel Rosmaninho Morgado Ferrão; Fermé, Eduardo LeopoldoUser profiling is the process of constructing a structured representation of the user within a system. This representation includes information such as preferences, behaviors, and characteristics. Based on the profile, the system can recommend services and products or, in this work, suggest actions. Machine learning methods are commonly used to this end, as they can identify complex patterns among large numbers of attributes. However, not all attributes are relevant. High-dimensional datasets often contain irrelevant, redundant, or noisy features that obscure valuable patterns and reduce model accuracy. To address this, dimensionality reduction techniques—particularly feature selection—are essential. Equally important is the ability to explain a model’s output, since understanding why a model produces a given outcome builds trust and clarifies which steps can change an undesirable situation. This thesis applies feature selection, explainability, causal discovery, and machine teaching techniques to user profiling. The goal is to support decision-making by identi fying the most relevant features, clarifying causal mechanisms, and ensuring that stake holders understand why recommendations are made. Specifically, we investigate the mRMR (minimum-Redundancy-Maximum-Relevance) method for feature selection, ex amine explainability strategies such as feature importance analysis and counterfactuals, apply causal discovery to map cause-and-effect relationships, and use machine teaching to explore profile simplification. We apply this approach in four domains: (i) Marine litter: developing static profiles to identify those who could benefit from literacy interventions; (ii) Football injuries: building predictive models based on player profile dynamics to forecast risk; (iii) Energy poverty: designing models, using counterfactuals, and applying causal discovery to understand health–poverty links; and (iv) Concept complexity: using machine teaching to study profile simplification. These applications show how profiling can deliver targeted literacy interventions, prevent sports injuries, inform preventive policies in energy poverty, and improve the efficiency of user representations and concept learnability.