Repository logo
 
Loading...
Profile Picture
Person

Teixeira Freitas, Diogo Nuno

Search Results

Now showing 1 - 9 of 9
  • Multiple Time Series Fusion Based on LSTM: An Application to CAP A Phase Classification Using EEG
    Publication . Mendonça, Fábio; Mostafa, Sheikh Shanawaz; Freitas, Diogo; Dias, Fernando Morgado; Ravelo-García, Antonio G.
    The Cyclic Alternating Pattern (CAP) is a periodic activity detected in the electroencephalo gram (EEG) signals. This pattern was identified as a marker of unstable sleep with several possible clinical applications; however, there is a need to develop automatic methodologies to facilitate real-world applications based on CAP assessment. Therefore, a deep learning-based EEG channels’ feature level fusion was proposed in this work and employed for the CAP A phase classification. Two optimization algorithms optimized the channel selection, fusion, and classification procedures. The developed methodologies were evaluated by fusing the information from multiple EEG channels for patients with nocturnal frontal lobe epilepsy and patients without neurological disorders. Results showed that both optimization algorithms selected a comparable structure with similar feature level fusion, consisting of three electroencephalogram channels (Fp2–F4, C4–A1, F4–C4), which is in line with the CAP protocol to ensure multiple channels’ arousals for CAP detection. Moreover, the two optimized models reached an area under the receiver operating characteristic curve of 0.82, with average accuracy ranging from 77% to 79%, a result in the upper range of the specialist agreement and best state-of-the-art works, despite a challenging dataset. The proposed methodology also has the advantage of providing a fully automatic analysis without requiring any manual procedure. Ultimately, the models were revealed to be noise-resistant and resilient to multiple channel loss, being thus suitable for real-world application.
  • Heuristic Optimization of Deep and Shallow Classifiers: An Application for Electroencephalogram Cyclic Alternating Pattern Detection
    Publication . Mendonça, Fábio; Mostafa, Sheikh Shanawaz; Freitas, Diogo; Dias, Fernando Morgado; Ravelo-García, Antonio G.
    Methodologies for automatic non-rapid eye movement and cyclic alternating pattern analysis were proposed to examine the signal from one electroencephalogram monopolar derivation for the A phase, cyclic alternating pattern cycles, and cyclic alternating pattern rate assessments. A population composed of subjects free of neurological disorders and subjects diagnosed with sleep-disordered breathing was studied. Parallel classifications were performed for non-rapid eye movement and A phase estimations, examining a one-dimension convolutional neural network (fed with the electroencephalogram signal), a long short-term memory (fed with the electroencephalogram signal or with proposed features), and a feed-forward neural network (fed with proposed features), along with a finite state machine for the cyclic alternating pattern cycle scoring. Two hyper-parameter tuning algorithms were developed to optimize the classifiers. The model with long short-term memory fed with proposed features was found to be the best, with accuracy and area under the receiver operating characteristic curve of 83% and 0.88, respectively, for the A phase classification, while for the non-rapid eye movement estimation, the results were 88% and 0.95, respectively. The cyclic alternating pattern cycle classification accuracy was 79% for the same model, while the cyclic alternating pattern rate percentage error was 22%.
  • Public perceptions, knowledge, responsibilities, and behavior intentions on marine litter: Identifying profiles of small oceanic islands inhabitants
    Publication . Bettencourt, Sara; Freitas, Diogo Nuno; Costa, Sónia; Caeiro, Sandra
    Marine litter is a global threat, particularly on oceanic islands where the problem is exacerbated. Perceptions, knowledge, awareness, and attitudes towards the theme are crucial in its mitigation and prevention. This study assessed these points through a questionnaire to the inhabitants of a Portuguese archipelago. Data revealed that people associate marine litter with plastic and its impacts and are well informed about its sources and pathways. Yet, the degradation rates of marine items were frequently underestimated and the problem of marine litter was attributed, among others, to littering, single-use products, and excessive packaging. Some individuals did not consider themselves responsible for reducing marine litter, attributing responsibilities to third parties. The youngest group, men, and students were the ones who reported less litter-reducing intentions and behaviors. Distinct profiles were traced using the questionnaire’s answers, highlighting who needs marine litter literacy. Individuals who do not consider marine litter a current threat and live in a community that does not care about marine litter (profiles 1 and 2) were the groups that needed deeper intervention, due to their low perception and understanding of the problem. Marine litter literacy, management, and governance measures are necessary so that the public recognizes marine litter as a current threat, is worried about its impacts, avoids plastic use, and choses re-useable products (profile 4). In the studied oceanic islands, results indicated marine litter is not fully perceived by the public. A global and transformative shift in the way people are educated and behave towards waste and pollution is required, thereby highlighting the importance of increasing public perceptions assessment and marine litter literacy in the society.
  • Particle swarm optimisation: a historical review up to the current developments
    Publication . Freitas, Diogo; Lopes, Luiz Guerreiro; Dias, Fernando Morgado
    The Particle Swarm Optimisation (PSO) algorithm was inspired by the social and biological behaviour of bird flocks searching for food sources. In this nature-based algorithm, individuals are referred to as particles and fly through the search space seeking for the global best position that minimises (or maximises) a given problem. Today, PSO is one of the most well-known and widely used swarm intelligence algorithms and metaheuristic techniques, because of its simplicity and ability to be used in a wide range of applications. However, in-depth studies of the algorithm have led to the detection and identification of a number of problems with it, especially convergence problems and performance issues. Consequently, a myriad of variants, enhancements and extensions to the original version of the algorithm, developed and introduced in the mid-1990s, have been proposed, especially in the last two decades. In this article, a systematic literature review about those variants and improvements is made, which also covers the hybridisation and parallelisation of the algorithm and its extensions to other classes of optimisation problems, taking into consideration the most important ones. These approaches and improvements are appropriately summarised, organised and presented, in order to allow and facilitate the identification of the most appropriate PSO variant for a particular application.
  • Open Rehab initiative: second development iteration
    Publication . Freitas, Diogo; Paulino, Teresa; Bermúdez i Badia, Sergi; Llorens, Roberto; Deutsch, Judith E.
    A substantial part of rehabilitation tools are developed in the context of research projects, which rarely reach their target audience, in particular clinicians and patients. To address this challenge, the Open Rehab Initiative (ORI) emerged as an international independent online portal with the goal of connecting clinicians, scientists, engineers, game developers, and end-users to interact and share virtual rehabilitation tools. The quality and efficacy of such platform can only be attained iteratively based on a user-centered design approach. This paper describes the design process and features implemented on the second development iteration subsequent to a formative evaluation of the first version of ORI. The main goal of the second iteration was to implement new features and make the platform functional and ready for a second evaluation process with beta testers, which will certainly prompt new features for improvement and will serve as a step toward the final release of the site.
  • A neural network-based approach for approximating arbitrary roots of polynomials
    Publication . Freitas, Diogo; Lopes, Luiz; Dias, Fernando Morgado
    Finding arbitrary roots of polynomials is a fundamental problem in various areas of science and engineering. A myriad of methods was suggested to address this problem, such as the sequential Newton’s method and the Durand–Kerner (D–K) simultaneous iterative method. The sequential iterative methods, on the one hand, need to use a deflation procedure in order to compute approximations to all the roots of a given polynomial, which can produce inaccurate results due to the accumulation of rounding errors. On the other hand, the simultaneous iterative methods require good initial guesses to converge. However, Artificial Neural Networks (ANNs) are widely known by their capacity to find complex mappings between the dependent and independent variables. In view of this, this paper aims to determine, based on comparative results, whether ANNs can be used to compute approximations to the real and complex roots of a given polynomial, as an alternative to simultaneous iterative algorithms like the D–K method. Although the results are very encouraging and demonstrate the viability and potentiality of the suggested approach, the ANNs were not able to surpass the accuracy of the D–K method. The results indicated, however, that the use of the approximations computed by the ANNs as the initial guesses for the D–K method can be beneficial to the accuracy of this method
  • Nature-inspired algorithms for solving some hard numerical problems
    Publication . Freitas, Diogo Nuno Teixeira; Lopes, Luiz Carlos Guerreiro; Dias, Fernando Manuel Rosmaninho Morgado Ferrão
    Optimisation 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.
  • Estereótipos de género entre os estudantes da formação de professores em educação infantil (0-10 anos): estudo de caso na Universidade da Madeira
    Publication . Mendonça, Alice; Brazão, Paulo; Nascimento, Andreia Micaela Sardinha do; Freitas, Diogo
    Embora a igualdade de género se encontre legalmente formalizada, os homens e as mulheres continuam a participar de forma distinta na sociedade, tal como atestam as estatísticas da Universidade da Madeira, onde em 2018/19, num total de 110 estudantes matriculados nos cursos de Formação de Professores para a Educação Infantil, apenas 3 são homens. Para determinarmos os motivos desse facto, aplicámos-lhes um inquérito por questionário. Concluímos que a abordagem das questões de género se encontra limitada a duas Unidades Curriculares e que, entre os estudantes, subsiste a ideia de que a feminização daquela profissão se encontra de tal modo enraizada que a implementação de quotas de género dificilmente conseguirá inverter esta tendência. A nível pedagógico, a diversidade e a heterogeneidade foram elencadas como fatores que permitem aumentar mais a produtividade das crianças. Ao nivel da cidadania, a divisão de tarefas entre os géneros acentua-se com o aumento da idade e em situação conjugal.
  • Things you need to know if you are writing a scientific paper, thesis or report in Engineering or Science
    Publication . Dias, F. Morgado; Freitas, Diogo; Ribeiro, Adriana
    This paper focuses on the common mistakes made by students at the early stages of research when writing scientific papers, thesis and reports. It points out mistakes to be avoided and the basic rules that can be inferred by reading a few scientific documents but are not usually clearly written and that we, as professors, end up teaching over and over again. The outcome of this paper will be, hopefully, that we will not need to correct the same common mistakes again and you, as a student, will have a faster lane to publishing. Starting with the abstract: it is composed of a single paragraph, does not contain acronyms or references and describes in short the work, main highlights and points out the results or main conclusions obtained from the work being presented. The abstract is an independent part of the paper and commonly has a character or word limit that you need to respect. It can be read as a “stand-alone” and the paper starts in the introduction, meaning that the introduction is not the sequence of the abstract and it can have some text in common if needed.