Browsing by Author "Ribeiro, Pedro"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
- Cardiovascular diseases diagnosis using an ECG multi-band non-linear machine learning framework analysisPublication . Ribeiro, Pedro; Sá, Joana; Paiva, Daniela; Rodrigues, Pedro MiguelBackground: cardiovascular diseases (CVDs), which encompass heart and blood vessel issues, stand as the leading cause of global mortality for many people. Methods: the present study intends to perform discrimination between seven well-known CVDs (bundle branch block, cardiomyopathy, myocarditis, myocardial hypertrophy, myocardial infarction, valvular heart disease, and dysrhythmia) and one healthy control group, respectively, by feeding a set of machine learning (ML) models with 10 non-linear features extracted every 1 s from electrocardiography (ECG) lead signals of a well-known ECG database (PTB diagnostic ECG database) using multi-band analysis performed by discrete wavelet transform (DWT). The ML models were trained and tested using a leave-one-out cross-validation approach, assessing the individual and combined capabilities of features, per each lead or combined, to distinguish between pairs of study groups and for conducting a comprehensive all vs. all analysis. Results: the 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 discrimination results ranged between 73% and 100%, the 𝑅𝑒𝑐𝑎𝑙𝑙 between 68% and 100%, and the 𝐴𝑈𝐶 between 0.42 and 1. Conclusions: the results suggest that our method is a good tool for distinguishing CVDs, offering significant advantages over other studies that used the same dataset, including a multi-class comparison group (all vs. all), a wider range of binary comparisons, and the use of classical non-linear analysis under ECG multi-band analysis performed by DWT.
- COVID-19 detection by means of ECG, Voice, and X-ray computerized systems: a reviewPublication . Ribeiro, Pedro; Marques, João Alexandre Lobo; Rodrigues, Pedro MiguelSince the beginning of 2020, Coronavirus Disease 19 (COVID-19) has attracted the attention of the World Health Organization (WHO). This paper looks into the infection mechanism, patient symptoms, and laboratory diagnosis, followed by an extensive assessment of different technologies and computerized models (based on Electrocardiographic signals (ECG), Voice, and X-ray techniques) proposed as a diagnostic tool for the accurate detection of COVID-19. The found papers showed high accuracy rate results, ranging between 85.70% and 100%, and F1-Scores from 89.52% to 100%. With this state-of-the-art, we concluded that the models proposed for the detection of COVID-19 already have significant results, but the area still has room for improvement, given the vast symptomatology and the better comprehension of individuals’ evolution of the disease.
- Detecção da doença de Alzheimer através de parâmetros não-lineares de sinais de falaPublication . Silva, Martim G.; Ribeiro, Pedro; Bispo, Bruno C.; Rodrigues, Pedro M.Este trabalho tem como objetivo a detecção da doença de Alzheimer (DA) através de parâmetros não-lineares de sinais de fala. Os parâmetros são extraídos de sub-bandas dos sinais, as quais são obtidas por meio da transformada Wavelet, e algumas das suas estatísticas descritivas são utilizadas como entrada para vários classificadores. Acurácias de 100, 77,8 e 85,2% são obtidas na detecção da DA entre mulheres, homens e todos, respectivamente, utilizando classificadores de regressão logística.
- Distinction of different colony types by a smart-data-driven toolPublication . Rodrigues, Pedro Miguel; Ribeiro, Pedro; Tavaria, Freni KekhasharúBackground: Colony morphology (size, color, edge, elevation, and texture), as observed on culture media, can be used to visually discriminate different microorganisms. Methods: This work introduces a hybrid method that combines standard pre-trained CNN keras models and classical machine-learning models for supporting colonies discrimination, developed in Petri-plates. In order to test and validate the system, images of three bacterial species (Escherichia coli, Pseudomonas aeruginosa, and Staphylococcus aureus) cultured in Petri plates were used. Results: The system demonstrated the following Accuracy discrimination rates between pairs of study groups: 92% for Pseudomonas aeruginosa vs. Staphylococcus aureus, 91% for Escherichia coli vs. Staphylococcus aureus and 84% Escherichia coli vs. Pseudomonas aeruginosa. Conclusions: These results show that combining deep-learning models with classical machine-learning models can help to discriminate bacteria colonies with good accuracy ratios.
- Exploring the relationship between CAIDE dementia risk and EEG signal activity in a healthy populationPublication . Manuel, Alice Rodrigues; Ribeiro, Pedro; Silva, Gabriel; Rodrigues, Pedro Miguel; Nunes, Maria Vânia SilvaBackground: Accounting for dementia risk factors is essential in identifying people who would benefit most from intervention programs. The CAIDE dementia risk score is commonly applied, but its link to brain function remains unclear. This study aims to determine whether the variation in this score is associated with neurophysiological changes and cognitive measures in normative individuals. Methods: The sample comprised 38 participants aged between 54 and 79 (M = 67.05; SD = 6.02). Data were collected using paper-and-pencil tests and electroencephalogram (EEG) recordings in the resting state, channels FP1 and FP2. The EEG signals were analyzed using Power Spectral Density (𝑃𝑆𝐷)-based features. Results: The CAIDE score is positively correlated with the relative power activation of the 𝜃 band and negatively correlated with the MMSE cognitive test score, and MMSE variations align with those found in distributions of EEG-extracted 𝑃𝑆𝐷-based features. Conclusions: The findings suggest that CAIDE scores can identify individuals without noticeable cognitive changes who already exhibit brain activity similar to that seen in people with dementia. They also contribute to the convergent validity between CAIDE and the risk of cognitive decline. This underscores the importance of early monitoring of these factors to reduce the incidence of dementia.
- Leitores sortudos: uma prática diferenciadora de fluência leitora no 1.º ano de escolaridadePublication . Almeida, Bianca; Lopes, Inês; Ribeiro, Pedro; Gonçalves, DanielaSão estas (e tantas outras) as palavras que, após o estudo das primeiras letras do alfabeto, vamos ouvindo nas salas de aula e nos encontros, mais ou menos formais, que temos com as famílias dos alunos do 1.ºano de escolaridade. A fim de harmonizar este processo de interiorização de processos de descodificação fonológica, que conduzirão os alunos ao processo de mobilização de competências com vista à fluência leitora, promovendo aquisição de hábitos de leitura no quotidiano, tendo em conta o Plano Nacional de Leitura, concebemos, para o primeiro ano um pequeno livro de leituras que consiste na dinâmica “Leitores Sortudos”. Este recurso consiste na compilação de frases variadas, com incidência no fonema abordado semana a semana. Em cada semana, os alunos realizam a leitura, em família, de quatro frases variadas. Cada familiar ouve a leitura das frases e regista um comentário sobre a mesma. São registados cinco comentários referentes a cinco leituras diferentes. Após esta atividade, e ainda na mesma semana, os alunos fazem no seu livro de leituras a ilustração da frase que preferiram ler. No início da semana seguinte, o professor recolhe e analisa todos os livros de leitura, pedindo aleatoriamente alguns alunos para efetuarem a leitura de algumas das frases e atribuindo um carimbo àqueles que cumpriram, na íntegra, com a tarefa semanal. Este carimbo consiste na letra inicial de uma palavra ou expressão em inglês (W de “Well Done”, G de “Good Work”, F de “Fantastic, entre outros). Articulamos, assim, esta dinâmica com a vertente da promoção do bilinguismo, presente no projeto da instituição educativa na qual implementamos o projeto. Deste modo, apresentar-se-ão resultados preliminares desta dinâmica promotora da interação escola família (Viana et al., 2010; Viana e Borges, 2016) e, ao mesmo tempo, o modo como todos os agentes de desenvolvimento e formação do aluno se colocam ao serviço da aprendizagem da leitura e escrita. Por outro lado, destacaremos o modo como o projeto, “Leitores Sortudos”, reforça as competências no domínio da leitura e como todos os implicados cooperam entre si, respeitando o ritmo, as especificidades e, sobretudo, o estilo de aprendizagem de cada aluno que, dentro daquele que é o “seu tempo”, conseguirá, mais tarde ou mais cedo, ler fluentemente, dando resposta aos pressupostos da recente legislação relativa à educação inclusiva (Decreto-Lei n.º 54/2018, de 6 de julho).
- Machine learning-based cardiac activity non-linear analysis for discriminating COVID-19 patients with different degrees of severityPublication . Ribeiro, Pedro; Marques, João Alexandre Lobo; Pordeus, Daniel; Zacarias, Laíla; Leite, Camila Ferreira; Sobreira-Neto, Manoel Alves; Peixoto Jr, Arnaldo Aires; Oliveira, Adriel de; Madeiro, João Paulo do Vale; Rodrigues, Pedro MiguelObjective: This study highlights the potential of an Electrocardiogram (ECG) as a powerful tool for early diagnosis of COVID-19 in critically ill patients with limited access to CT–Scan rooms. Methods: In this investigation, 3 categories of patient status were considered: Low, Moderate, and Severe. For each patient, 2 different body positions have been used to collect 2 ECG signals. Then, from each collected signal, 10 non-linear features (Energy, Approximate Entropy, Logarithmic Entropy, Shannon Entropy, Hurst Exponent, Lyapunov Exponent, Higuchi Fractal Dimension, Katz Fractal Dimension, Correlation Dimension and Detrended Fluctuation Analysis) were extracted every 1s ECG time-series length to serve as entries for 19 Machine learning classifiers within a leave-one-out cross-validation procedure. Four different classification scenarios were tested: Low vs. Moderate, Low vs. Severe, Moderate vs. Severe and one Multi-class comparison (All vs. All). Results: The classification report results were: (1) Low vs. Moderate - 100% of Accuracy and 100% of F1–Score; (2) Low vs. Severe - Accuracy of 91.67% and an F1–Score of 94.92%; (3) Moderate vs. Severe - Accuracy of 94.12% and an F1–Score of 96.43%; and (4) All vs All - 78.57% of Accuracy and 84.75% of F1–Score. Conclusion: The results indicate that the applied methodology could be considered a good tool for distinguishing COVID-19’s different severity stages using ECG signals. Significance: The findings highlight the potential of ECG as a fast and effective tool for COVID-19 examination. In comparison to previous studies using the same database, this study shows a 7.57% improvement in diagnostic accuracy for the All vs All comparison.
- Machine learning-driven GLCM analysis of structural MRI for Alzheimer’s disease diagnosisPublication . Oliveira, Maria João; Ribeiro, Pedro; Rodrigues, Pedro MiguelBackground: Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative condition that increasingly impairs cognitive functions and daily activities. Given the incurable nature of AD and its profound impact on the elderly, early diagnosis (at the mild cognitive impairment (MCI) stage) and intervention are crucial, focusing on delaying disease progression and improving patients’ quality of life. Methods: This work aimed to develop an automatic sMRI-based method to detect AD in three different stages, namely healthy controls (CN), mild cognitive impairment (MCI), and AD itself. For such a purpose, brain sMRI images from the ADNI database were pre-processed, and a set of 22 texture statistical features from the sMRI gray-level co-occurrence matrix (GLCM) were extracted from various slices within different anatomical planes. Different combinations of features and planes were used to feed classical machine learning (cML) algorithms to analyze their discrimination power between the groups. Results: The cML algorithms achieved the following classification accuracy: 85.2% for AD vs. CN, 98.5% for AD vs. MCI, 95.1% for CN vs. MCI, and 87.1% for all vs. all. Conclusions: For the pair AD vs. MCI, the proposed model outperformed state-of-the-art imaging source studies by 0.1% and non-imaging source studies by 4.6%. These results are particularly significant in the field of AD classification, opening the door to more efficient early diagnosis in real-world settings since MCI is considered a precursor to AD.
- Near-infrared spectroscopy machine-learning spectral analysis tool for blueberries (vaccinium corymbosum) cultivar discriminationPublication . Ribeiro, Pedro; Barbosa, Maria Inês; Sousa, Clara; Rodrigues, Pedro MiguelVaccinium corymbosum is one of the main sources of commercialized blueberries across the world. This species has a large number of distinct cultivars, leading to significantly different berries characteristics such as size, sweetness, production rate, and growing season. In this context, accurate cultivar discrimination is of significant relevance, and currently, it is mostly performed through berries examination. In this work, we developed a method to discriminate 19 cultivars from the V. corymbosum species through their leaves’ near-infrared spectra. Spectra were acquired from fresh blueberry leaves collected from two geographic regions and across three seasons. Machine-learning-based models, selected from a pool of 10 classifiers based on their discrimination power under a twofold stratified cross-validation process, were trained/tested with 1 to 20 components obtained by the application of data dimensionality reduction (DDR) techniques (dictionary learning, factor analysis, fast individual component analysis, and principal component analysis) to different near-infrared (NIR) spectra regions’ data, to either analyze a single spectral region and season or combine spectral regions and/or seasons for each side of the blueberry leaf. The percentage of correct cultivar discrimination ranged from 52.27 to 100%, with the best spectral results obtained with the adaxial side of the leaves in the fall (100% Accuracy); the fast ICA DDR technique was present in 83.33% of the best analyses (five out of six); and the LinearSVC was present in 66.67% (four out six best analyses). The results obtained in this work denote that near-infrared spectroscopy is a suitable and accurate technique for V. corymbosum cultivar discrimination.