A carregar...
5 resultados
Resultados da pesquisa
A mostrar 1 - 5 de 5
- Projeto não invasivo de medição de glicose baseado em espectroscopia de infravermelho próximoPublication . Leite, Gabriel A.; Leite, Gabriel A.; Lima, José; Pereira, Ana I.; Monteiro, André Luiz RégisO Diabetes Mellitus, uma doença metabólica crônica, apresenta-se como um desafio global de saúde, com projeções de 642 milhões de casos até 2040. Atualmente, encontra-se entre as dez principais causas de morte em países de renda média-baixa, demandando monitoramento diário. A falta de técnicas não invasivas para medir a glicose torna esse processo repetitivo, doloroso e suscetível a infecções. Portanto, há uma urgência na pesquisa e desenvolvimento de tecnologias para auxiliar no tratamento e controle dos índices glicêmicos. A espectroscopia de infravermelho próximo, embora uma tecnologia previamente limi- tada pelo alto custo, agora está se popularizando devido aos avanços tecnológicos. Este projeto utiliza essa técnica para criar um protótipo destinado a medir diferentes concen- trações de glicose, tanto in vitro quanto in vivo. Os resultados deste estudo revelam que diferentes comprimentos de onda (625 nm, 950 nm, 1450 nm e 1720 nm) interagem de maneiras distintas com a glicose. Essas inte- rações resultam em notáveis diferenças diante das concentrações observadas nas análises realizadas, sendo essas concentrações de 50 até 2000 mg/dL de glicose. Em resumo, este estudo contribui para o avanço da pesquisa sobre diabetes. Os métodos utilizados para testes e análises demonstraram eficácia, embora seja necessária uma melhoria técnica para atender aos requisitos clínicos na medição não invasiva de glicose.
- Categorizing Students of the MathE Platform: A Fuzzy Clustering PerspectivePublication . Leite, Gabriel A.; Azevedo, Beatriz Flamia; Pacheco, Maria F.; Fernandes, Florbela P.; Pereira, Ana I.Active learning and technology integration offer enhanced student engagement and adaptive learning, accommodating diverse preferences. This work uses fuzzy clustering method to analyze the data of students who answer questions on the MathE platform. To do this, the Fuzzy c-means algorithm was used, which allows flexibility and adaptability in the clustering partitioning, especially in situations where data elements may exhibit overlapping characteristics or belong to multiple categories. Thereby, two datasets are considered: the first is composed of 121 students who answered questions from the Vector Space subtopic, and the second dataset comprises the answers of 297 students who answered to any topic or subtopic of the platform. The results show that the fuzzy clustering method is appropriate for analyzing the student’s data since most students are highly associated with more than one cluster. Besides, the findings can support the formulation of intervention strategies to improve the student’s academic achievement.
- Influence of habits and comorbidities on liver diseasePublication . Leite, Gabriel A.; Azevedo, Beatriz Flamia; Pacheco, Maria F.; Fernandes, Florbela P.; Pereira, Ana I.The prevalence of hepatocellular carcinoma is expected to continue increasing worldwide, and its difficulty in early detection highlights the need for advanced monitoring technologies. As the disease progresses, it has a serious impact on patients’ health, and in severe cases, liver transplantation becomes the only viable solution, reinforcing its importance as a global health problem. This study proposes the use of different artificial intelligence methods to compare and understand them related to liver disease. Well-known algorithms such as Random Forest and Multi-Layer Perceptron were tested, as well as ensemble methods that exploit different modeling structures. The results showed that AdaBoost, Random Forest, and Gradient Boosting performed best with Area Under the Curve of 0.89, 0.86, and 0.84 respectively. To analyze their influence on clinical results, the best-performing model was reapplied only to the non-biochemical features that compose the dataset. The results indicate that portal vein thrombosis, diabetes, and hypertension are the most influential variables, with contributions of 29.48%, 20.50%, and 16.60%, respectively.
- Fuzzy c-Means as a Decision Support Tool for Liver Disease Diagnosis Based on Data AnalysisPublication . Leite, Gabriel A.; Azevedo, Beatriz Flamia; Ferreira, Sofia Ribeiro; Pacheco, Maria F.; Fernandes, Florbela P.; Pereira, Ana I.The liver is a vital organ responsible for numerous essential functions in the body. Thus, liver disorders can have severe consequences on overall health and well-being. Early diagnosis and treatment of liver disorders are crucial to prevent complications such as cirrhosis, liver failure and liver cancer. In this work, a data analysis system aims to identify the most important features in defining liver disease and categorize sick patients according to the severity of the disease. The Indian Liver Patient Dataset was evaluated using a pre-processing data analysis method that considered the Z-score, the correlation, and the Recursive Feature Elimination. After identifying the most important characteristics of the patients, the Fuzzy c-means algorithm was used to classify them based on the severity of the disease. The results of the proposed methodology proved to be effective in creating a decision support system, since it was possible to identify four levels of severity among the patients.
- Multi-objective clustering algorithm applied to the mathE categorization problemPublication . Azevedo, Beatriz Flamia; Leite, Gabriel A.; Pacheco, Maria F.; Fernandes, Florbela P.; Rocha, Ana Maria A. C.; Pereira, Ana I.This work explores bio-inspired strategies and clustering techniques to propose an automatic clustering algorithm, named Multi-objective Clustering Algorithm (MCA). This algorithm uses a set of measure combinations to define the optimal number of clusters and the partitioning of the elements, minimizing an intra-clustering measure and maximizing an inter-clustering one. The MathE platform is an educational tool whose main objective is to assist students facing challenges in Mathematics at higher education level. Based on previous studies, the opinions of lecturers and students diverge regarding the difficulty level of the questions available on the platform. Therefore, this research aims to explore and develop a new clustering method for question categorization, taking into account the opinions of both lecturers and students about the difficulty levels of the questions. The Multi-objective Clustering Algorithm (MCA) is proposed to group the questions into clusters representing the difficulty level of the platform's questions. Compared with the k-means algorithm, the MCA results exhibit outstanding performance. Through a combination of multi-objective clustering measures, the MCA successfully achieved a set of optimal solutions (Hybrid Pareto front). This method empowers the decision-maker, enabling them to choose the most appropriate solution based on additional insights beyond the model.