Escola Superior de Tecnologia e Gestão
URI permanente desta comunidade:
Navegar
Percorrer Escola Superior de Tecnologia e Gestão por Objetivos de Desenvolvimento Sustentável (ODS) "03:Saúde de Qualidade"
A mostrar 1 - 10 de 46
Resultados por página
Opções de ordenação
- 5th Symposium of Applied Science for Young Researchers: Book of AbstractsPublication . Fernandes, Florbela P.; Torres, Helena; Pinto, Pedro; Malta, SilvestreThese are the abstracts of the 5th Symposium of Applied Science for Young Researchers – SASYR. This scientific event welcomed scientific works on the topics covered by the following four research centers: – CeDRI (from IPB, Instituto Politécnico de Bragança) – 2Ai (from IPCA, Instituto Politécnico do Cávado e do Ave) – GECAD (from IPP, Instituto Politécnico do Porto) – ADiT-lab (from IPVC, Instituto Politécnico de Viana do Castelo) The primary objective of SASYR 2025 is to create a welcoming and relaxed environment for young researchers to present their work, discuss recent findings, and explore new ideas. In this way, this event offers an opportunity for the CeDRI, 2Ai, GECAD, and ADiT-lab research communities to leverage synergies and promote collaborations, thereby enhancing the quality of their research. The SASYR 2025 took place at Instituto Politécnico de Viana do Castelo, Viana do Castelo, Portugal, on 2 July 2025.
- A relação dos fatores psicossociais na saúde e produtividade dos trabalhadores de uma IPSSPublication . Vilela, Catarina Machado; Oliveira, Rui; Cardim, SofiaO mundo laboral está em constante transformação, o que acarreta uma série de desafios, com aspetos tanto positivos como negativos. Os riscos associados à forma como o trabalho é planeado, organizado e gerido, bem como ao seu contexto económico e social, podem dar origem a sérios problemas de saúde física e mental, conhecidos como riscos psicossociais. Considerando que os profissionais das instituições de solidariedade social lidam diariamente com populações vulneráveis, como idosos e pessoas em situação de exclusão social, o contacto contínuo com esta realidade de sofrimento, doença, carência e até lidar com a morte pode provocar um desgaste emocional, tornando-os mais propensos a enfrentar riscos psicossociais. Neste sentido, o objetivo principal do estudo foi identificar os fatores psicossociais que afetam o seu dia a dia e como estes lidam com tais desafios. A metodologia utilizada teve por base uma revisão bibliográfica, que deu fundamentação teórica para conceitos fundamentais sobre a temática, foi também utilizada para o desenvolvimento dos inquéritos, para a sua aplicação também foi utilizado o método quantitativo descritivo. Os resultados obtidos demonstraram que, de uma forma geral, os riscos psicossociais apresentam níveis reduzidos, demonstrando, contudo, maior vulnerabilidade entre os ajudantes de ação direta, seguidos pelos profissionais de cozinha e, por último, pela equipa técnica. As exigências emocionais e físicas, o ritmo de trabalho, a sobrecarga de tarefas e a falta de reconhecimento foram identificados como fatores de maior impacto. Em suma, o estudo demonstra a importância de promover ambientes laborais saudáveis e emocionalmente equilibrados, de forma a promover o bem-estar dos trabalhadores, pois são o pilar essencial da eficácia e eficiência das organizações do setor social.
- Aplicação de identificação de episódios de fibrilação atrialPublication . Guerreiro, Nathan Antonio; Teixeira, João Paulo; Dajer, Maria EugeniaAs Doenças Cardiovasculares (DCVs) causam cerca de 18 milhões de mortes por ano, segundo a Organização Mundial da Saúde (OMS). Na Europa, mais de 10 milhões de pessoas são afetadas anualmente, com 3 milhões de óbitos registrados em 2021. No Brasil, são aproximadamente 400 mil mortes por ano, resaltando arritmias cardíacas. A fibrilação atrial (FA), arritmia mais comum, é caracterizada por ritmo cardíaco irregular. Diante desse cenário e alinhado ao papel social do engenheiro e ao Objetivo de Desenvolvimento Sustentável (ODS) “Garantir saúde e bem-estar para todos” da Organização das Nações Unidas (ONU), este trabalho apresenta o desenvolvimento de uma interface gráfica do usuário (GUI) para aquisição e classificação de eletrocardiogramas (ECG). O sistema foi implementado em MATLAB, integrando aquisição em tempo real com a plataforma BITalino c (derivação I, via Bluetooth), detecção dos picos R e classificação automática de episódios de FA com redes neurais LSTM. São extraídas quatro características principais a cada 60 ciclos cardíacos: intervalos RR e entropias de Shannon das ondas T, U e P. Após normalização, essas variáveis compõem os vetores de entrada da rede, que classifica como Outro Ritmo, Ritmo Normal e Ritmo FA. A aplicação permite ainda a visualização dos sinais em tempo real e a geração automática de relatórios em PDF. A validação com sinais da base de dados MIT-BIH Atrial Fibrillation demonstrou que a interface é funcional, e a acurácia de 98,17%, obtida em estudo anterior, evidencia seu potencial como ferramenta auxiliar na análise de ECGs em ambientes clínicos e domiciliares.
- The artificial intelligence act: insights regarding its application and implicationsPublication . Cabrera, Beatriz M.; Luiz, Luiz E.; Teixeira, João PauloThis paper deals with Europe's Artificial Intelligence Act, the first regulation on the subject and is considered an international milestone. Therefore, the introduction provides a historical overview of legislative developments on Artificial Intelligence in Europe until the current milestone, namely the approval of the AI Act text, which is currently being amended and translated into its official publication. Afterwards, the regulation is dealt with in detail; its nuances are presented, along with the conceptualisation of artificial intelligence in the regulation and the classification of artificial intelligence systems, which is based on risks to users, together with the mechanisms created to make the regulation more efficient, specifically the Artificial Intelligence Office. Ultimately, considering the great innovation on the subject, this work presents different opinions regarding the application of the regulation, its risk-based analysis and classification, expectations and views on the possible impacts of the act on the market, thereby seeking to expose society's receptiveness to the regulation created. Therefore, based on the discussion points, it can be concluded that the regulation, which will soon be in effect, brings different feelings to citizens and members of the European market, who are still insecure about the risk-based approach used, harbouring feelings of fear about the limitation of innovation. However, at the same time, there is hope, given that regulation is necessary to guarantee safe innovation in line with the fundamental rights set out by the European Union. It can also be concluded that the approval and forthcoming publication of the act is a small step towards the challenges that will arise. It is certain that, regardless of the different opinions that exist, it is necessary to start implementing the act to analyse its effects on the market, society, politics, the economy and, above all, on innovations in artificial intelligence systems.
- Binary classification of cardiac pathologies using deep learning: a PTB-XL dataset approachPublication . Chaabani, Mohamed Khalil; Teixeira, João Paulo; Slim , Mohamed AymenCardiovascular diseases, including myocardial infarction, remain among the leading causes of mortality worldwide. Timely and accurate diagnosis is critical for effective treatment but often requires labour-intensive manual analysis of clinical-grade electrocardiograms (ECGs). This dissertation proposes a novel deep learning-based approach for binary classification of cardiac pathologies, using the PTB-XL dataset. The final model architecture integrates EfficientNetB3 for spatial feature extraction and a Linformer block to capture long-range dependencies between ECG leads, the results prove its adaptability for ECG image classification tasks. Extensive experimentation and iterative model development were conducted to reach the final design. Early trials involved exploring different hyperparameter tuning like Optuna and Adam optimizer and a wide range of hyperparameter configurations, including different learning rates, dropout rates, batch sizes, and numbers of Linformer layers. These experiments were critical in finding the optimal combination of parameters that balanced computational efficiency and model accuracy. Comprehensive details of these trials and evaluations are provided in the report. The preprocessing pipeline involves selecting the ECGs and converting them to 11 images (aVR was excluded) each representing a lead, converting RGBA ECG images to RGB format and applying normalization to ensure compatibility with model input requirements. This preprocessing step addresses the unique format of the dataset and prepares it for high-performance neural network training. Initial results from the finalized model architecture have demonstrated promising performance, achieving an AUC (Area Under the Curve) of 85.02% and a F1-score of 78.94%. The achieved results are comparable to recent state-of-the-art models reported on the PTB-XL dataset, which typically range between 85% and 95% AUC for similar binary classification tasks. These results indicate that the model's AUC of 85.02% is promising but on the edge of the current state-of-the-art. These findings indicate strong potential for the system to support clinical decision-making by automating the classification of ECG data. Ongoing research aims to extend the current binary classification framework to multi-class scenarios, further enhancing its clinical applicability. Additionally, efforts are being made to improve the model for faster inference times, enabling real-time ECG analysis and improving its feasibility for deployment in healthcare settings.
- Classical Versus Wellness Thermalism: The Case of Portuguese Thermal Establishments Before and After the COVID-19 PandemicPublication . Alves, Maria José; Nunes, Alcina; Alves, Jéssica; Gonçalves, Estelle SilvaThermal/mineral springs are one of the fastest-growing subcategories of wellness tourism. Indeed, it is an activity that has steadily increased in all of Europe’s developed economies over the last few decades. The pandemic has raised awareness of the importance of healthy lifestyles and has subsequently led to a surge in consumption of experiences and travel, somehow motivated by wellness. This study analyses the evolution of thermal users’ alternation between wellness and classical thermalism in Portugal. The objective is achieved by applying exploratory and cluster data analysis to a Portuguese administrative database containing the number of user registers and revenues generated from 2012 to 2022. During this period, the wellness registers increased in most thermal establishments compared to the classic records, even if service diversification may be found in most thermal establishments. Still, the financial value added by wellness consumers does not seem to follow the previously observed shift. The establishments with more classical registers are still the ones that are able to generate the highest income per person.
- Classificação de sinais de ECG com técnicas explicáveis de inteligência artificialPublication . Martins, Hugo Fidalgo Oliveira; Teixeira, João PauloCardiovascular diseases are among the main causes of premature mortality, with atrial flutter representing a clinically relevant arrhythmia due to its association with stroke and heart failure. The eletrocardiogram (ECG) is the most suitable diagnostic method for evaluating chardiac rhytms. Automatic ECG interpretations have attempted to improve clinical practice. However, the lack of interpretability of existing models has limited their acceptance. This dissertation presents a framework for atrial flutter classification using raw 12- lead ECG signals from PTB-XL Database, Georgia 12-Lead ECG Challenge Database and Large 12-Lead ECG Database for Arrhythmia Study. A hybrid deep learning model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks was developed and trained under a 10-fold cross-validation scheme. To ensure model transparency, explainable artificial intelligence (XAI) mehods were applied: Shapley Additive Explanations (SHAP) was used to quantify the contribution of each lead, and Local Interpretable Model-Agnostic Explanations (LIME) was employed to highlight the most informative temporal segments at the patient level. The results demonstrate that the proposed approach achieves competitive performance while improving interpretability, thus contributing to more reliable and clinically meaningful applications of artificial intelligence in cardiology.
- Colorectal Polyp Segmentation: Impact of Combining Different Datasets on Deep Learning Model PerformancePublication . Araujo, Sandro Luis de; Scheeren, Michel Hanzen; Aguiar, Rubens Miguel Gomes; Mendes, Eduardo; Franco, Ricardo Augusto Pereira; Paula Filho, Pedro Luiz deColorectal cancer is a major health concern, ranking as one of the most common and deadly forms of cancer. It typically begins as polyps, which are abnormal growths in the intestinal mucosa. Identifying and removing these polyps through colonoscopy is a crucial preventative measure. However, even experienced professionals can overlook some polyps during examinations. In this context, segmentation algorithms can assist medical professionals by identifying areas in an image that correspond to a polyp. These algorithms, which rely on deep learning, require extensive image datasets to effectively learn how to identify and segment polyps. This study aimed to identify public colonoscopy image datasets that contain polyps and to examine how combining these datasets might affect the performance of a deep learning-based segmentation algorithm. After selecting the datasets and defining their combinations, we trained a segmentation algorithm on each combination. The evaluation of the trained models showed that merging datasets can enhance model generalization, with increases of up to 0.242 in the dice coefficient and 0.256 in the Intersection over Union (IoU). These improvements could lead to higher diagnostic accuracy in clinical settings, enhancing efforts to prevent colorectal cancer.
- Comparison of neural network architectures for diabetes predictionPublication . Guerreiro, Nathan Antonio; Nijo, Rui; Teixeira, João PauloDiabetes represents a significant global health challenge, with millions of individuals affected and substantial impacts on healthcare systems. In this study, we compare two neural network architectures for diabetes prediction: the Feedforward Neural Network (FFNN) and the Cascade-Forward Backpropagation Neural Network (CFBPNN). Utilizing the Diabetes Prediction Dataset, comprising 100,000 samples, and after a balanced result, 17,000 samples were obtained. The networks are trained using the Levenberg-Marquardt and Resilient Backpropagation algorithms, and performance metrics, including precision, sensitivity, specificity, accuracy, F1-score, and computational time, are evaluated. Results indicate that the FFNN architecture paired with the Levenberg-Marquardt algorithm demonstrates superior diagnostic prediction accuracy with 91,10%. However, this comes at the cost of longer computational time compared to the CFBPNN.
- Contributions to accelerating a numerical simulation of free flow parallel to a porous planePublication . Schepke, Claudio; Spigolon, Roberta A.; Rufino, José; Cristaldo, Cesar F. Da C.; Pizzolato, Glener L.Flow models over flat p orous surfaces have applications in natural processes, such as material, food, chemical processing, or mountain mudflow simulations. The development of simplified a nalytical or numerical models can predict characteristics such as velocity, pressure, deviation length, and even temperature of such flows for geophysical and engineering purposes. In this context, there is considerable interest in theoretical and experimental models. Mathematical models to represent such phenomena for fluid mechanics have continuously been developed and implemented. Given this, we propose a mathematical and simulation model to describe a free-flowing flow pa rallel toa porous material and its transition zone. The objective of the application is to analyze the influence o f t he p orous matrix on the flow u nder d ifferent m atrix p roperties. W e i mplement a Computational Fluid Dynamics scheme using the Finite Volume Method to simulate and calculate the numerical solutions for case studies. However, computational applications of this type demand high performance, requiring parallel execution techniques. Due to this, it is necessary to modify the sequential version of the code. So, we propose a methodology describing the steps required to adapt and improve the code. This approach decreases 5.3% the execution time of the sequential version of the code. Next, we adopt OpenMP for parallel versions and instantiate parallel code flows and executions on multi-core. We get a speedup of 10.4 by using 12 threads. The paper provides simulations that offer the correct understanding, modeling, and construction of abrupt transitions between free flow a nd porous media. The process presented here could expand to the simulations of other porous media problems. Furthermore, customized simulations require little processing time, thanks to parallel processing.