A carregar...
359 resultados
Resultados da pesquisa
A mostrar 1 - 10 de 359
- Escalonamentos de tratamentos em unidades de saúdePublication . Leite, Ana; Pereira, Ana I.; Fernandes, AdíliaO problema de escalonamento de tratamentos em unidades de saúde é um tema atual na investigação operacional e bastante importante na área da gestão hospitalar, estando associado à redução de custos com o pessoal especializado bem como a redução de tempo de espera dos utentes.
- EUREKit - Jogos MatemáticosPublication . Fernandes, Florbela P.; Pacheco, Maria F.; Pereira, Ana I.A exposição EUREKit do Instituto Politécnico de Bragança é constituída por seis módulos de jogos de estratégia e de tabuleiro. A partir da exploração dos jogos e da sua relação com a Matemática, este projecto pretende, de uma forma didáctica e atractiva, contribuir para aumentar o interesse dos alunos de todos os níveis de ensino pela disciplina, motivar para a aprendizagem, melhorar a autoconfiança, a concentração, a atenção e o raciocínio lógico, estimular a imaginação e a capacidade de construir estratégias e fomentar o trabalho em equipa. Esta exposição pode ser requisitada gratuitamente por instituições de ensino e outras instituições ligadas à ciência e sua divulgação. Nesta comunicação, serão apresentados os jogos que constituem a EUREKit e os mesmos serão relacionados com conteúdos programáticos leccionados na Disciplina de Matemática nos vários níveis de ensino.
- E-Learning from nature: picking from nature the inspiration to teach and learn sciencePublication . Pereira, Ana I.; Ferreira, Olga; Barreiro, M.F.; Teixeira, Amílcar; Cortez, José Paulo; Aguiar, CarlosThis work aims to present the work done so far by he Polytechnic Institute of Bragança (IPB) within the projet E-learning form nature.
- A reduction method for semi-infinite programming by means of a global stochastic approachPublication . Pereira, Ana I.; Fernandes, Edite M.G.P.We describe a reduction algorithm for solving semi-infinite programming problems. The proposed algorithm uses the simulated annealing method equipped with a function stretching as a multi-local procedure, and a penalty technique for the finite optimization process. An exponential penalty merit function is reduced along each search direction to ensure convergence from any starting point. Our preliminary numerical results seem to show that the algorithm is very promising in practice.
- Interior point filter method to solve semi-infinite programming problemsPublication . Pereira, Ana I.; Costa, M. Fernanda P.; Fernandes, Edite M.G.P.We present a new reduction-type method for solving semi-infinite programming problems, where the multi-local optimization is carried out with a sequential simulated annealing algorithm, and the finite reduced problem is solved by an interior point method combined with a line search filter strategy to ensure the global convergence. Numerical experiments with a set of well-known problems are shown.
- Optimization of heat and ultrasound-assisted extraction of Eucalyptus globulus leaves reveals strong antioxidant and antimicrobial propertiesPublication . Lima, Laíres; Pereira, Ana I.; Vaz, Clara B.; Ferreira, Olga; Dias, Maria Inês; Heleno, Sandrina A.; Calhelha, Ricardo C.; Barros, Lillian; Carocho, MárcioThe extraction of phenolic compounds from eucalyptus leaves was optimized using heat and ultrasound-assisted techniques, and the bioactive potential of the resulting extract was assessed. The independent variables, including time (t), solvent concentration (S), and temperature (T) or power (P), were incorporated into a fivelevel central composite design combined with Response Surface Methodology. Phenolic content was determined by HPLC-DAD-ESI/MS and used as response criteria. The developed models were successfully fitted to the experimental data to identify the optimal extraction conditions. Heat-assisted extraction proved to be the most efficient method for phenolic recovery, yielding 27 ± 2 mg/g extract under optimal conditions (120 min, 76.5 ◦C, and 25 % ethanol, v/v). The extracts exhibited a high concentration of phenolic glycoside derivatives, including gallotannin, quercetin, and isorhamnetin. These findings suggest that the extracts hold promise as natural additives in food technology, owing to their moderate antimicrobial activity and strong antioxidant properties.
- XAI Framework for Fall Detection in an AAL SystemPublication . Messaoudi, Chaima; Kalbermatter, Rebeca B.; Lima, José; Pereira, Ana I.; Guessoum, Zahia; Kalbermatter, Rebeca B.The Ambient Assisted Living (AAL) systems are humancentered and designed to prioritize the needs of elderly individuals, providing them with assistance in case of emergencies or unexpected situations. These systems involve caregivers or selected individuals who can be alerted and provide the necessary help when needed. To ensure effective assistance, it is crucial for caregivers to understand the reasons behind alarm triggers and the nature of the danger. This is where an explainability module comes into play. In this paper, we introduce an explainability module that offers visual explanations for the fall detection module. Our framework involves generating anchor boxes using the K-means algorithm to optimize object detection and using YOLOv8 for image inference. Additionally, we employ two well-known XAI (Explainable Artificial Intelligence) algorithms, LIME (Local Interpretable Model) and Grad-CAM (Gradient-weighted Class Activation Mapping), to provide visual explanations.
- Optimization, Learning Algorithms and Applications (OL2A 2024) Part IPublication . Pereira, Ana I.; Fernandes, Florbela P.; Coelho, João Paulo; Teixeira, João Paulo; Lima, José; Pacheco, Maria F.; Lopes, Rui Pedro; Álvarez, Santiago T.This volume, CCIS 2280, contains the refereed proceedings of the 4th International Conference on Optimization, Learning Algorithms and Applications (OL2A 2024), a hybrid event held on July 24–26. OL2A provided a space for the research community on optimization and learning to get together and share the latest developments, trends and techniques as well as develop new paths and collaborations. OL2A had the participation of more than three hundred participants in an online and face-to-face environment throughout three days, discussing topics associated with areas such as optimization and learning and state-ofthe- art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty, and the 4th industrial revolution. Three special sessions were organized on the topics Learning Algorithms in Engineering Education, Optimization in the SDG context, and Optimization in Control Systems Design. The event accepted 41 papers. All papers were carefully reviewed and selected from 105 submissions. All the reviews were carefully carried out by a scientific committee of 115 researchers from twenty-six countries.
- Optimization, Learning Algorithms and Applications (OL2A 2024) Part IIPublication . Pereira, Ana I.; Coelho, João Paulo; Teixeira, João Paulo; Lima, José; Pacheco, Maria F.; Lopes, Rui Pedro; Álvarez, Santiago T.; Fernandes, Florbela P.This volume, CCIS 2280, contains the refereed proceedings of the 4th International Conference on Optimization, Learning Algorithms and Applications (OL2A 2024), a hybrid event held on July 24–26. OL2A provided a space for the research community on optimization and learning to get together and share the latest developments, trends and techniques as well as develop new paths and collaborations. OL2A had the participation of more than three hundred participants in an online and face-to-face environment throughout three days, discussing topics associated with areas such as optimization and learning and state-of-the- art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty, and the 4th industrial revolution. Three special sessions were organized on the topics Learning Algorithms in Engineering Education, Optimization in the SDG context, and Optimization in Control Systems Design. The event accepted 41 papers. All papers were carefully reviewed and selected from 105 submissions. All the reviews were carefully carried out by a scientific committee of 115 researchers from twenty-six countries.
- Optimizing Olive Disease Classification Through Hybrid Machine Learning and Deep Learning TechniquesPublication . Mendes, João; Moso, Juliet; Berger, Guido S.; Lima, José; Costa, Lino; Guessoum, Zahia; Pereira, Ana I.Olive trees play a crucial role in the global agricultural landscape, serving as a primary source of olive oil production. However, olive trees are susceptible to several diseases, which can significantly impact yield and quality. This study addresses the challenge of improving the diagnosis of diseases in olive trees, specifically focusing on aculus olearius and Olive Peacock Spot diseases. Using a novel hybrid approach that combines deep learning and machine learning methodologies, the authors aimed to optimize disease classification accuracy by analyzing images of olive leaves. The presented methodology integrates Local Binary Patterns (LBP) and an adapted ResNet50 model for feature extraction, followed by classification through optimized machine learning models, including Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), and Random Forest (RF). The results demonstrated that the hybrid model achieved a groundbreaking accuracy of 99.11%, outperforming existing models. This advancement underscores the potential of integrated technological approaches in agricultural disease management and sets a new benchmark for the early and accurate detection of foliar diseases.