56 documents found, page 1 of 6
The performance of bank portfolio optimization
Coelho, C.; Santos, J. L.; Judice, P.Given a liability structure, the bank portfolio optimization determines an asset allocation that maximizes profit, subject to restrictions on Basel III ratios and credit, liquidity, and market risks. Bank allocation models have not been tested using historical data. Using an optimization model based on turnover constraints, we develop such tests, which document the superior performance of optimization strategie...
The role of adaptive activation functions in fractional physics-informed neural...
Coelho, C.; Costa, M. Fernanda P.; Ferrás, Luís Jorge LimaIn this work, we use adaptive activation functions for regression fractional physics-informed neural networks (fPINNs) to approximate nonsmooth solutions. The adaptive activation function has better learning capabilities than the traditional one because it improves the convergence rate and solution accuracy. Our simulation results show that the adaptive parameter contributes less to the improvement of the resul...
The influence of neural networks on hydropower plant management in Agriculture:...
Coelho, C.; Costa, M. Fernanda P.; Ferrás, Luís Jorge LimaHydropower plants are crucial for stable renewable energy and serve as vital water sources for sustainable agriculture. However, it is essential to assess the current water management practices associated with hydropower plant management software. A key concern is the potential conflict between electricity generation and agricultural water needs. Prioritising water for electricity generation can reduce irrigati...
Prior knowledge meets neural odes: a two stage training method for improved exp...
Coelho, C.; Costa, M. Fernanda P.; Ferrás, Luís Jorge LimaNeural Ordinary Differential Equations (ODEs) have been used extensively to model physical systems because they represent a continuous-time function that can make predictions over the entire time domain. However, most of the time, the parameters of these physical systems are subject to strict laws/constraints. But there is no guarantee that the Neural ODE model satisfies these constraints. Therefore, we propose...
Improving public parking by using artificial intelligence
Albuquerque, L.; Coelho, C.; Costa, M. Fernanda P.; Ferrás, L. L.; Soares, A. J.In this work, a generic solution for parking management is presented. The solution uses artificial intelligence and remote data reading to implement a detection system, a server, a mobile phone application and a back office. With the mobile phone application, users can retrieve information about available parking spaces, specify their preferences and destination on the map, and receive local parking suggestions...
Optimization of traffic lights using supervised learning
Carrilho, D. S.; Coelho, C.; Costa, M. Fernanda P.; Ferrás, L. L.; Soares, A. J.With the increasing number of vehicles, conventional traffic lights with fixed times are unable to prevent traffic congestion at intersections . In this work, an intelligent traffic simulator is developed based on a Supervised Learning approach using artificial neural networks. The simulator makes decisions about which traffic light should be activated to minimise waiting times and maximise traffic flow, result...
The influence of the optimization algorithm in the solution of the fractional L...
Coelho, C.; Costa, M. Fernanda P.; Ferrás, L. L.In this paper, the influence of the optimization algorithms Adam, RMSprop, L-BFGS and SGD with momentum on the solution of Fractional Laplacian Equation (FLE) by physics-informed neural networks is analysed when considering two different analytical solutions, one smooth and one non-smooth. The influence of the optimization method, the smoothness of the analytical solution and the network configuration on the ac...
Nasal colonization by Staphylococcus aureusin Health Sciences students and anal...
Gomes-Sampaio, L. M.; Cláudia-Ferreira, A.; Prata, J. C.; Azevedo, R. M. S.; Pacheco, P.; Campos, Carla; Novais, C.; Peixe, L.; Dinis-Oliveira, R. J.Staphylococcus aureusis the leading bacterial cause of death globally. Nasal carriage of S. aureusincreases the risk of invasive infections, including by methicillin-resistant S. aureus(MRSA) strains, but studies including Portuguese university students (PUS) are scarce. To analyse the prevalence of methicillin-susceptible S. aureus(MSSA) and MRSA among PUS enrolled in different courses/years (1st-4th) at IUCS-...
Produção de farinha de larvas e pupas de zângão
Correia, Paula; Vouga, C.; Coelho, C.; Guiné, Raquel P. F.; Costa, Cristina Amaro DaA técnica da remoção dos quadros de zângão, utilizada no controlo do ácaro Varroa destructor, pode proporcionar uma fonte alternativa de alimento, sendo para isso necessário desenvolver técnicas simples e viáveis de extração e utilização das larvas e pupas. Este trabalho teve como objetivo testar dois métodos de extração, o método de extração a frio e a quente. Após a recolha os quadros foram congelados para ga...
Object detection with RetinaNet on aerial imagery: the Algarve landscape
Coelho, C.; Costa, M. Fernanda P.; Ferrás, Luís Jorge Lima; Soares, A. J.This work presents a study of the different existing object detection algorithms and the implementation of a Deep Learning model capable of detecting swimming pools from satellite images. In order to obtain the best results for this particular task, the RetinaNet algorithm was chosen. The model was trained using a customised dataset from Kaggle and tested with a newly developed dataset containing aerial images ...