Browsing by Author "Ferreira, P. M."
Now showing 1 - 10 of 59
Results Per Page
Sort Options
- A comparison of four data selection methods for artificial neural networks and support vector machinesPublication . Khosravani, Hamid Reza; Ruano, Antonio; Ferreira, P. M.The performance of data-driven models such as Artificial Neural Networks and Support Vector Machines relies to a good extent on selecting proper data throughout the design phase. This paper addresses a comparison of four unsupervised data selection methods including random, convex hull based, entropy based and a hybrid data selection method. These methods were evaluated on eight benchmarks in classification and regression problems. For classification, Support Vector Machines were used, while for the regression problems, Multi-Layer Perceptrons were employed. Additionally, for each problem type, a non-dominated set of Radial Basis Functions Neural Networks were designed, benefiting from a Multi Objective Genetic Algorithm. The simulation results showed that the convex hull based method and the hybrid method involving convex hull and entropy, obtain better performance than the other methods, and that MOGA designed RBFNNs always perform better than the other models. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
- A convex hull-based data selection method for data driven modelsPublication . Khosravani, Hamid Reza; Ruano, Antonio; Ferreira, P. M.The accuracy of classification and regression tasks based on data driven models, such as Neural Networks or Support Vector Machines, relies to a good extent on selecting proper data for designing these models, covering the whole input range in which they will be employed. The convex hull algorithm can be applied as a method for data selection; however the use of conventional implementations of this method in high dimensions, due to its high complexity, is not feasible. In this paper, we propose a randomized approximation convex hull algorithm which can be used for high dimensions in an acceptable execution time, and with low memory requirements. Simulation results show that data selection by the proposed algorithm (coined as ApproxHull) can improve the performance of classification and regression models, in comparison with random data selection. (C) 2016 Elsevier B.V. All rights reserved.
- An overview of nonlinear identification and control with neural networks.Publication . Ruano, Antonio; Ferreira, P. M.; Fonseca, C. M.The aim of this chapter is to introduce background concepts in nonlinear systems identification and control with artificial neural networks. As this chapter is just an overview, with a limited page space, only the basic ideas will be explained here. The reader is encouraged, for a more detailed explanation of a specific topic of interest, to consult the references given throughout the text. Additionally, as general books in the field of neural networks, the books by Haykin [1] and Principe et al. [2] are suggested. Regarding nonlinear systems identification, covering both classical and neural and neuro-fuzzy methodologies, Reference 3 is recommended. References 4 and 5 should be used in the context of B-spline networks.
- Application of computational intelligence methods to greenhouse environmental modellingPublication . Ferreira, P. M.; Ruano, AntonioIn order to implement a model-based predictive control methodology for a research greenhouse several predictive models are required. This paper presents the modelling framework and results about the models that were identified. RBF neural networks are used as non-linear auto-regressive and non-linear auto-regressive with exogenous inputs models. The networks parameters are determined using the Levenberg-Marquardt optimisation method and their structure is selected by means of multi-objective genetic algorithms. By network structure we refer to the number of neurons of the networks, the input variables and for each variable considered its lagged input terms. Two types of models were identified: process models (greenhouse climate) and external disturbances (external weather). Pseudo-random binary signals were employed to generate control input commands for the greenhouse actuators, in order to build input/output data sets suitable for the process models identification. The final model arrangement consists of four interconnected models, two of which are coupled, providing greenhouse climate and external weather long term predictions.
- Application of radial basis function neural networks to a greenhouse inside air temperature modelPublication . Ferreira, P. M.; Faria, E. A.; Ruano, AntonioThe problem with the adequacy of radial basis function neural networks to model the inside air temperature as a function of the outside air temperature and solar radiation, and the inside relative humidity in an hydroponic greenhouse is addressed.
- Choice of RBF model structure for predicting greenhouse inside air temperaturePublication . Ferreira, P. M.; Ruano, AntonioThe application of the radial basis function neural network to greenhouse inside air temperature modelling has been previously investigated by the authors. In those studies, the inside air temperature is modelled as a function of the inside relative humidity and of the outside temperature and solar radiation. Several training and learning methods were compared and the application of the Levenberg-Marquardt optimisation method was found to be the best way to determine the neural network parameters. A second-order model structure previously selected in the context of dynamic temperature models identification, was used. The model is intended to be incorporated in a real-time predictive greenhouse environmental control strategy. It is now relevant to question if the model structure used so far, selected in a different modelling framework, is the most correct in some sense. In this paper the usefulness of correlation-based model validity tests is addressed in order to answer the question mentioned above.
- Cloud and clear sky pixel classification in ground-based all-sky hemispherical digital imagesPublication . Ferreira, P. M.; Martins, I.; Ruano, AntonioCloudiness is the non-predictable factor most a ecting the solar radiation reaching a particular location on the Earth surface. Therefore it has great impact on the performance of predictive solar radiation models for that location. This work represents one step towards the improvement of such models by using ground-to-sky hemispherical colour digital images as a means to estimate the fraction of visible sky corresponding to clouds and to clear sky. The general approach, common to many image processing applications, consists in finding one threshold on a given pixel intensity scale that segments the image pixels into clear sky and cloud. In order to allow the evaluation and comparison of image thresholding methods, the pixels of 410 images were manually classified as clear sky or cloud, establishing a reference database. Two well known image thresholding algorithms are tested and a neural network approach is presented. For the latter, a number of statistical measures is extracted from the images constituting a feature space of potential inputs for the neural network. The actual inputs and number of neurons to be employed are selected by means of a multi-objective genetic algorithm.
- CloudspotterPublication . Gomes, João; Ferreira, P. M.; Ruano, AntonioDevido a uma crescente consciência ambiental, a nível global, têm vindo a fazer-se inúmeros esforços para reduzir o consumo energético e, consequentemente, a pegada de carbono deixada pela população mundial.
- Comparison of on-line learning algorithms for RBF models in greenhouse environmental control problemsPublication . Ferreira, P. M.; Faria, E. A.; Ruano, AntonioThe problem with the adequacy of radial basis function neural networks to model the inside air temperature as a function of the outside air temperature and solar radiation, and the inside relative humidity in an hydroponic greenhouse is addressed.
- Correction: Ferreira, P.M., et al. A neural network based intelligent predictive sensor for cloudiness, solar radiation and air temperature. Sensors 2012, 12, 15750–15777Publication . Ferreira, P. M.; Gomes, João M.; Martins, I.; Ruano, AntonioAccurate measurements of global solar radiation and atmospheric temperature, as well as the availability of the predictions of their evolution over time, are important for different areas of applications, such as agriculture, renewable energy and energy management, or thermal comfort in buildings. For this reason, an intelligent, light-weight and portable sensor was developed, using artificial neural network models as the time-series predictor mechanisms. These have been identified with the aid of a procedure based on the multi-objective genetic algorithm. As cloudiness is the most significant factor affecting the solar radiation reaching a particular location on the Earth surface, it has great impact on the performance of predictive solar radiation models for that location. This work also represents one step towards the improvement of such models by using ground-to-sky hemispherical colour digital images as a means to estimate cloudiness by the fraction of visible sky corresponding to clouds and to clear sky. The implementation of predictive models in the prototype has been validated and the system is able to function reliably, providing measurements and four-hour forecasts of cloudiness, solar radiation and air temperature.