Inés M. Galván

• Professor
• University Carlos III de Madrid

(https://authors.elsevier.com/c/1kCzC2OYd7iqI)

https://authors.elsevier.com/c/1kI9z3QJ-dtJI0

Accurate solar radiation nowcasting models are critical for the integration of the increasing solar energy in power systems. This work explored the benefits obtained by the blending of four all-sky-imagers (ASI)-based models, two satellite-images-based models and a data-driven model. Two blending approaches (general and horizon) and two blending mo...

As the relevance of probabilistic forecasting grows, the need of estimating multiple high-quality prediction intervals (PI) also increases. In the current state of the art, most deep neural network gradient descent-based methods take into account interval width and coverage into a single loss function, focusing on a unique nominal coverage target,...

Machine learning is routinely used to forecast solar radiation from inputs, which are forecasts of meteorological variables provided by numerical weather prediction (NWP) models, on a spatially distributed grid. However, the number of features resulting from these grids is usually large, especially if several vertical levels are included. Principal...

Deep neural networks (DNN) are becoming increasingly relevant for probabilistic forecasting because of their ability to estimate prediction intervals (PIs). Two different ways for estimating PIs with neural networks stand out: quantile estimation for posterior PI construction and direct PI estimation. The former first estimates quantiles, which are...

Wind and solar energy forecasting have become crucial for the inclusion of renewable energy in electrical power systems. Although most works have focused on point prediction, it is currently becoming important to also estimate the forecast uncertainty. With regard to forecasting methods, deep neural networks have shown good performance in many fiel...

In the last years, there is an increasing interest for enhanced method for assessing and monitoring the level of the global horizontal irradiance (GHI) in photovoltaic (PV) systems, fostered by the massive deployment of this energy. Thermopile or photodiode pyranometers provide point measurements, which may not be adequate in cases when areal infor...

The aim of data transformation is to transform the original feature space of data into another space with better properties. This is typically combined with dimensionality reduction, so that the dimensionality of the transformed space is smaller. A widely used method for data transformation and dimensionality reduction is Principal Component Analys...

Galván, Inés M., Javier Huertas-Tato, Francisco J. Rodríguez-Benítez, Clara Arbizu-Barrena, David Pozo-Vázquez, and Ricardo Aler. Applied Soft Computing 109 (2021): 107531. https://doi.org/10.1016/j.asoc.2021.107531

Recent research has shown that the integration or blending of different forecasting models is able to improve the predictions of solar radiation. However, most works perform model blending to improve point forecasts, but the integration of forecasting models to improve probabilistic forecasting has not received much attention. In this work the esti...

The ability of four models to provide short-term (up to 6 h ahead) GHI and DNI forecasts in the Iberian Peninsula is assessed based on two years of data collected at four stations. The models follow (mostly) independent ap-proaches: one pure statistical model (Smart Persistence), one model based on CMV derived from satellite images (Satellite), one...

In this article we explore the blending of the four models (Satellite, WRF-Solar, Smart Persistence and CIADCast) studied in Part 1 by means of Support Vector Machines with the aim of improving GHI and DN I forecasts. Two blending approaches that use the four models as predictors have been studied: the horizon approach constructs a different blendi...

Prediction Intervals are pairs of lower and upper bounds on point forecasts and are useful to take into account the uncertainty on predictions. This article studies the influence of using measured solar power, available at prediction time, on the quality of prediction intervals. While previous studies have suggested that using measured variables ca...

While it is common to make point forecasts for solar energy generation, estimating the forecast uncertainty has received less attention. In this article, prediction intervals are computed within a multi-objective approach in order to obtain an optimal coverage/width tradeoff. In particular, it is studied whether using measured power as an another i...

Predicting solar irradiance is an active research problem, with many physical models having being designed to accurately predict Global Horizontal Irradiance. However, some of the models are better at short time horizons, while others are more accurate for medium and long horizons. The aim of this research is to automatically combine the prediction...

In this work two different machine learning approaches have been studied to predict wind power for different time horizons: individual and global models. The individual approach constructs a model for each horizon while the global approach obtains a single model that can be used for all horizons. Both approaches have advantages and disadvantages. E...

Image clustering is a critical and essential component of image analysis to several fields and could be considered as an optimization problem. Cuckoo Search (CS) algorithm is an optimization algorithm that simulates the aggressive reproduction strategy of some cuckoo species. In this paper, a combination of CS and classical algorithms (KM, FCM, and...

In this article, a filter feature weighting technique for attribute selection in classification problems is proposed (LIA). It has two main characteristics. First, unlike feature weighting methods, it is able to consider attribute interactions in the weighting process, rather than only evaluating single features. Attribute subsets are evaluated by...

The comparison between the real egg production curve and the graph proposed by management guidelines, aims towards continuous performance evaluation. The objectives of this study was to compare the capacity of curve fitting daily egg production of Lokhorst (LM), neural network multilayer perceptron (MP) and Jordan and Elman recurrent neural network...

A methodology, aimed to be fully operational, for automatic cloud classification based on the synergetic use of a sky camera and a ceilometer is presented. The Random Forest Machine Learning algorithm was used to train the classifier with 19 input features: 12 extracted from the sky-camera images and 7 from the ceilometer. The method was developed...

In the context of forecasting for renewable energy, it is common to produce point forecasts but it is also important to have information about the uncertainty of the forecast. To this extent, instead of providing a single measure for the prediction, lower and upper bound for the expected value for the solar radiation are used (prediction interval)....

This work deals with wind energy prediction using meteorological variables estimated by a Numerical Weather Prediction model in a grid around the wind farm of interest. Two machine learning techniques have been tested, Support Vector Machine and Gradient Boosting Regression, in order to study their performance and compare the results. The use of me...

Based on a large and recently developed database of 1-min irradiance and ancillary data observations at 54 world stations, this study uses the gradient boosting Machine Learning (ML) technique to improve the process of components separation, through which the direct and diffuse solar radiation components are estimated from 1-min global horizontal i...

In the automatic cloud classification problem it is very important to extract relevant features from the cloud images that can be used as inputs to the classifiers. Typically, sets of hand-designed features, based on the red, green, and blue channels, are used. For instance, spectral and textural, among other characteristics, are commonly extracted...

La comparación entre la curva de producción real del huevo y la gráfica propuesta por las pautas de gestión, tiene como objetivo la evaluación continua del rendimiento. Los objetivos de este estudio fueron comparar la capacidad de la curva de ajuste de la producción diaria de huevo de Lokjorst (LM), la red neuronal del perceptrón multicapa (MP) y l...

Obtaining high accuracy classification from Brain Computer Interfaces require to attach many electrodes on the scalp of subjects. On the other hand, their placement on the scalp involves generally a laborious and time consuming process. Therefore, it is important for the practitioner to estimate how many electrodes, and which ones, are needed to ob...

This article addresses two issues in solar energy forecasting from the numerical weather prediction (NWP) models using machine learning. First, we are interested in determining the relevant information for the forecasting task. With this purpose, a study has been carried out to evaluate the influence on accuracy of the number of NWP grid nodes used...

Forecasting solar energy is becoming an important issue in the context of renewable energy sources and Machine Learning Algorithms play an important rule in this field. The prediction of solar energy can be addressed as a time series prediction problem using historical data. Also, solar energy forecasting can be derived from numerical weather predi...

In this work, a methodology based on the combined use of a multilayer perceptron model fed using selected spectral information is presented to invert the radiative transfer equation (RTE) and to recover the spatial temperature profile inside an axisymmetric flame. The spectral information is provided by the measurement of the infrared CO2 emission...

Real world optimization of financial portfolios pose a challenging multiobjective problem that can be tackled using Evolutionary Algorithms. The fact that the optimization process is subject to the presence of uncertainty concerning asset returns is likely to lead to unreliable solutions. This work suggests extending the classic mean-variance optim...

Las Redes de Neuronas de Base Radial (RNBR) se comportan muy bien en la aproximación de funciones, siendo su convergencia extremadamente rápida comparada con las redes de neuronas de tipo perceptrón multicapa. Sin embargo, el diseño de una RNBR para resolver un problema dado, no es sencillo ni inmediato, siendo el número de neuronas de la capa ocul...

Constrained financial portfolio optimization is a challenging domain where the use of multiobjective evolutionary algorithms has been thriving over the last few years. One of the major issues related to this problem is the dependence of the results on a set of parameters. Given the nature of financial prediction, these figures are often inaccurate,...

An appropriate preprocessing of EEG signals is crucial to get high classification accuracy for Brain–Computer Interfaces (BCI). The raw EEG data are continuous signals in the time-domain that can be transformed by means of filters. Among them, spatial filters and selecting the most appropriate frequency-bands in the frequency domain are known to im...

Traditional mean–variance financial portfolio optimization is based on two sets of parameters, estimates for the asset returns and the variance–covariance matrix. The allocations resulting from both traditional methods and heuristics are very dependent on these values. Given the unreliability of these forecasts, the expected risk and return for the...

In the field of brain–computer interfaces, one of the main issues is to classify the electroencephalogram (EEG) accurately. EEG signals have a good temporal resolution, but a low spatial one. In this article, metaheuristics are used to compute spatial filters to improve the spatial resolution. Additionally, from a physiological point of view, not a...

The subject of financial portfolio optimization under real-world constraints is a difficult problem that can be tackled using multiobjective evolutionary algorithms. One of the most problematic issues is the dependence of the results on the estimates for a set of parameters, that is, the robustness of solutions. These estimates are often inaccurate...

In this paper, we propose a lazy learning strategy for building classification learning models. Instead of learning the models with the whole training data set before observing the new instance, a selection of patterns is made depending on the new query received and a classification model is learnt with those selected patterns. The selection of pat...

The main motivation of this paper is to propose a method to extract the output structure and find the input data manifold that best represents that output structure in a multivariate regression problem. A graph similarity viewpoint is used to develop an algorithm based on LDA, and to find out different output models which are learned as an input su...

The aim of this paper is to study the use of Evolutionary Multiobjective Techniques to improve the performance of Neural Networks (NN). In particular, we will focus on classification problems where classes are imbalanced. We propose an evolutionary multiobjective approach where the accuracy rate of all the classes is optimized at the same time. Thu...

Machine Learning techniques are routinely applied to Brain Computer Interfaces in order to learn a classifier for a particular user. However, research has shown that classification techniques perform better if the EEG signal is previously preprocessed to provide high quality attributes to the classifier. Spatial and frequency-selection filters can...

Proceeding of: Biomedical Engineering Systems and Technologies International Joint Conference: BIOSTEC 2009, Porto, Portugal, January 14-17, 2009 Abstract. This paper deals with the classification of signals for brain-computer interfaces (BCI).We take advantage of the fact that thoughts last for a period, and therefore EEG samples run in sequences b...

Nearest prototype methods can be quite successful on many pattern classification problems. In these methods, a collection of prototypes has to be found that accurately represents the input patterns. The classifier then assigns classes based on the nearest prototype in this collection. In this paper, we first use the standard particle swarm optimize...

The main motivation of this paper is to propose a method to extract the structure information from the output data and find the input data manifold that best represents that output structure. A graph similarity viewpoint is used to build up a clustering algorithm that tries to find out different linear models in a regression framework. The main nov...

In regression problems where the number of predictors exceeds the number of observations and the correlation between the predictors is high, a dimensionality reduction or a variable selection approach is demanded. In this paper we deal with a real application where we want to retrieve the physical characteristics of a combustion process from the me...

The aim os this paper is to study the hybridization of two multi-objective algorithms in the context of a real problem, the MANETs problem. The algorithms studied are Particle Swarm Optimization (MOPSO) and a new multiobjective algorithm based in the combination of NSGA-II with Evolution Strategies (ESN). This work analyzes the improvement produced...

This paper presents a new approach to Particle Swarm Optimization, called Michigan Approach PSO (MPSO), and its applica- tion to continuous classi cation problems as a Nearest Prototype (NP) classi er. In Nearest Prototype classi ers, a collection of prototypes has to be found that accurately represents the input patterns. The classi er then assign...

Most machine learning algorithms are eager methods in the sense that a model is generated with the complete training data set and, afterwards, this model is used to generalize the new test instances. In this work we study the performance of different machine learning algorithms when they are learned using a lazy approach. The idea is to build a cla...

This work presents the application of a parallel cooperative optimization approach to the broadcast operation in mobile ad-hoc networks (manets). The optimization of the broadcast operation implies satisfying several objectives simultaneously, so a multi-objective approach has been designed. The optimization lies on searching the best configuration...

Biosignals 2009. International Conference on Bio-inspired Systems and Signal Processing. Porto (Portugal), 14-17 January 2009 The context of this paper is the brain-computer interface (BCI), and in particular the classification of signals with machine learning methods. In this paper we intend to improve classification accuracy by taking advantage of...

Lazy learning methods have been used to deal with problems in which the learning examples are not evenly distributed in the input space. They are based on the selection of a subset of training patterns when a new query is received. Usually, that selection is based on the k closest neighbors and it is a static selection, because the number of patter...

In this paper, a combustion temperature retrieval approximation for high-resolution infrared ground-based measurements has been developed based on a multilayer perceptron (MLP) technique. The introduction of a selection subset of features is mandatory due to the problems related to the high dimensionality data and the worse performance of MLPs with...

Nearest Prototype methods can be quite successful on many pattern classification problems. In these methods, a collection of proto- types has to be found that accurately represents the input patterns. The classifier then assigns classes based on the nearest prototype in this collec- tion. In this paper we develop a new algorithm (called AMPSO), bas...

This paper presents an application of particle swarm optimization (PSO) to continuous classification problems, using a Michigan approach. In this work, PSO is used to process training data to find a reduced set of prototypes to be used to classify the patterns, maintaining or increasing the accuracy of the nearest neighbor classifiers. The Michigan...

In the domain of inductive learning from examples, usually, training data are not evenly distributed in the input space. This makes global and eager methods, like Neural Networks, not very accurate in those cases. On the other hand, lazy methods have the problem of how to select the best examples for each test pattern. A bad selection of the traini...

The use of high spectral resolution measurements to obtain a retrieval of certain physical properties related with the radiative transfer of energy leads a priori to a better accuracy. But this improvement in accuracy is not easy to achieve due to the great amount of data which makes difficult any treatment over it and it’s redundancies. To solve t...

Proceeding of: 16th International Conference on Artificial Neural Networks, ICANN 2006. Athens, Greece, September 10-14, 2006 Usually, training data are not evenly distributed in the input space. This makes non-local methods, like Neural Networks, not very accurate in those cases. On the other hand, local methods have the problem of how to know whi...

Radial Basis Neural Networks have been successfully used in many applications due, mainly, to their fast convergence properties. However, the level of generalization is heavily dependent on the quality of the training data. It has been shown that, with careful dynamic selection of training patterns, better generalization performance may be obtained...

Neural networks appear to be a promising tool to solve the so-called inverse problems focused to obtain a retrieval of certain physical properties related to the radiative transference of energy. In this paper the capability of neural networks to retrieve the temperature profile in a combustion environment is proposed. Temperature profile retrieval...

Proceeding of: 15th International Conferenceon Artificial Neural Networks ICANN 2005, Poland, 11-15 September, 2005 In BCI (Brain Computer Interface) research, the classification of EEG signals is a domain where raw data has to undergo some preprocessing, so that the right attributes for classification are obtained. Several transformational techniq...

This paper shows the performance of the binary PSO algorithm as a classification system. These systems are classified in two different perspectives: the Pittsburgh and the Michigan approaches. In order to implement the Michigan approach binary PSO algorithm, the standard PSO dynamic equations are modified, introducing a repulsive force to favor par...

Architecture design is a fundamental step in the successful application of Feed forward Neural Networks. In most cases a large number of neural networks architectures suitable to solve a problem exist and the architecture design is, unfortunately, still a human expert’s job. It depends heavily on the expert and on a tedious trial-and-error process....

Purpose of this work is to show that the Particle Swarm Optimization Algorithm may improve the results of same well known Machine Learning methods in the resolution of discrete classification problems. A binary version of the PSO algorithm is used to obtain a set of logic rules that map binary masks (that represent the attribute values), lo the ava...

Radial Basis Neural Networks have been successfully used in a large number of applications having in its rapid convergence time one of its most important advantages. However, the level of generalization is usually poor and very dependent on the quality of the training data because some of the training patterns can be redundant or irrelevant. In thi...

Many methods to codify artificial neural networks have been developed to avoid the disadvantages of direct encoding schema, improving the search into the solution's space. A method to analyse how the search space is covered and how are the movements along search process applying genetic operators is needed in order to evaluate the different encodin...

Lazy learning methods have been proved useful when dealing with problems in which the learning examples have multiple local functions. These methods are related with the selection, for training purposes, of a subset of examples, and making some linear combination to generate the output. On the other hand, neural network are eager learning methods t...

It has been shown that the selection of the most similar training patterns to generalize a new sample can improve the generalization capability of Radial Basis Neural Networks. In previous works, authors have proposed a learning method that automatically selects the most appropriate training patterns for the new sample to be predicted. However, the...

Different authors have developed modifications of the Kohonen Self-Organizing Maps to solve known combinatorial optimization problems. In this paper a modification of the Kohonen Map is proposed to solve the detection of white inter-text spaces in a digitized plain text documents. The idea relies on the fact that line extraction problem has several...

Many methods to codify artificial neural networks have been developed to avoid the defects of direct encoding schema, improving the search into the solution's space. A method to evaluate how the search space is covered and how movement along the search process applying genetic operators is needed in order to evaluate the different encoding strategi...

Proceeding of: International Conference on Artificial Neural Networks. ICANN 2002, Madrid, Spain, August 28-30, 2002 Automatic methods for designing artificial neural nets are desired to avoid the laborious and erratically human expert’s job. Evolutionary computation has been used as a search technique to find appropriate NN architectures. Direct a...

Designing the optimal neural net (NN) architecture can be formulated as a search problem in the architectures space, where each point represents an architecture. The search space of all possible architectures is very large, and the task of finding the simplest architecture may be an arduous and mostly a random task. Methods based on indirect encodi...

The level of generalization of neural networks is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of training patterns, better generalization performance may be obtained. Nevertheless, generalization is carried out ind...

In the recent years, the interest to develop automatic methods to determine appropriate architectures of feed-forward neural networks has increased. Most of the methods are based on evolutionary computation paradigms. Some of the designed methods are based on direct representations of the parameters of the network. These representations do not allo...

Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in many applications. However, the level of generalization is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of trainin...

This paper is focused on the development of non-linear neural models able to provide appropriate predictions when acting as process simulators. Parallel identification models can be used for this purpose. However, in this work it is shown that since the parameters of parallel identification models are estimated using multilayer feed-forward network...

Multi-step prediction is a difficult task that has attracted increasing interest in recent years. It tries to achieve predictions several steps ahead into the future starting from current information. The interest in this work is the development of nonlinear neural models for the purpose of building multi-step time series prediction schemes. In tha...

Abstract. Radial Basis Neural (RBN) network has the power of the universal approximation function and the convergence of those networks is very fast compared to multilayer feedforward neural networks. However, how to determine the architecture of the RBN networks to solve a given problem is not straightforward. In addition, the number of hidden uni...

Proceeding of: 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001 Granada, Spain, June 13–15, 2001 In the recent years, the interest to develop automatic methods to determine appropriate architectures of feed-forward neural networks has increased. Most of the methods are based on evolutionary computation paradig...

Radial Basis Neural (RBN) network has the power of the universal approximation function and the convergence of that networks is very fast compared to multilayer feedforward neural networks. However, how to determine the architecture of the RBN networks to solve a given problem is not straightforward. In addition, the number of hidden units allocate...

The level of generalization of a Multilayer feedforward neural networks is heavily dependent on the quality of the training data. Very often training set contains redundant or irrelevant patterns. It has been shown that with a careful and dynamic selection of the training patterns, better generalization performance may be obtained. Nevertheless, ge...

The class of feedforward neural networks trained with back-propagation admits a large variety of specific architectures applicable to approximation pattern tasks. Unfortunately, the architecture design is still a human expert job. In recent years, the interest to develop automatic methods to determine the architecture of the feedforward neural netw...

The design of the architecture is a fundamental step in the succesful application of a Neural Network. However, the architecture design is a human expert job. Therefore the development of automatic methods to determine the architecture of feed-forward neural networks is an interest field in the neural network comunity. Most of methods use direct re...

4th Conference of Systemics Cybernetics and Informatics. Orlando, 23-26 July 2000 The design of the architecture is a crucial step in the successful application of a neural network. However, the architecture design is basically, in most cases, a human experts job. The design depends heavily on both, the expert experience and on a tedious trial-and-...

Time series analysis using nonlinear dynamics systems theory and multilayer neural networks models have been applied to the time sequence of water level data recorded every hour at ‘Punta della Salute’ from Venice Lagoon during the years 1980–1994. The first method is based on the reconstruction of the state space attractor using time delay embeddi...

Multi-step prediction is a difficult task that has been attracted increasing the interest in recent years. It tries to achieve predictions several steps ahead into the future starting from information al time k. This paper is focused on the development of nonlinear neural models with the purpose of building long-term or multi-step time series predi...

Although nonlinear inverse and predictive control techniques based on artificial neural networks have been extensively applied to nonlinear systems, their use in real time applications is generally limited. In this paper neural inverse and predictive control systems have been applied to the real-time control of the heat transfer fluid temperature i...

Although nonlinear inverse and predictive control techniques based on artificial neural networks have been extensively applied to nonlinear systems, their use in real time applications is generally limited. In this paper neural inverse and predictive control systems have been applied to the real-time control of the heat transfer fluid temperature i...

This paper is focused on the development of nonlinear models, using artificial neural networks, able to provide appropriate predictions when acting as process simulators. The dynamic behaviour of the heat transfer fluid temperature in a jacketed chemical reactor has been selected as a case study. Different structures of NARMA (Non-linear ARMA) mode...

Congrès ESCAPE-3: European Symposium on Computer Aided Process Engineering n.3, Graz , Autriche, 1993 In this paper the use of neural networks for fitting complex kinetic data is discussed. To assess the validity of the approach two different neural network architectures are compared with the traditional kinetic identification methods for two cases...