Search

Summary: One of the goals of efficient water supply management is the regular supply of clean water at the pressure required by consumers. In this context, predicting water consumption in urban areas is of key importance for water supply management. This prediction is also relevant in processes for reviewing prices; as well as for operational management of a water network. In this paper, we describe and compare a series of predictive models for forecasting water demand. The models are obtained using time series data from water consumption in an urban area of a city in south-eastern Spain. This includes highly non-linear time series data, which has conditioned the type of models we have included in our study. Namely, we have considered artificial neural networks, projection pursuit regression, multivariate adaptive regression splines, random forests and support vector regression. Apart from these models, we also propose a simple model based on the weighted demand profile resulting from our exploratory analysis of the data. In our comparative study, all predictive models were evaluated using an experimental methodology for hourly time series data that detailed water demand in a hydraulic sector of a water supply network in a city in south-eastern Spain. The accuracy of the obtained results, together with the medium size of the demand area, suggests that this was a suitable environment for making adequate management decisions. [Copyright &y& Elsevier]

Abstract: In this paper, a new forecast strategy is proposed for day-ahead prediction of electricity prices, which are so valuable for both producers and consumers in the new competitive electric power markets. However, electricity price has a nonlinear, volatile and time dependent behavior owning many outliers. Our forecast strategy is composed of a preprocessor and a Hybrid Neuro-Evolutionary System (HNES). Preprocessor selects the input features of the HNES according to MRMR (Maximum Relevance Minimum Redundancy) principal. The HNES is composed of three Neural Networks (NN) and Evolutionary Algorithms (EA) in a cascaded structure with a new data flow among its building blocks. The effectiveness of the whole proposed method is demonstrated by means of real data of the PJM and Spanish electricity markets. Also, the proposed price forecast strategy is compared with some of the most recent techniques in the area. [Copyright &y& Elsevier]

This paper investigates the possibility of improving the predictive ability of a tourism demand model with meteorological explanatory variables. The authors use as a case study the monthly British tourism demand for the Balearic Islands (Spain). For this purpose, a transfer function model and causal artificial neural network are fitted. The results are compared with those obtained by non-causal methods: an ARIMA model and an autoregressive neural network. The results indicate that incorporating meteorological variables can increase predictive power, although the most accurate prediction is obtained using a non-causal model - specifically, an autoregressive neural network. [ABSTRACT FROM AUTHOR]

Abstract: In new deregulated electricity market, price forecasts have become a fundamental input to an energy company’s decision making and strategy development process. However, the exclusive characteristics of electricity price such as non-stationarity, non-linearity and time-varying volatile structure present a number of challenges for this task. In spite of all performed research on this area in the recent years, there is still essential need for more accurate and robust price forecast methods. Besides, there is a lack of efficient feature selection technique for designing the input vector of electricity price forecast. In this paper, a new two-stage feature selection algorithm composed of modified relief and mutual information (MI) techniques is proposed for this purpose. Moreover, cascaded neural network (CNN) is presented as forecast engine for electricity price prediction. The CNN is composed of cascaded forecasters where each forecaster is a neural network (NN). The proposed feature selection algorithm selects the best set of candidate inputs which is used by the CNN. The proposed method is examined on PJM, Spanish and Ontario electricity markets and compared with some of the most recent price forecast techniques. [Copyright &y& Elsevier]

Abstract: This paper presents the hybridization of the fifth generation mesoscale model (MM5) with neural networks in order to tackle a problem of short-term wind speed prediction. The mean hourly wind speed forecast at wind turbines in a wind park is an important parameter used to predict the total power production of the park. Our model for short-term wind speed forecast integrates a global numerical weather prediction model and observations at different heights (using atmospheric soundings) as initial and boundary conditions for the MM5 model. Then, the outputs of this model are processed using a neural network to obtain the wind speed forecast in specific points of the wind park. In the experiments carried out, we present some results of wind speed forecasting in a wind park located at the south-east of Spain. The results are encouraging, and show that our hybrid MM5-neural network approach is able to obtain good short-term predictions of wind speed at specific points. [Copyright &y& Elsevier]

Abstract: In this work an application of a methodology to obtain solar radiation maps is presented. This methodology is based on a neural network system [Lippmann, R.P., 1987. An introduction to computing with neural nets. IEEE ASSP Magazine, 4–22] called Multi-Layer Perceptron (MLP) [Haykin, S., 1994. Neural Networks. A Comprehensive Foundation. Macmillan Publishing Company; Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366]. To obtain a solar radiation map it is necessary to know the solar radiation of many points spread wide across the zone of the map where it is going to be drawn. For most of the locations all over the world the records of these data (solar radiation in whatever scale, daily or hourly values) are non-existent. Only very few locations have the privilege of having good meteorological stations where records of solar radiation have being registered. But even in those locations with historical records of solar data, the quality of these solar series is not as good as it should be for most purposes. In addition, to draw solar radiation maps the number of points on the maps (real sites) that it is necessary to work with makes this problem difficult to solve. Nevertheless, with the application of the methodology proposed in this paper, this problem has been solved and solar radiation maps have been obtained for a small region of Spain: Jaén province, a southern province of Spain between parallels 38°25′ N and 37°25′ N, and meridians 4°10′ W and 2°10′ W, and for a larger region: Andalucía, the most southern region of Spain situated between parallels 38°40′ N and 36°00′ N, and meridians 7°30′ W and 1°40′ W. [Copyright &y& Elsevier]

Abstract: Several methods for sizing stand alone photovoltaic (pv) systems has been developed. The more simplistic are called intuitive methods. They are a useful tool for a first approach in sizing stand alone photovoltaic systems. Nevertheless they are very inaccurate. Analytical methods use equations to describe the pv system size as a function of reliability. These ones are more accurate than the previous ones but they are also not accurate enough for sizing of high reliability. In a third group there are methods which use system simulations. These ones are called numerical methods. Many of the analytical methods employ the concept of reliability of the system or the complementary term: loss of load probability (LOLP). In this paper an improvement for obtaining LOLP curves based on the neural network called Multilayer Perceptron (MLP) is presented. A unique MLP for many locations of Spain has been trained and after the training, the MLP is able to generate LOLP curves for any value and location. [Copyright &y& Elsevier]

The origin–destination (OD) demand matrix plays an essential role in travel modeling and transport planning. Traditional OD matrices are estimated from expensive and laborious traffic counts and surveys. Accordingly, this study proposes a new combined methodology to estimate or update OD matrices (urban mobility) directly from easy-to-obtain and free-of-charge socioeconomic variables. The Málaga region, Spain, was used as a case study. The proposed methodology involves two stages. First, an automatic feature selection procedure was developed to determine the most relevant socioeconomic variables, discarding the irrelevant ones. Several feature selection techniques were studied and combined. Second, machine learning (ML) models were used to estimate mobility between predefined zones. Artificial neural networks (ANNs) and support vector regression (SVR) were tested and compared using the most relevant variables as inputs. The experimental results show that the proposed combined model can be more accurate than traditional methods and ML models without the feature selection procedure. In particular, SVR with feature selection slightly outperformed the combined model using ANNs. The proposed methodology can be a promising and affordable alternative method for estimating OD matrices, reducing costs and lead time significantly, and assisting and improving urban transport planning. [ABSTRACT FROM AUTHOR]

This study presents a comparison between sixteen filter ranking methods applied to a real air pollution problem. Adaptations of the Minimum-Redundancy-Maximum-Relevance (mRMR) algorithm to use the Spearman's rank correlation, the kernel canonical correlation analysis, the Hilbert–Schmidt independence criterion, correntropy, the Pearson's correlation and the distance correlation are included among them. These methods were compared by estimating the hourly NO2 concentrations at three monitoring stations located in the Bay of Algeciras (Spain). The estimation models were generated using Bayesian regularized artificial neural networks. Different estimation cases were tested for each ranking method. Finally, results were statistically compared to determine which filter ranking strategy produced the best performing model in each case. The proposed estimation scenarios showed how mRMR methods had better results than all the remaining methods when a small number of features was selected. However, their advantage was not so evident when the number of selected features increased. Results from the proposed mRMR methods were promising, especially in the case of the distance correlation mRMR, the kernel canonical correlation analysis mRMR and the Spearman's rank correlation mRMR. These ranking methods performed better than the original mRMR algorithm that employs mutual information internally. [ABSTRACT FROM AUTHOR]

Hydrological models are widely used tools in water resources management. Their successful application requires an efficient calibration of the model parameters. Nowadays, there are very powerful global search methods applied to this end, but they have the disadvantage of presenting a high computational cost, because the numerical model to be calibrated needs to be evaluated a large number of times with different parameter sets. In this context, surrogate models can reduce significantly the run time of hydrological models, easing the total computational burden of global search methods. In the present work, we propose and explore the combination of a swarm intelligence-based optimization method, the artificial bee colony algorithm, with a surrogate model based on artificial neural networks in order to calibrate hydrological models. The proposed approach (ABC-ANN) is applied to the calibration and validation of a nine-parameter continuous hydrological model in two basins located in the northwest of Spain. Several aspects of the algorithm are evaluated, including its capability to calibrate the model parameters and its efficiency in terms of CPU time compared to a standard implementation of the ABC algorithm. Results show that the ABC-ANN algorithm is able to identify the location of suitable parameter sets with an accuracy rate within 89 and 99 %, and a reduction in CPU time of more than three orders of magnitude when compared to a sequential implementation. In addition, the frequency distribution of the parameter sets identified gives valuable information about the sensitivity of model output to the input parameters. [ABSTRACT FROM AUTHOR]

Time series forecasting of disaggregated freight flow is a key issue in decision-making by port authorities. For this purpose and to test new deep learning techniques we have selected seven time series of imported goods from Morocco to Spain through the port of Algeciras, and we have tested two forecasting deep neural networks models: dilated causal convolutional and encoder–decoder recurrent. We have experimented with four different granularities for each series: quarterly, monthly, weekly and daily. The results show that our neural network models can manage these raw series without first removing seasonality or trend. We also highlight the ability of neural models to work with a fixed input size of one year, being able to make good predictions using the same input size for all granularities. The two deep learning models have globally improved the benchmarks of the M4 Competition of forecasting. Each neural network model obtains its best results under different circumstances: the recurrent one with daily granularity and intermittent series, and the convolutional one with weekly and monthly granularities. [ABSTRACT FROM AUTHOR]

Air pollution in large cities produces numerous diseases and even millions of deaths annually according to the World Health Organization. Pollen exposure is related to allergic diseases, which makes its prediction a valuable tool to assess the risk level to aeroallergens. However, airborne pollen concentrations are difficult to predict due to the inherent complexity of the relationships among both biotic and environmental variables. In this work, a stochastic approach based on supervised machine learning algorithms was performed to forecast the daily Olea pollen concentrations in the Community of Madrid, central Spain, from 1993 to 2018. Firstly, individual Light Gradient Boosting Machine (LightGBM) and artificial neural network (ANN) models were applied to predict the day of the year (DOY) when the peak of the pollen season occurs, resulting the estimated average peak date 149.1 ± 9.3 and 150.1 ± 10.8 DOY for LightGBM and ANN, respectively, close to the observed value (148.8 ± 9.8). Secondly, the daily pollen concentrations during the entire pollen season have been calculated using an ensemble of two-step GAM followed by LightGBM and ANN. The results of the prediction of daily pollen concentrations showed a coefficient of determination (r2) above 0.75 (goodness of the model following cross-validation). The predictors included in the ensemble models were meteorological variables, phenological metrics, specific site-characteristics, and preceding pollen concentrations. The models are state-of-the-art in machine learning and their potential has been shown to be used and deployed to understand and to predict the pollen risk levels during the main olive pollen season. [ABSTRACT FROM AUTHOR]

Accurate wind speed prediction is critical for many tasks, especially for air pollution modelling. Data-driven approaches are particularly interesting but the stochastic nature of wind renders prediction tasks difficult. Therefore, a combination of methods could be useful to obtain better results. To overcome this difficulty, a hybrid wind speed forecasting approach is proposed in this work. The Bay of Algeciras, Spain, was used as a case study, and the database was collected from a weather monitoring station. The study consists of combining a pre-processing method, the empirical mode decomposition (EMD), an information-based method, the permutation entropy (PE), and a machine learning technique (artificial neural networks, ANNs), using an ensemble learning methodology. Different prediction horizons were considered: ph-hours (ph = 1, 2, 8, 24) ahead and 8-h and 24-h average. The introduction of PE significantly reduces the computational cost and the predictive risk in comparison with traditional EMD methodology, by reducing the number of the decomposed components to be predicted. Moreover, the experimental results demonstrated that the EMD–PE–ANN approach outperforms the prediction performance of the single ANN models in all the prediction horizons tested. The EMD–PE–ANN model is capable to achieve a correlation coefficient of 0.981 and 0.807 for short-term (1 h) and medium-term (24 h) predictions, respectively, significantly overcoming those obtained by a single ANN model (0.929 and 0.503). These results show that the proposed model reaches significant improvements when the prediction horizon increases, where forecasting models tend to worsen their prediction performance. Therefore, the proposed EMD–PE–ANN approach may become a powerful tool for wind speed forecasting. [ABSTRACT FROM AUTHOR]

• The model estimates the biomass required to produce the syngas in a BFBGP. • The proposed FF-PSO algorithm showed to solve model dynamic Power Generation systems. • The FF-PSO model proposed for the ANN-based model has the best performance. Agriculture and forestry crop residues represent more than half of the world's residual biomass; these residues turn into synthesis gas (syngas) and are used for power generation. Including Syngas Gensets into hybrid renewable microgrids for electricity generation is an interesting alternative, especially for rural communities where forest and agricultural waste are abundant. However, energy demand is not constant throughout the day. The variations in the energy demand provoke changes in both gasification plant efficiency and biomass consumption. This paper presents an Artificial Neural Network (ANN) based model hybridized with a Particle Swarm Optimization (PSO) algorithm for a Biomass Gasification Plant (BGP) that allows estimating the amount of biomass needed to produce the required syngas to meet the energy demand. The proposed model is compared with two traditional models of ANNs: Feed Forward Back Propagation (FF-BP) and Cascade Forward Propagation (CF-P). ANNs are trained in MATLAB software using a set of historical real data from a BGP located in the Distributed Energy Resources Laboratory of the Universitat Politècnica de València in Spain. The model performance is validated using the Mean Squared Error (MSE) and linear regression analysis. The results show that the proposed model performs 23.2% better in terms of MSE than de other models. The tunning parameters of the optimal PSO algorithm for this application were found. Finally, the model was validated to predict the necessary biomass and syngas to cover the energy demand. [ABSTRACT FROM AUTHOR]

Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology. [ABSTRACT FROM AUTHOR]

Purpose - The purpose of this study is to construct the first short-term financial distress prediction model for the Spanish banking sector. Design/methodology/approach - The concept of financial distress covers a range of different types of financial problems, in addition to bankruptcy, which is not common in the sector. The methodology used to predict financial problems was artificial neural networks using traditional financial variables according to the capital, assets, management, earnings, liquidity and sensibility system, as well as a series of macroeconomic variables, the impact of which has been proven in a number of studies. Findings - The results obtained show that artificial neural networks are a highly suitable method for studying financial distress in Spanish credit institutions and for predicting all cases in which an entity has short-term financial problems. Originality/value - This is the first work that tries to build a model of artificial neural networks to predict the financial distress in the Spanish banking system, grouping under the concept of financial distress, apart from bankruptcy, other financial problems that affect the viability of these entities. [ABSTRACT FROM AUTHOR]

The poor maintenance of social dwellings causes the possible building deficiencies to be significantly increased, especially when most of these dwellings have been built before any thermal standard and without considering the effect of climate change. Façades are one of the building elements which are most degraded by the contact with the exterior, and surface condensation is the most common cause. This study applies the calculation of surface condensation from ISO 13788 to a representative case of social dwelling in Spain for all climate zones, both in the current and 2050 scenarios. Risks of corrosion, mould formation, and surface condensation were studied in nine different points of the façade, which were validated by in-situ measurements. The results determined that there was a greater risk of condensation or mould depending on the climate zone, and thermal resistance significantly influenced data variation in future scenarios. The results also showed that an adequate ventilation generally decreased risks, removing the risk of mould and surface condensation by 2050. To predict the results obtained, a model based on artificial neural networks was generated, and it could also be used to estimate risks in the future. [ABSTRACT FROM AUTHOR]

Wildfires in Mediterranean regions have become a serious problem, and it is currently the main cause of forest loss. Numerous prediction methods have been applied worldwide to estimate future fire activity and area burned in order to provide a stable basis for future allocation of fire-fighting resources. The present study investigated the performance of an artificial neural network (ANN) in burned area size prediction and to assess the evolution of future wildfires and the area concerned under climate change in southern Spain. The study area comprised 39.41 km2 of land burned from 2000 to 2014. ANNs were used in two subsequential phases: classifying the size of the wildfires and predicting the burned surface for fires larger than 30,000 m2. Matrix of confusion and 10-fold cross-validations were used to evaluate ANN classification and mean absolute deviation, root mean square error, mean absolute percent error and bias, which were the metrics used for burned area prediction. The success rate achieved was above 60–70% depending on the zone. An average temperature increase of 3 °C and a 20% increase in wind speed during 2071–2100 results in a significant increase of the number of fires, up to triple the current figure, resulting in seven times the average yearly burned surface depending on the zone and the climate change scenario. [ABSTRACT FROM AUTHOR]

Fire danger models are a very useful tool for the prevention and extinction of forest fires. Some inputs of these models, such as vegetation status and temperature, can be obtained from remote sensing images, which offer higher spatial and temporal resolution than direct ground measures. In this paper, we focus on the Galicia region (north-west of Spain), and MODIS (Moderate Resolution Imaging Spectroradiometer) images are used to monitor vegetation status and to obtain land surface temperature as essential inputs in forest fire danger models. In this work, we tested the potential of artificial neural networks and logistic regression to estimate forest fire danger from remote sensing and fire history data. Remote sensing inputs used were the land surface temperature and the Enhanced Vegetation Index. A classification into three levels of fire danger was established. Fire danger maps based on this classification will facilitate fire prevention and extinction tasks. In this work, two methodologies (logistic regression and neural networks) and different combinations of input parameters (including land surface temperature (LST), vegetation indices and fire history) have been analysed for fire danger estimation. LST seems to be the best indicator of fire danger and neural networks the best methodology to apply. [ABSTRACT FROM AUTHOR]

At present time, although many theoretical formulations have been successfully proposed, there is a lack of ICT-based tools to support practical deployment of knowledge management (KM) in real settings. To bridge this gap, a hybrid artificial intelligence system is proposed in present study, aimed at gaining deeper knowledge about KM practices in four different economic sectors. By means of soft computing, companies are diagnosed according to their status regarding KM and subsequent explanations about crucial KM practices and perspectives are generated. Interesting conclusions are then derived from these explanations, allowing KM managers to optimise their decisions and obtain better results. Experimental results of real-life data from Spanish companies associated with different economic sectors validate the proposed combination of techniques. [ABSTRACT FROM AUTHOR]

The agricultural system in south-eastern Spain is based on intensive horticulture in greenhouses. Public and private organizations have spent substantial resources on optimizing irrigation, due to the scant annual precipitation (close to 250 mm). In order to preserve natural water resources, avoiding overexploitation and salinization aquifers, the water loss has to be minimized. Farmers save water in irrigation reservoirs, which are open to the atmosphere most of the time. In this work, the loss to evaporation from open water reservoirs was estimated in a typical agricultural greenhouse area in Almeria province, south-eastern Spain. The data source was both a high-resolution satellite image, and a set of climatic data from the Agro-climatic Information Network of Andalusia (AINA) and from a Class-A pan evaporimeter. The image was used for detecting and delineating open water bodies applying a supervised classification algorithm based on an artificial neural network. The climatic data were used to estimate the distribution of monthly evaporation. It was concluded that irrigation water reservoirs can evaporate 3.76% of the input water used for crops. If all of the water bodies were covered with shade materials and if the precipitation intercepted by the roofs of greenhouses were saved in the irrigation water reservoirs, 49.87% of water annually consumed by greenhouse crops could be saved. © 2016 American Institute of Chemical Engineers Environ Prog, 35: 1750-1757, 2016 [ABSTRACT FROM AUTHOR]

Alcohol prevention policies alone neither cause nor explain changes in alcohol consumption, nor in related harm. Alcohol consumption in Spain throughout the period 1962-2008 was analyzed considering selected contextual factors and alcohol policies. Increased urbanization was found to be associated with higher consumption, especially of beer. Restrictive policies regulating purchase age, advertising, and licensing premises to sell alcohol were associated with decreased alcohol consumption, while lower blood alcohol concentration limits were followed by an increase. Study limitations are noted. Changes in the evolution of socioeconomic, sociodemographic, and cultural factors should be carefully analyzed to inform alcohol policy planning and evaluation. [ABSTRACT FROM AUTHOR]

This study was carried out to evaluate sediment pollution related to trace elements such as Cd, Cu, Ni, Pb, Zn, Hg, As and Cr and eight polycyclic aromatic hydrocarbons (PAHs) in 127 sites located in 85 rivers in Spain. Sediment samples were classified according to similar chemical characteristics by means of statistical multivariate techniques (principal component analysis, PCA) and artificial neural networks such as self-organizing maps (SOM). Sediment sample classification provided by PCA was not as useful as the one provided by the SOM, revealing itself as a powerful tool to be incorporated in the first steps of sediment quality assessments. The use of sediment quality guidelines such as the mean-probable effects concentration quotient (m-PECQ) predicted sediment quality and gave an overall view of sediment pollution throughout Spain. Most of the samples (118 out of 127) showed m-PECQ values below 0.5 highlighting their relative low potential risk to cause adverse effects on the benthic fauna. However, some samples presented m-PECQ values higher than 0.5 suggesting a clear potential risk to these fauna. Besides, unusual high concentrations of trace elements and PAHs were related to the human activities carried out near each sampling point. [ABSTRACT FROM AUTHOR]

Chemical and physical-chemical parameters define water quality and are involved in water body type and habitat determination. They support a biological community of a certain ecological status. Water quality controls involve a large number of measurements of variables and observations according to the European Water Framework Directive (Directive /60/EC). In some cases, such as areas with especially critical uses or points in which potential pollution episodes are expected, the automatic monitoring is recommended. However, the chemical and physical-chemical measurements are costly and time consuming. Turbidity is shown as a key variable for the water quality control and it is also an integrative parameter. For this reason, the aim of this work is focused on this main parameter through the study of the influence of several water quality parameters on it. The artificial neural networks (ANNs) have been used in a wide range of biological problems with promising results. Bearing this in mind, turbidity values have been predicted here by using artificial neural networks (ANNs) from the remaining measured water quality parameters with success taking into account the synergistic interactions between the input variables in the Nalón river basin (Northern Spain). Finally, the main conclusions of this study are exposed. [ABSTRACT FROM AUTHOR]

Climate change is increasing temperatures and causing periods of water scarcity in arid and semi-arid climates. The agricultural sector is one of the most affected by these changes, having to optimise scarce water resources. An important phenomenon within the water cycle is the evaporation from water reservoirs, which implies a considerable amount of water lost during warmer periods of the year. Indeed, evaporation rate forecasting can help farmers grow crops more sustainably by managing water resources more efficiently in the context of precision agriculture. In this work, we expose an interpretable machine learning approach, based on a multivariate decision tree, to forecast the evaporation rate on a daily basis using data from an Internet of Things (IoT) infrastructure, which is deployed on a real irrigated plot located in Murcia (southeastern Spain). The climate data collected feed the models that provide a forecast of evaporation and a summary of the parameters involved in this process. Finally, the results of the interpretable presented model are validated with the best literature models for evaporation rate prediction, i.e., Artificial Neural Networks, obtaining results very similar to those obtained for them, reaching up to 0.85 R 2 and 0.6 M A E . Therefore, in this work, a double objective is faced: to maintain the performance obtained by the models most frequently used in the problem while maintaining the interpretability of the knowledge captured in it, which allows better understanding the problem and carrying out appropriate actions. [ABSTRACT FROM AUTHOR]

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections. [ABSTRACT FROM AUTHOR]

Academics and practitioners have not yet developed an adequate method to evaluate the social performance of organisations that includes a robust and comprehensive approach of sustainability and uses the most relevant data sources. However, sustainability rating agencies are evaluating the social performance of organisations according to their own methodologies, which are not always clearly explained to stakeholders; and the evaluations they provide are being used as a reference in markets. This study contributes to research on the evaluation of social performance in organisations, by means of an innovative methodology that combines the use of neural networks and fuzzy logic for the development of expert systems suitable for classifying organisations according to their performance on Corporate Social Responsibility. The methodology has been validated in a simplified scenario and results indicate that it is suitable for replicating the classifications provided by sustainability rating agencies. [ABSTRACT FROM PUBLISHER]

In this article, we examine whether traditional linear models are suitable to assess financial samples, because financial data usually present nonnormality or nonlinear patterns, therefore linear models do not always adequately capture them. For this reason, as returns series usually follow autoregressive patterns, nonlinear models such as Self-Exciting Threshold Autoregressive (SETAR), Logistic STAR (LSTAR), Additive Autoregressive (AAR) or Neural Network (NNET) could provide a good fit. We study whether two samples of pension funds' returns in Spain and the United Kingdom present these features, and we find that the most appropriate model for the Spanish sample is an autoregressive model, but in the United Kingdom sample, we fit a neural network. [ABSTRACT FROM PUBLISHER]

Based on a feed-forward and error-back-propagated neural network (NN), a new bio-optical algorithm is developed for the Bay of Biscay. It is designed as a set of NNs individually dedicated to the retrieval of the phytoplankton chlorophyll (chl), and total suspended matter (tsm) from Sea-viewing Wide Field-of-View Sensor (SeaWiFS) and Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua data. The retrieved versus in situ measured concentrations of chl and tsm correlation coefficients for chl proved to be ∼0.8 (SeaWiFS) and 0.72 (MODIS), and for tsm 0.71 (SeaWiFS) and 0.74 (MODIS). The developed NN-based bio-optical algorithms are employed to assess the compatibility of SeaWiFS and MODIS data on chl and tsm in the coastal zone of the Bay of Biscay (case 2 waters). The value of the ratio between the concentration of chl and tsm derived from the same-day SeaWiFS and MODIS data (the overflight time difference, Δt is ≤2.5 hours) has in most cases values of approximately 1, however, in specific cases it varies appreciably. These results indicate that, unlike the reportedly very successful cases of merging of SeaWiFS and MODIS data on chl in open ocean waters (case 1 waters), the merging of chl (and tsm) data from these sensors collected over case 2 waters needs to be supervised at a level of a few pixels. At the same time, when averaged over the entire coastal zone of the Bay of Biscay, the retrieved monthly mean chl and tsm concentrations from SeaWiFS and MODIS practically coincide throughout the years (2002-2004) of contemporaneous operation of these two satellite sensors. Thus, even in the case of such dynamic and optically complex case 2 waters that are inherent in the Bay of Biscay, the potentials for ocean colour data merging are very good. The merging efficiency is assessed and illustrated via documenting the spatio-temporal dynamics of bottom sediment re-suspension in the bay occurring in winter - the season of heaviest cloudiness over the bay. [ABSTRACT FROM AUTHOR]

The ‘Campo de Gibraltar’ region is a very industrialized area where very few air pollution studies have been carried out. Up to date, no model has been developed in order to predict air pollutant levels in the different towns spread in the region. Carbon monoxide (CO), Sulphur dioxide (SO2) and suspended particulate matter (SPM) series have been investigated (years 1999–2000–2001). Multilayer perceptron models (MLPs) with backpropagation learning rule have been used. A resampling strategy with two-fold crossvalidation allowed the statistical comparison of the different models considered in this study. Artificial neural networks (ANN) models were compared with Persistence and ARIMA models and also with models based on standard Multiple Linear Regression (MLR) over test sets with data that had not been used in the training stage. The models based on ANNs showed better capability of generalization than those based on MLR. The designed procedure of random resampling permits an adequate and robust multiple comparison of the tested models. Principal component analysis (PCA) is used to reduce the dimensionality of data and to transform exogenous variables into significant and independent components. Short-term predictions were better than medium-term predictions in the case of CO and SO2 series. Conversely, medium-term predictions were better in the case of SPM concentrations. The predictions are significantly promising (e.g., d SPM 24-ahead = 0.906, d CO 1-ahead = 0.891, d SO2 1-ahead = 0.851). [ABSTRACT FROM AUTHOR]

This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model's performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases. [ABSTRACT FROM AUTHOR]

The present work aims to assess the usefulness of five vegetation indices (VI) derived from multispectral UAS imagery to capture the effects of deficit irrigation on the canopy structure of sweet cherry trees (Prunus avium L.) in southeastern Spain. Three irrigation treatments were assayed, a control treatment and two regulated deficit irrigation treatments. Four airborne flights were carried out during two consecutive seasons; to compare the results of the remote sensing VI, the conventional and continuous water status indicators commonly used to manage sweet cherry tree irrigation were measured, including midday stem water potential (Ψs) and maximum daily shrinkage (MDS). Simple regression between individual VIs and Ψs or MDS found stronger relationships in postharvest than in preharvest. Thus, the normalized difference vegetation index (NDVI), resulted in the strongest relationship with Ψs (r2 = 0.67) and MDS (r2 = 0.45), followed by the normalized difference red edge (NDRE). The sensitivity analysis identified the optimal soil adjusted vegetation index (OSAVI) as the VI with the highest coefficient of variation in postharvest and the difference vegetation index (DVI) in preharvest. A new index is proposed, the transformed red range vegetation index (TRRVI), which was the only VI able to statistically identify a slight water deficit applied in preharvest. The combination of the VIs studied was used in two machine learning models, decision tree and artificial neural networks, to estimate the extra labor needed for harvesting and the sweet cherry yield. [ABSTRACT FROM AUTHOR]

Plantations of fast-growing Eucalyptus trees have become a common sight in the western Iberian peninsula where they are planted to exploit their economic potential. Negative side-effects of large scale plantations including the invasive behavior of Eucalyptus trees outside of regular plantations have become apparent. This study uses medium resolution, multi-spectral imagery of the Sentinel 2 satellites to map Eucalyptus across Portugal and parts of Spain with a focus on Natura 2000 areas inside Portugal, that are protected under the European birds and habitats directives. This method enables the detection of small incipient as well as mixed populations outside of regular plantations. Ground truth maps were compiled using field surveys as well as high resolution satellite imagery and were used to train Feedforward Neural Networks. These models predict Eucalyptus tree cover with a sensitivity of up to 75.7% as well as a specificity of up to 95.8%. The overall accuracy of the prediction is 92.5%. A qualitative assessment of Natura 2000 areas in Portugal has been performed and 15 areas have been found to be affected by Eucalyptus of which 9 are strongly affected. This study demonstrates the applicability of multi-spectral imagery for tree-species classification and invasive species control. It provides a probability-map of Eucalyptus tree cover for the western Iberian peninsula with 10 m spatial resolution and shows the need for monitoring of Eucalyptus in protected areas. [ABSTRACT FROM AUTHOR]

The goal of the present research is to contribute to the detection of tax fraud concerning personal income tax returns (IRPF, in Spanish) filed in Spain, through the use of Machine Learning advanced predictive tools, by applying Multilayer Perceptron neural network (MLP) models. The possibilities springing from these techniques have been applied to a broad range of personal income return data supplied by the Institute of Fiscal Studies (IEF). The use of the neural networks enabled taxpayer segmentation as well as calculation of the probability concerning an individual taxpayer's propensity to attempt to evade taxes. The results showed that the selected model has an efficiency rate of 84.3%, implying an improvement in relation to other models utilized in tax fraud detection. The proposal can be generalized to quantify an individual's propensity to commit fraud with regards to other kinds of taxes. These models will support tax offices to help them arrive at the best decisions regarding action plans to combat tax fraud. [ABSTRACT FROM AUTHOR]