Aplicação de redes neurais artificiais na análise de dados de molhamento foliar por orvalho

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Aplicação de redes neurais no controle de teores de cobre e ouro do depósito de Chapada (GO)

Pós-graduação em Geologia Regional - IGCE

Capacidad de obtener beneficio de reglas técnicas de contratación basadas en algoritmos de minería de datos

Trabajo Fin de Grado de la doble titulación de Grado en Ingeniería Informática y Grado en Administración y Dirección de Empresas.

Estimating Annual CO2 Flux for Lutjewad Station Using Three Different Gap-Filling Techniques

Long-term measurements of CO2 flux can be obtained using the eddy covariance technique, but these datasets are affected by gaps which hinder the estimation of robust long-term means and annual ecosystem exchanges. We compare results obtained using three gap-fill techniques: multiple regression (MR), multiple imputation (MI), and artificial neural networks (ANNs), applied to a one-year dataset of hourly CO2 flux measurements collected in Lutjewad, over a flat agriculture area near the Wadden Sea dike in the north of the Netherlands. The dataset was separated in two subsets: a learning and a validation set. The performances of gap-filling techniques were analysed by calculating statistical criteria: coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), maximum absolute error (MaxAE), and mean square bias (MSB). The gap-fill accuracy is seasonally dependent, with better results in cold seasons. The highest accuracy is obtained using ANN technique which is also less sensitive to environmental/seasonal conditions. We argue that filling gaps directly on measured CO2 fluxes is more advantageous than the common method of filling gaps on calculated net ecosystem change, because ANN is an empirical method and smaller scatter is expected when gap filling is applied directly to measurements.

Statistical models for short-term wind power ramp forecasting

La predicción de energía eólica ha desempeñado en la última década un papel fundamental en el aprovechamiento de este recurso renovable, ya que permite reducir el impacto que tiene la naturaleza fluctuante del viento en la actividad de diversos agentes implicados en su integración, tales como el operador del sistema o los agentes del mercado eléctrico. Los altos niveles de penetración eólica alcanzados recientemente por algunos países han puesto de manifiesto la necesidad de mejorar las predicciones durante eventos en los que se experimenta una variación importante de la potencia generada por un parque o un conjunto de ellos en un tiempo relativamente corto (del orden de unas pocas horas). Estos eventos, conocidos como rampas, no tienen una única causa, ya que pueden estar motivados por procesos meteorológicos que se dan en muy diferentes escalas espacio-temporales, desde el paso de grandes frentes en la macroescala a procesos convectivos locales como tormentas. Además, el propio proceso de conversión del viento en energía eléctrica juega un papel relevante en la ocurrencia de rampas debido, entre otros factores, a la relación no lineal que impone la curva de potencia del aerogenerador, la desalineación de la máquina con respecto al viento y la interacción aerodinámica entre aerogeneradores. En este trabajo se aborda la aplicación de modelos estadísticos a la predicción de rampas a muy corto plazo. Además, se investiga la relación de este tipo de eventos con procesos atmosféricos en la macroescala. Los modelos se emplean para generar predicciones de punto a partir del modelado estocástico de una serie temporal de potencia generada por un parque eólico. Los horizontes de predicción considerados van de una a seis horas. Como primer paso, se ha elaborado una metodología para caracterizar rampas en series temporales. La denominada función-rampa está basada en la transformada wavelet y proporciona un índice en cada paso temporal. Este índice caracteriza la intensidad de rampa en base a los gradientes de potencia experimentados en un rango determinado de escalas temporales. Se han implementado tres tipos de modelos predictivos de cara a evaluar el papel que juega la complejidad de un modelo en su desempeño: modelos lineales autorregresivos (AR), modelos de coeficientes variables (VCMs) y modelos basado en redes neuronales (ANNs). Los modelos se han entrenado en base a la minimización del error cuadrático medio y la configuración de cada uno de ellos se ha determinado mediante validación cruzada. De cara a analizar la contribución del estado macroescalar de la atmósfera en la predicción de rampas, se ha propuesto una metodología que permite extraer, a partir de las salidas de modelos meteorológicos, información relevante para explicar la ocurrencia de estos eventos. La metodología se basa en el análisis de componentes principales (PCA) para la síntesis de la datos de la atmósfera y en el uso de la información mutua (MI) para estimar la dependencia no lineal entre dos señales. Esta metodología se ha aplicado a datos de reanálisis generados con un modelo de circulación general (GCM) de cara a generar variables exógenas que posteriormente se han introducido en los modelos predictivos. Los casos de estudio considerados corresponden a dos parques eólicos ubicados en España. Los resultados muestran que el modelado de la serie de potencias permitió una mejora notable con respecto al modelo predictivo de referencia (la persistencia) y que al añadir información de la macroescala se obtuvieron mejoras adicionales del mismo orden. Estas mejoras resultaron mayores para el caso de rampas de bajada. Los resultados también indican distintos grados de conexión entre la macroescala y la ocurrencia de rampas en los dos parques considerados. Abstract One of the main drawbacks of wind energy is that it exhibits intermittent generation greatly depending on environmental conditions. Wind power forecasting has proven to be an effective tool for facilitating wind power integration from both the technical and the economical perspective. Indeed, system operators and energy traders benefit from the use of forecasting techniques, because the reduction of the inherent uncertainty of wind power allows them the adoption of optimal decisions. Wind power integration imposes new challenges as higher wind penetration levels are attained. Wind power ramp forecasting is an example of such a recent topic of interest. The term ramp makes reference to a large and rapid variation (1-4 hours) observed in the wind power output of a wind farm or portfolio. Ramp events can be motivated by a broad number of meteorological processes that occur at different time/spatial scales, from the passage of large-scale frontal systems to local processes such as thunderstorms and thermally-driven flows. Ramp events may also be conditioned by features related to the wind-to-power conversion process, such as yaw misalignment, the wind turbine shut-down and the aerodynamic interaction between wind turbines of a wind farm (wake effect). This work is devoted to wind power ramp forecasting, with special focus on the connection between the global scale and ramp events observed at the wind farm level. The framework of this study is the point-forecasting approach. Time series based models were implemented for very short-term prediction, this being characterised by prediction horizons up to six hours ahead. As a first step, a methodology to characterise ramps within a wind power time series was proposed. The so-called ramp function is based on the wavelet transform and it provides a continuous index related to the ramp intensity at each time step. The underlying idea is that ramps are characterised by high power output gradients evaluated under different time scales. A number of state-of-the-art time series based models were considered, namely linear autoregressive (AR) models, varying-coefficient models (VCMs) and artificial neural networks (ANNs). This allowed us to gain insights into how the complexity of the model contributes to the accuracy of the wind power time series modelling. The models were trained in base of a mean squared error criterion and the final set-up of each model was determined through cross-validation techniques. In order to investigate the contribution of the global scale into wind power ramp forecasting, a methodological proposal to identify features in atmospheric raw data that are relevant for explaining wind power ramp events was presented. The proposed methodology is based on two techniques: principal component analysis (PCA) for atmospheric data compression and mutual information (MI) for assessing non-linear dependence between variables. The methodology was applied to reanalysis data generated with a general circulation model (GCM). This allowed for the elaboration of explanatory variables meaningful for ramp forecasting that were utilized as exogenous variables by the forecasting models. The study covered two wind farms located in Spain. All the models outperformed the reference model (the persistence) during both ramp and non-ramp situations. Adding atmospheric information had a noticeable impact on the forecasting performance, specially during ramp-down events. Results also suggested different levels of connection between the ramp occurrence at the wind farm level and the global scale.

Estimación de la resistencia de estructuras de hormigón armado reforzadas a cortante mediante FRP

El empleo de refuerzos de FRP en vigas de hormigón armado es cada vez más frecuente por sus numerosas ventajas frente a otros métodos más tradicionales. Durante los últimos años, la técnica FRP-NSM, consistente en introducir barras de FRP sobre el recubrimiento de una viga de hormigón, se ha posicionado como uno de los mejores métodos de refuerzo y rehabilitación de estructuras de hormigón armado, tanto por su facilidad de montaje y mantenimiento, como por su rendimiento para aumentar la capacidad resistente de dichas estructuras. Si bien el refuerzo a flexión ha sido ampliamente desarrollado y estudiado hasta la fecha, no sucede lo mismo con el refuerzo a cortante, debido principalmente a su gran complejidad. Sin embargo, se debería dedicar más estudio a este tipo de refuerzo si se pretenden conservar los criterios de diseño en estructuras de hormigón armado, los cuales están basados en evitar el fallo a cortante por sus consecuencias catastróficas Esta ausencia de información y de normativa es la que justifica esta tesis doctoral. En este pro-yecto se van a desarrollar dos metodologías alternativas, que permiten estimar la capacidad resistente de vigas de hormigón armado, reforzadas a cortante mediante la técnica FRP-NSM. El primer método aplicado consiste en la implementación de una red neuronal artificial capaz de predecir adecuadamente la resistencia a cortante de vigas reforzadas con este método a partir de experimentos anteriores. Asimismo, a partir de la red se han llevado a cabo algunos estudios a fin de comprender mejor la influencia real de algunos parámetros de la viga y del refuerzo sobre la resistencia a cortante con el propósito de lograr diseños más seguros de este tipo de refuerzo. Una configuración óptima de la red requiere discriminar adecuadamente de entre los numerosos parámetros (geométricos y de material) que pueden influir en el compor-tamiento resistente de la viga, para lo cual se han llevado a cabo diversos estudios y pruebas. Mediante el segundo método, se desarrolla una ecuación de proyecto que permite, de forma sencilla, estimar la capacidad de vigas reforzadas a cortante con FRP-NSM, la cual podría ser propuesta para las principales guías de diseño. Para alcanzar este objetivo, se plantea un pro-blema de optimización multiobjetivo a partir de resultados de ensayos experimentales llevados a cabo sobre vigas de hormigón armado con y sin refuerzo de FRP. El problema multiobjetivo se resuelve mediante algoritmos genéticos, en concreto el algoritmo NSGA-II, por ser más apropiado para problemas con varias funciones objetivo que los métodos de optimización clásicos. Mediante una comparativa de las predicciones realizadas con ambos métodos y de los resulta-dos de ensayos experimentales se podrán establecer las ventajas e inconvenientes derivadas de la aplicación de cada una de las dos metodologías. Asimismo, se llevará a cabo un análisis paramétrico con ambos enfoques a fin de intentar determinar la sensibilidad de aquellos pa-rámetros más sensibles a este tipo de refuerzo. Finalmente, se realizará un análisis estadístico de la fiabilidad de las ecuaciones de diseño deri-vadas de la optimización multiobjetivo. Con dicho análisis se puede estimar la capacidad resis-tente de una viga reforzada a cortante con FRP-NSM dentro de un margen de seguridad espe-cificado a priori. ABSTRACT The use of externally bonded (EB) fibre-reinforced polymer (FRP) composites has gained acceptance during the last two decades in the construction engineering community, particularly in the rehabilitation of reinforced concrete (RC) structures. Currently, to increase the shear resistance of RC beams, FRP sheets are externally bonded (EB-FRP) and applied on the external side surface of the beams to be strengthened with different configurations. Of more recent application, the near-surface mounted FRP bar (NSM-FRP) method is another technique successfully used to increase the shear resistance of RC beams. In the NSM method, FRP rods are embedded into grooves intentionally prepared in the concrete cover of the side faces of RC beams. While flexural strengthening has been widely developed and studied so far, the same doesn´t occur to shearing strength mainly due to its great complexity. Nevertheless, if design criteria are to be preserved more research should be done to this sort of strength, which are based on avoiding shear failure and its catastrophic consequences. However, in spite of this, accurately calculating the shear capacity of FRP shear strengthened RC beams remains a complex challenge that has not yet been fully resolved due to the numerous variables involved in the procedure. The objective of this Thesis is to develop methodologies to evaluate the capacity of FRP shear strengthened RC beams by dealing with the problem from a different point of view to the numerical modeling approach by using artificial intelligence techniques. With this purpose two different approaches have been developed: one concerned with the use of artificial neural networks and the other based on the implementation of an optimization approach developed jointly with the use of artificial neural networks (ANNs) and solved with genetic algorithms (GAs). With these approaches some of the difficulties concerned regarding the numerical modeling can be overcome. As an alternative tool to conventional numerical techniques, neural networks do not provide closed form solutions for modeling problems but do, however, offer a complex and accurate solution based on a representative set of historical examples of the relationship. Furthermore, they can adapt solutions over time to include new data. On the other hand, as a second proposal, an optimization approach has also been developed to implement simple yet accurate shear design equations for this kind of strengthening. This approach is developed in a multi-objective framework by considering experimental results of RC beams with and without NSM-FRP. Furthermore, the results obtained with the previous scheme based on ANNs are also used as a filter to choose the parameters to include in the design equations. Genetic algorithms are used to solve the optimization problem since they are especially suitable for solving multi-objective problems when compared to standard optimization methods. The key features of the two proposed procedures are outlined and their performance in predicting the capacity of NSM-FRP shear strengthened RC beams is evaluated by comparison with results from experimental tests and with predictions obtained using a simplified numerical model. A sensitivity study of the predictions of both models for the input parameters is also carried out.

Using non-parametric search algorithms to forecast daily excess stock returns

Are the learning procedures of genetic algorithms (GAs) able to generate optimal architectures for artificial neural networks (ANNs) in high frequency data? In this experimental study,GAs are used to identify the best architecture for ANNs. Additional learning is undertaken by the ANNs to forecast daily excess stock returns. No ANN architectures were able to outperform a random walk,despite the finding of non-linearity in the excess returns. This failure is attributed to the absence of suitable ANN structures and further implies that researchers need to be cautious when making inferences from ANN results that use high frequency data.

Short-term wind power forecasting using Gaussian processes

Since wind has an intrinsically complex and stochastic nature, accurate wind power forecasts are necessary for the safety and economics of wind energy utilization. In this paper, we investigate a combination of numeric and probabilistic models: one-day-ahead wind power forecasts were made with Gaussian Processes (GPs) applied to the outputs of a Numerical Weather Prediction (NWP) model. Firstly the wind speed data from NWP was corrected by a GP. Then, as there is always a defined limit on power generated in a wind turbine due the turbine controlling strategy, a Censored GP was used to model the relationship between the corrected wind speed and power output. To validate the proposed approach, two real world datasets were used for model construction and testing. The simulation results were compared with the persistence method and Artificial Neural Networks (ANNs); the proposed model achieves about 11% improvement in forecasting accuracy (Mean Absolute Error) compared to the ANN model on one dataset, and nearly 5% improvement on another.

Soft computing based parameter identification in pavements and geomechanical systems

Accurate estimation of road pavement geometry and layer material properties through the use of proper nondestructive testing and sensor technologies is essential for evaluating pavement’s structural condition and determining options for maintenance and rehabilitation. For these purposes, pavement deflection basins produced by the nondestructive Falling Weight Deflectometer (FWD) test data are commonly used. The nondestructive FWD test drops weights on the pavement to simulate traffic loads and measures the created pavement deflection basins. Backcalculation of pavement geometry and layer properties using FWD deflections is a difficult inverse problem, and the solution with conventional mathematical methods is often challenging due to the ill-posed nature of the problem. In this dissertation, a hybrid algorithm was developed to seek robust and fast solutions to this inverse problem. The algorithm is based on soft computing techniques, mainly Artificial Neural Networks (ANNs) and Genetic Algorithms (GAs) as well as the use of numerical analysis techniques to properly simulate the geomechanical system. A widely used pavement layered analysis program ILLI-PAVE was employed in the analyses of flexible pavements of various pavement types; including full-depth asphalt and conventional flexible pavements, were built on either lime stabilized soils or untreated subgrade. Nonlinear properties of the subgrade soil and the base course aggregate as transportation geomaterials were also considered. A computer program, Soft Computing Based System Identifier or SOFTSYS, was developed. In SOFTSYS, ANNs were used as surrogate models to provide faster solutions of the nonlinear finite element program ILLI-PAVE. The deflections obtained from FWD tests in the field were matched with the predictions obtained from the numerical simulations to develop SOFTSYS models. The solution to the inverse problem for multi-layered pavements is computationally hard to achieve and is often not feasible due to field variability and quality of the collected data. The primary difficulty in the analysis arises from the substantial increase in the degree of non-uniqueness of the mapping from the pavement layer parameters to the FWD deflections. The insensitivity of some layer properties lowered SOFTSYS model performances. Still, SOFTSYS models were shown to work effectively with the synthetic data obtained from ILLI-PAVE finite element solutions. In general, SOFTSYS solutions very closely matched the ILLI-PAVE mechanistic pavement analysis results. For SOFTSYS validation, field collected FWD data were successfully used to predict pavement layer thicknesses and layer moduli of in-service flexible pavements. Some of the very promising SOFTSYS results indicated average absolute errors on the order of 2%, 7%, and 4% for the Hot Mix Asphalt (HMA) thickness estimation of full-depth asphalt pavements, full-depth pavements on lime stabilized soils and conventional flexible pavements, respectively. The field validations of SOFTSYS data also produced meaningful results. The thickness data obtained from Ground Penetrating Radar testing matched reasonably well with predictions from SOFTSYS models. The differences observed in the HMA and lime stabilized soil layer thicknesses observed were attributed to deflection data variability from FWD tests. The backcalculated asphalt concrete layer thickness results matched better in the case of full-depth asphalt flexible pavements built on lime stabilized soils compared to conventional flexible pavements. Overall, SOFTSYS was capable of producing reliable thickness estimates despite the variability of field constructed asphalt layer thicknesses.

Detecção e classificação de curto-circuitos em sistemas de distribuição usando rede neural artificial ARTMAP nebulosa

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Threat analysis of IoT networks using artificial neural network intrusion detection system

The Internet of things (IoT) is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However, as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using internet packet traces, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison

PURPOSE: The main goal of this study was to develop and compare two different techniques for classification of specific types of corneal shapes when Zernike coefficients are used as inputs. A feed-forward artificial Neural Network (NN) and discriminant analysis (DA) techniques were used. METHODS: The inputs both for the NN and DA were the first 15 standard Zernike coefficients for 80 previously classified corneal elevation data files from an Eyesys System 2000 Videokeratograph (VK), installed at the Departamento de Oftalmologia of the Escola Paulista de Medicina, São Paulo. The NN had 5 output neurons which were associated with 5 typical corneal shapes: keratoconus, with-the-rule astigmatism, against-the-rule astigmatism, "regular" or "normal" shape and post-PRK. RESULTS: The NN and DA responses were statistically analyzed in terms of precision ([true positive+true negative]/total number of cases). Mean overall results for all cases for the NN and DA techniques were, respectively, 94% and 84.8%. CONCLUSION: Although we used a relatively small database, results obtained in the present study indicate that Zernike polynomials as descriptors of corneal shape may be a reliable parameter as input data for diagnostic automation of VK maps, using either NN or DA.

Context-free and context-sensitive dynamics in recurrent neural networks

Continuous-valued recurrent neural networks can learn mechanisms for processing context-free languages. The dynamics of such networks is usually based on damped oscillation around fixed points in state space and requires that the dynamical components are arranged in certain ways. It is shown that qualitatively similar dynamics with similar constraints hold for a(n)b(n)c(n), a context-sensitive language. The additional difficulty with a(n)b(n)c(n), compared with the context-free language a(n)b(n), consists of 'counting up' and 'counting down' letters simultaneously. The network solution is to oscillate in two principal dimensions, one for counting up and one for counting down. This study focuses on the dynamics employed by the sequential cascaded network, in contrast to the simple recurrent network, and the use of backpropagation through time. Found solutions generalize well beyond training data, however, learning is not reliable. The contribution of this study lies in demonstrating how the dynamics in recurrent neural networks that process context-free languages can also be employed in processing some context-sensitive languages (traditionally thought of as requiring additional computation resources). This continuity of mechanism between language classes contributes to our understanding of neural networks in modelling language learning and processing.