Generation of electric energy through wind turbines is one the practically inexhaustible alternatives generation. It considered a source clean energy, but still needs lot research for development science and technologies that ensures uniformity in generation, providing greater participation this matrix, since presents abrupt variations speed, density other important variables. In wind-based electrical systems, it essential to predict at least day advance future values behavior, order...

The detection of T-wave end points on electrocardiogram (ECG) is a basic procedure for ECG processing and analysis. Several methods have been proposed tested, featuring high accuracy percentages correct detection. Nevertheless, their performance in noisy conditions remains an open problem.A new approach algorithm location based the computation Trapezium's areas validated (in terms repeatability), using signals from Physionet QT Database. has tested compared with one most used approaches...

This paper proposes a hybrid approach based on seasonal autoregressive integrated moving average (SARIMA) and neural networks for multi-step ahead wind speed forecasting using explanatory variables. In the proposed model, variables are first predicted, is performed taking into account these forecasted values historical series. The achieved recursively, by value as input to obtain next value. tested records of meteorological data collected from two real-world locations in Brazil. order...

This paper proposes a process for human resource performance evaluation using computational intelligence techniques. The (or employee's) is essentially regular assessment and review of an employee's on the job. can be performed in different ways, depending kind job employee company's politics or business area. proposed this research combines Fuzzy logic, text sentiment analysis supervised learning classification techniques, such as multi layer perceptron artificial neural network, decision...

Economic-emission load dispatch uses the fuel cost variables and gas emission in a minimized way to obtain an optimal operation generation units power plant, guaranteeing supply of demand. The first variable is definitive ensure business continuity second comply with environmental legislation no degradation environment. This paper analyzes use new computational optimization algorithm based on cultural (CA), improved local search techniques simulated annealing Tabu search, using data from...

Global environmental impacts such as climate change require behavior from society that aims to minimize greenhouse gas emissions. This includes the substitution of fossil fuels with other energy sources. An important aspect efficient and sustainable management electricity supply in Brazil is prediction some variables national electric system (NES), price differences settlement (PLD) wind speed for energy. In this context, present study investigated two distinct forecasting approaches. The...

This work presents the use of wavelet transform and computational intelligence techniques to quantify voltage short-duration variation in electric power systems, with respect time duration magnitude. The is used determine event duration, as well for obtaining a characteristic curve relating signal norm function number cycles waveform without disturbance that reference calculation magnitude event. A Generalized Regression Neural Network (GRNN) interpolate not stored points curve. method part...

There is a general consensus that electricity price forecasting an important task nowadays since power market players are interested in the maximization of profit and minimization risk. In this context, paper proposes use data-mining techniques to predict short-term Brazilian market. Brazil, model adopted has unique characteristics with centralized form dispatch due predominance hydro generation. To apply proposed prediction model, all features considered, such as transmission restrictions...

Primary aluminum production is an uninterrupted and complex process that must operate in a closed loop, hindering possibilities for experiments to improve production. In this sense, it important have ways simulate computationally without acting directly on the plant, since such direct intervention could be dangerous, expensive, time-consuming. This problem addressed paper by combining real data, artificial neural network technique, clustering methods create soft sensors estimate temperature,...

Game Theory (GT) formalizes dispute scenarios between two or more players where each one makes a move following their strategy profiles. The paper introduces the integration of GT to selection and crossover steps Genetic Algorithms as an evolutionary model representation population in similar way human social evolution. Two ideas are proposed be incorporated into GA. First, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Genetic Algorithm...

In this paper we introduce a biologically plausible methodology capable to automatically generate Artificial Neural Networks (ANNs) with optimum number of neurons and adequate connection topology. order do this, three biological metaphors were used: Genetic Algorithms (GA), Lindenmayer Systems (L-Systems) ANNs. The tries mimic the natural process nervous system growing evolution, using L-Systems as recipe for development its connections GA evolve optimize architecture suited an specific...

Summary This paper presents a modified genetic algorithm (GA) using new crossover operator (ADX) and novel statistic correlation mutation (CAM). Both ADX CAM work with population information to improve existing individuals of the GA increase exploration potential via mutation. Solution-based methods offer better local improvement already known solutions while lacking at exploring whole search space; in contrast, evolutionary algorithms provide global exchange exploitation power. Hybrid are...

Convolutional neural networks (CNNs) are one of the most promising techniques from computer vision that can generate substantial gains in varied classification problems. In sense, this paper aims to perform image processing on XDB plant disease database for enhancing 20 different diseases 10 distinct species. This encompassed two pre-processing activities (image selection and resizing) application modified VGG architectures, VGG16 VGG19, along with pre-trained weights ImageNet database. A...

This research project deals with the application of dynamic modeling methods for prediction and correction (filtering) state variables in calculation position speed training rockets launched at Alcantara Launch Center. Initially, an approach is made means involved launching tracking rockets, purpose obtaining understanding acquisition radar signals, which are input filter. Then it mathematical treatment filter model to obtain equations used filtering rocket trajectory. Finally Kalman...

Despite being extensively used in many fields of science, there is still no general procedure to determine the most suitable neural architecture for a given task. Even today design an artificial network (ANN) very dependent on designer's experience. Several methods automatic ANNs have been proposed, but they are not biologically inspired, this paper it's presented state art about research theme, from earliest methodologies emerged 80's present day focusing aspects such as biological...

Data collection and manipulation from real environments are two tasks that, in a well-organized way, can support the next generation of wireless networks (NGWNs) resource allocation-related such as spectrum frequency transmission power. Due to complexity NGWNs, several metaheuristics have been proposed help these operations. However, large number studies present solutions using only one algorithm or procedure, i.e., research uses just metaheuristic resolve radio allocation problem. This fact...

This paper presents some results obtained with the development of a project to identify an experimental harmonic current model represent low voltage customers metropolitan electrical distribution system Belem city, located in north Brazil, and describes application genetic algorithm calculate R-L-C parameters passive filters that may be installed customers' houses. The main goal projecting is minimize impedance specific frequencies and, simultaneously, maximize fundamental frequency branches...