Previsão do índice bovespa por meio de redes neurais artificiais: uma análise comparada aos métodos tradicionais de séries de tempo

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Efeitos da tilápia do Nilo (Oreochromis niloticus) e do enriquecimento por nutrientes sobre a comunidade planctônica em um lago artificial no semi-árido brasileiro

The major aim of this study was to test the hypothesis that the introduction of the Nile tilapia (Oreochromis niloticus) and the enrichment with nutrients (N and P) interact synergistically to change the structure of plankton communities, increase phytoplankton biomass and decrease water transparency of a semi-arid tropical reservoir. One field experiment was performed during five weeks in twenty enclosures (8m3) to where four treatments were randomly allocated: with tilapia addition (T), with nutrients addition (NP), with tilapia and nutrients addition (T+NP) and a control treatment with no tilapia or nutrients addition (C). A two-way repeated measures ANOVA was done to test for time (t), tilapia (T) and nutrient (NP) effects and their interaction on water transparency, total phosphorus, total nitrogen, phytoplankton and zooplankton. The results show that there was no effect of nutrient addition on these variables but significant fish effects on the biomass of total zooplankton, nauplii, rotifers, cladocerans and calanoid copepods, on the biovolume of Bacillariophyta, Zygnemaphyceae and large algae (GALD ≥ 50 μm) and on Secchi depth. In addition, we found significant interaction effects between tilapia and nutrients on Secchi depth and rotifers. Overall, tilapia decreased the biomass of most zooplankton taxa and large algae (diatoms) and decreased the water transparency while nutrient enrichment increased the biomass of zooplankton (rotifers) but only in the absence of tilapia. In conclusion, the influence of fish on the reservoir plankton community and water transparency was greater than that of nutrient loading. This finding suggests that biomanipulation should be a greater priority in the restoration of eutrophic reservoirs in tropical semi-arid regions

Ambiente para avaliação de controladores fuzzy aplicados ao método de elevação artificial por bombeio centrífugo submerso

From their early days, Electrical Submergible Pumping (ESP) units have excelled in lifting much greater liquid rates than most of the other types of artificial lift and developed by good performance in wells with high BSW, in onshore and offshore environments. For all artificial lift system, the lifetime and frequency of interventions are of paramount importance, given the high costs of rigs and equipment, plus the losses coming from a halt in production. In search of a better life of the system comes the need to work with the same efficiency and security within the limits of their equipment, this implies the need for periodic adjustments, monitoring and control. How is increasing the prospect of minimizing direct human actions, these adjustments should be made increasingly via automation. The automated system not only provides a longer life, but also greater control over the production of the well. The controller is the brain of most automation systems, it is inserted the logic and strategies in the work process in order to get you to work efficiently. So great is the importance of controlling for any automation system is expected that, with better understanding of ESP system and the development of research, many controllers will be proposed for this method of artificial lift. Once a controller is proposed, it must be tested and validated before they take it as efficient and functional. The use of a producing well or a test well could favor the completion of testing, but with the serious risk that flaws in the design of the controller were to cause damage to oil well equipment, many of them expensive. Given this reality, the main objective of the present work is to present an environment for evaluation of fuzzy controllers for wells equipped with ESP system, using a computer simulator representing a virtual oil well, a software design fuzzy controllers and a PLC. The use of the proposed environment will enable a reduction in time required for testing and adjustments to the controller and evaluated a rapid diagnosis of their efficiency and effectiveness. The control algorithms are implemented in both high-level language, through the controller design software, such as specific language for programming PLCs, Ladder Diagram language.

Sistema de sensoriamento eletromagnético utilizado para detecção da contaminação do óleo isolante do motor no método de elevação artificial do tipo bombeio centrífugo submerso

In the artificial lift method by Electrical Submersible Pump (ESP), the energy is transmitted for the well´s deep through a flat electric handle, where it is converted into mechanical energy through an engine of sub-surface, which is connected to a centrifugal pump. This transmits energy to the fluid under the pressure form, bringing it to the surface In this method the subsurface equipment is basically divided into: pump, seal and motor. The main function of the seal is the protect the motor, avoiding the motor´s oil be contaminated by oil production and the consequent burning of it. Over time, the seal will be wearing and initiates a contamination of motor oil, causing it to lose its insulating characteristics. This work presents a design of a magnetic sensor capable of detecting contamination of insulating oil used in the artificial lift method of oil-type Electrical Submersible Pump (ESP). The objective of this sensor is to generate alarm signal just the moment when the contamination in the isolated oil is present, enabling the implementation of a predictive maintenance. The prototype was designed to work in harsh conditions to reach a depth of 2000m and temperatures up to 150°C. It was used a simulator software to defined the mechanical and electromagnetic variables. Results of field experiments were performed to validate the prototype. The final results performed in an ESP system with a 62HP motor showed a good reliability and fast response of the prototype.

Contribuição para o estudo do embarque de uma rede neural artificial em field programmable gate array (FPGA)

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Secagem de grãos de girassol em leito fixo e em leito de jorro

This work studies two methods for drying sunflower grains grown in the western region of Rio Grande do Norte, in the premises of the Instituto Federal de Educação, Ciência e Tecnologia do Rio Grande do Norte - IFRN - Campus Apodi. This initiative was made because of the harvested grain during the harvest, being stored in sheds without any control of temperature, humidity etc. Therewith, many physical, chemical and physiological characteristics are compromised and grains lose much quality for oil production as their germination power. Taking into account that most of the stored grain is used for replanting, the studied methods include drying of grains in a thin layer using an oven with air circulation (fixed bed) and drying in a spouted bed. It was studied the drying of grains in natura, i.e., newly harvested. The fixed bed drying was carried out at temperatures of 40, 50, 60 and 70°C. Experiments in spouted bed were performed based on an experimental design, 2² + 3, with three replications at the central point, where the independent variables were grains load (1500, 2000 and 2500 g) and the temperature of the inlet air (70, 80, and 90 °C), obtaining the drying and desorption equilibrium isotherms. Previously, the characteristic curves of the bed were obtained. Both in the fixed bed as in the spouted bed, drying and desorption curves were obtained by weighing the grains throughout the experiments and measurements of water activity, respectively. The grains drying in the spouted bed showed good results with significant reduction of processing time. The models of FICK and PAGE were fitted to the experimental data, models which will represent the drying of grains both in the fixed bed as in the spouted bed. The desorption curves showed no influence of the processing temperature in the hygroscopic characteristics of the grains. The models of GAB, OSWIN and LUIKOV could well represent the desorption isotherms

Influência de fotoperíodo artificial no comportamento de um primata neotropical diurno (Callithrix jacchus)

One of the main environmental cues for the adjustment of temporal organization of the animals is the light-dark cycle (LD), which undergoes changes in phase duration throughout the seasons. Photoperiod signaling by melatonin in mammals allows behavioral changes along the year, as in the activity-rest cycle, in mood states and in cognitive performance. The aim of this study was to investigate if common marmoset (Callithrix jacchus) exhibits behavioral changes under short and long photoperiods in a 24h cycle, assessing their individual behaviors, vocal repertoire, exploratory activity (EA), recognition memory (RM) and the circadian rhythm of locomotor activity (CRA). Eight adult marmosets were exposed to a light-dark cycle of 12:12; LD 08:16; LD 12:12 and LD 16:08, sequentially, for four weeks in each condition. Locomotor activity was recorded 24h/day by passive infrared motion detectors above the individual cages. A video camera system was programmed to record each animal, twice a week, on the first two light hours. From the videos, frequency of behaviors was registered as anxiety-like, grooming, alert, hanging position, staying in nest box and feeding using continuous focal animal sampling method. Simultaneously, the calls emitted in the experimental room were recorded by a single microphone centrally located and categorized as affiliative (whirr, chirp), contact (phee), long distance (loud shrill), agonistic (twitter) and alarm (tsik, seep, see). EA was assessed on the third hour after lights onset on the last week of each condition. In a first session, marmosets were exposed to one unfamiliar object during 15 min and 24h later, on the second session, a novel object was added to evaluate RM. Results showed that long days caused a decreased of amplitude and period variance of the CRA, but not short days. Short days decreased the total daily activity and active phase duration. On long days, active phase duration increased due to an advance of activity onset in relation to symmetric days. However, not all subjects started the activity earlier on long days. The activity offset was similar to symmetric days for the majority of marmosets. Results of EA showed that RM was not affected by short or long days, and that the marmosets exhibited a decreased in duration of EA on long days. Frequency and type of calls and frequency of anxiety-like behaviors, staying in nest box and grooming were lower on the first two light hours on long days. Considering the whole active phase of marmosets as we elucidate the results of vocalizations and behaviors, it is possible that these changes in the first two light hours are due to the shifting of temporal distribution of marmoset activities, since some animals did not advance the activity onset on long days. Consequently, the marmosets mean decreased because the sampling was not possible. In conclusion, marmosets synchronized the CRA to the tested photoperiods and as the phase angle varied a lot among marmosets it is suggested that they can use different strategies. Also, long days had an effect on activity-rest cycle and exploratory behaviors

Efeitos do turno fixo sobre a saúde mental em operadores de petróleo :um estudo de caso em dois ativos produção da Petrobrás

Un conjunto de cambios viene siendo implantado en la Petrobrás procurando que sus unidades de negocios resulten más modernas y competitivas para atender las necesidades del mercado. Dentro de esta perspectiva, un nuevo régimen de trabajo, denominado turno fijo , ha sido implantado en dos activos de producción de la provincia de Rio Grande do Norte. Tal situación originó varios reclamos de los petroleros y, consecuentemente, el interés del SINDIPETRO-RN en obtener una evaluación más precisa de las consecuencias de los mismos. Este estudio, realizado a partir de la demanda sindical de esos trabajadores, ha tenido como objetivo central analizar los efectos del turno fijo sobre la salud mental de los operadores de producción, actualmente lotados en los referidos activos. El estudio ha sido realizado con 39 operadores que representan el 82,9% de la población objeto de este estudio. La muestra ha sido homogénea en cuanto al género, grado de instrucción, edad y tiempo de servicio en la compañía, lo que ha posibilitado un mayor control de las variables y un estudio comparativo entre los dos activos. Para el desarrollo del estudio, se han aplicado los siguientes instrumentos de colecta de datos: una escala de medida probada y validada (QSG-12), un cuestionario abierto, entrevistas individuales y una ficha socio-demográfica. Las respuestas del cuestionario abierto han sido categorizadas mediante la aplicación de análisis de contenido. Los resultados de ese tratamiento y las respuestas del QSG-12 han sido registradas en la forma de banco de datos del SPSS for Windows (Statical Package for social sciense for Windows) para luego procederse con el desarrolllo de los análisis estadísticos. Los principales resultados encontrados en el estudio han sido que la mitad de los participantes de la muestra han presentado resultados de deteriorización de la autoeficacia más elevado que 1,44 (un una escala de 0 a 3) y, en tensión emocional y depresión, el resultado es más elevado que 1,67; la mayoría se da cuenta del aumento de carga de trabajo, revela acentuado sufrimiento con el distanciamiento de la familia, y 58,8% presenta enfermedades psicosomáticas crónicas. La percepción de los operadores sobre el turno fijo e el análisis de éste, conforme el modelo vitamínico de Warr, conducen a la conclusión de que el turno fijo es uno de los factores que está influyendo negativamente en la salud mental de esos trabajadores

Registro global de nuvens de pontos RGB-D em tempo real usando fluxo óptico e marcadores

Registration of point clouds captured by depth sensors is an important task in 3D reconstruction applications based on computer vision. In many applications with strict performance requirements, the registration should be executed not only with precision, but also in the same frequency as data is acquired by the sensor. This thesis proposes theuse of the pyramidal sparse optical flow algorithm to incrementally register point clouds captured by RGB-D sensors (e.g. Microsoft Kinect) in real time. The accumulated errorinherent to the process is posteriorly minimized by utilizing a marker and pose graph optimization. Experimental results gathered by processing several RGB-D datasets validatethe system proposed by this thesis in visual odometry and simultaneous localization and mapping (SLAM) applications.

Previsão do índice bovespa por meio de redes neurais artificiais: uma análise comparada aos métodos tradicionais de séries de tempo

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Efeitos da tilápia do Nilo (Oreochromis niloticus) e do enriquecimento por nutrientes sobre a comunidade planctônica em um lago artificial no semi-árido brasileiro

The major aim of this study was to test the hypothesis that the introduction of the Nile tilapia (Oreochromis niloticus) and the enrichment with nutrients (N and P) interact synergistically to change the structure of plankton communities, increase phytoplankton biomass and decrease water transparency of a semi-arid tropical reservoir. One field experiment was performed during five weeks in twenty enclosures (8m3) to where four treatments were randomly allocated: with tilapia addition (T), with nutrients addition (NP), with tilapia and nutrients addition (T+NP) and a control treatment with no tilapia or nutrients addition (C). A two-way repeated measures ANOVA was done to test for time (t), tilapia (T) and nutrient (NP) effects and their interaction on water transparency, total phosphorus, total nitrogen, phytoplankton and zooplankton. The results show that there was no effect of nutrient addition on these variables but significant fish effects on the biomass of total zooplankton, nauplii, rotifers, cladocerans and calanoid copepods, on the biovolume of Bacillariophyta, Zygnemaphyceae and large algae (GALD ≥ 50 μm) and on Secchi depth. In addition, we found significant interaction effects between tilapia and nutrients on Secchi depth and rotifers. Overall, tilapia decreased the biomass of most zooplankton taxa and large algae (diatoms) and decreased the water transparency while nutrient enrichment increased the biomass of zooplankton (rotifers) but only in the absence of tilapia. In conclusion, the influence of fish on the reservoir plankton community and water transparency was greater than that of nutrient loading. This finding suggests that biomanipulation should be a greater priority in the restoration of eutrophic reservoirs in tropical semi-arid regions

Ambiente para avaliação de controladores fuzzy aplicados ao método de elevação artificial por bombeio centrífugo submerso

From their early days, Electrical Submergible Pumping (ESP) units have excelled in lifting much greater liquid rates than most of the other types of artificial lift and developed by good performance in wells with high BSW, in onshore and offshore environments. For all artificial lift system, the lifetime and frequency of interventions are of paramount importance, given the high costs of rigs and equipment, plus the losses coming from a halt in production. In search of a better life of the system comes the need to work with the same efficiency and security within the limits of their equipment, this implies the need for periodic adjustments, monitoring and control. How is increasing the prospect of minimizing direct human actions, these adjustments should be made increasingly via automation. The automated system not only provides a longer life, but also greater control over the production of the well. The controller is the brain of most automation systems, it is inserted the logic and strategies in the work process in order to get you to work efficiently. So great is the importance of controlling for any automation system is expected that, with better understanding of ESP system and the development of research, many controllers will be proposed for this method of artificial lift. Once a controller is proposed, it must be tested and validated before they take it as efficient and functional. The use of a producing well or a test well could favor the completion of testing, but with the serious risk that flaws in the design of the controller were to cause damage to oil well equipment, many of them expensive. Given this reality, the main objective of the present work is to present an environment for evaluation of fuzzy controllers for wells equipped with ESP system, using a computer simulator representing a virtual oil well, a software design fuzzy controllers and a PLC. The use of the proposed environment will enable a reduction in time required for testing and adjustments to the controller and evaluated a rapid diagnosis of their efficiency and effectiveness. The control algorithms are implemented in both high-level language, through the controller design software, such as specific language for programming PLCs, Ladder Diagram language.

Sistema de sensoriamento eletromagnético utilizado para detecção da contaminação do óleo isolante do motor no método de elevação artificial do tipo bombeio centrífugo submerso

In the artificial lift method by Electrical Submersible Pump (ESP), the energy is transmitted for the well´s deep through a flat electric handle, where it is converted into mechanical energy through an engine of sub-surface, which is connected to a centrifugal pump. This transmits energy to the fluid under the pressure form, bringing it to the surface In this method the subsurface equipment is basically divided into: pump, seal and motor. The main function of the seal is the protect the motor, avoiding the motor´s oil be contaminated by oil production and the consequent burning of it. Over time, the seal will be wearing and initiates a contamination of motor oil, causing it to lose its insulating characteristics. This work presents a design of a magnetic sensor capable of detecting contamination of insulating oil used in the artificial lift method of oil-type Electrical Submersible Pump (ESP). The objective of this sensor is to generate alarm signal just the moment when the contamination in the isolated oil is present, enabling the implementation of a predictive maintenance. The prototype was designed to work in harsh conditions to reach a depth of 2000m and temperatures up to 150°C. It was used a simulator software to defined the mechanical and electromagnetic variables. Results of field experiments were performed to validate the prototype. The final results performed in an ESP system with a 62HP motor showed a good reliability and fast response of the prototype.