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

Biologia populacional comparada de duas espécies de heliconius (Lepidoptera: Nymphalidae) em um ambiente sazonal de floresta atlântica do nordeste brasileiro

Tropical environments often face strong seasonal variations in climate, such as alternate periods of dry and rain, that may often be important influence in the annual X the organisms lives. Here we assess how population dynamics of two butterfly species (Heliconius erato and Heliconius mepomene) respond to environmental and seasonal variations. A mark-release-recapture study carried out in an Atlantic forest reserve, 15 Km from Natal, Rio Grande do Norte, Brazil, for 3 years, during the dry and rainy season, with three visits weekly done. Information such as species, wing lenght, site of capture, pollen load and phenotype (number of spots) (in H. erato only) were noted for each capture. Seasonal variation exists in capture rates of the two species, with great capture rates during the rainy season. Despite finding differences in the mean density of individuals of the two species among the different collection areas, this difference was only significant between floodplain and central areas, and no influence of seasonality was observed in the mean density between the areas. Seasonality in wing size was only observed for H. erato, with larger wings during the rainy season. Females carried larger pollen loads than males both species, but species were similar. Only males differed seasonally, with larger pollen loads during the rainy season. The distribution of the number of wing spots did not vary between the dry and rainy seasons, and the number of spots in males and females was similar. Therefore, we conclude that there was a strong influence of seasonal variation in the population dynamic of the two Heliconius species, as well as in several aspects of their biology

Análise citoarquitetônica dos componentes do sistema de temporização circadiana do sagui (Calithrix jacchus), comparada com a inervação das suas principais aferências

The suprachiasmatic nucleus (SCN) of the anterior hypothalamus, together with the intergeniculate leaflet (IGL) of the thalamus are considered the central components of the circadian timing system (CTS) of mammals. This system is responsible for the generation and regulation of circadian rhythms by establishing a temporal organization of physiological processes and behaviors. The neuronal specific nuclear protein (NeuN) has been widely used as a neuronal marker in several studies. Since glial fibrillary acidic protein (GFAP) is a component of intermediate filaments found in the cytoplasm of astrocytes and is commonly used as a specific marker for these cells. This study aims to identify, in the marmoset, the NeuN immunoreactive neurons and glial cells immunoreactive to GFAP, as well as map the major route of photic synchronization of the STC, retinohypothalamic tract (RHT), and identify the indirect pathway to the SCN and pregeniculate nucleus (PGN) - structure homologous to IGL rodents, using immunohistochemical and cytoarchitectonic techniques. Observed in SCN the presence of neurons immunoreactive to NeuN and terminals immunoreactive subunit b of cholera toxin (CTb), neuropeptide Y (NPY) and serotonin (5- HT). In the PGN noted the presence of the NeuN and NPY immunoreactive neurons and the immunoreactive terminals CTb and 5-HT. Astrocytes are present throughout the extent of the SCN and the PGN this New World primate

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