REDUÇÃO DE VARIÁVEIS DE ENTRADA DE REDES NEURAIS ARTIFICIAIS A PARTIR DE DADOS DE ANÁLISE DE COMPONENTES PRINCIPAIS NA MODELAGEM DE OXIGÊNIO DISSOLVIDO

The objective of this work is to demonstrate the efficient utilization of the Principal Components Analysis (PCA) as a method to pre-process the original multivariate data, that is rewrite in a new matrix with principal components sorted by it's accumulated variance. The Artificial Neural Network (ANN) with backpropagation algorithm is trained, using this pre-processed data set derived from the PCA method, representing 90.02% of accumulated variance of the original data, as input. The training goal is modeling Dissolved Oxygen using information of other physical and chemical parameters. The water samples used in the experiments are gathered from the Paraíba do Sul River in São Paulo State, Brazil. The smallest Mean Square Errors (MSE) is used to compare the results of the different architectures and choose the best. The utilization of this method allowed the reduction of more than 20% of the input data, which contributed directly for the shorting time and computational effort in the ANN training.

Description of epidemics of coffee rust with neural networks

The objective of this paper was to evaluate the potential of neural networks (NN) as an alternative method to the basic epidemiological approach to describe epidemics of coffee rust. The NN was developed from the intensities of coffee (Coffea arabica) rust along with the climatic variables collected in Lavras-MG between 13 February 1998 and 20 April 2001. The NN was built with climatic variables that were either selected in a stepwise regression analysis or by the Braincel® system, software for NN building. Fifty-nine networks and 26 regression models were tested. The best models were selected based on small values of the mean square deviation (MSD) and of the mean prediction error (MPE). For the regression models, the highest coefficients of determination (R²) were used. The best model developed with neural networks had an MSD of 4.36 and an MPE of 2.43%. This model used the variables of minimum temperature, production, relative humidity of the air, and irradiance 30 days before the evaluation of disease. The best regression model was developed from 29 selected climatic variables in the network. The summary statistics for this model were: MPE=6.58%, MSE=4.36, and R²=0.80. The elaborated neural networks from a time series also were evaluated to describe the epidemic. The incidence of coffee rust at four previous fortnights resulted in a model with MPE=4.72% and an MSD=3.95.

Production of baruzeiro seedling in different protected environments and substrates

The high seedlings quality is essential for deployment of homogeneous orchards. This study evaluated the baruzeiro (Dipteryx alata Vog) seedlings formation on different substrates within protected environments. It was used substrates with100% of cattle manure; 100% of cassava stems; 100% of vermiculite; 50% of cattle manure + 50% of cassava stems; 50% of cattle manure + 50% of vermiculite; 50% of cassava stems + 50% of vermiculite; and + ⅓ of cattle manure + ⅓ of cassava stems + ⅓ of vermiculite. These substrates were tested in protected areas: greenhouse; black shade net of 50% shading; and aluminized thermo-reflective screen of 50% shading. A completely randomized experimental design with five replicates of four plants was adopted. Initially, data were submitted to analysis of individual variance of the substrates, in each environment of cultivation, then performing the evaluation of the residual mean square and the analysis of these environments together for comparison. The best substrate for baruzeiro seedlings was pure vermiculite. The substrates with 100% of manure and the substrate with 33.33% of the mixed studied materials can be used for seedlings formation. The environment with screen can be indicated for the production of baruzeiro seedlings, since it gave vigor to the seedlings.

Seedlings of Acrocomia aculeata in diferent substrates and protected environments

The seedling production stage is the key to achieve uniformity in tree breeding stage. This study evaluated "bocaiúva" (Acrocomia aculeata) seedling formation, with pre-germinated seeds in different substrates and protected environments, in the University of Mato Grosso do Sul State, Aquidauana, MS. As substrates, we used 100% cattle manure (M), 100% cassava branches (CB), 100% vermiculite (V), 50% cattle manure + 50% cassava branches, 50 % cattle manure + 50% vermiculite, 50% cassava branches + 50% vermiculite and ⅓ cattle manure + ⅓ cassava branches + ⅓ vermiculite. These substrates were tested in a greenhouse covered with 150 µm low density polyethylene (LDPE) film under thermo-reflective screen with 50% shading under film; black screen with 50% shading on the sides; black monofilament screen with 50% shading set on roof and sides; and aluminized thermo- reflective screen with 50% shading set on roof and sides. The completely randomized experimental design with 5 replications of 5 plants each was adopted. Initially, data were submitted to analysis of substrate individual variance in each growing environment, then performing the waste mean square evaluation and their environment joint analysis for comparison. The best growing environment is the thermo-reflective screen compared to LDPE greenhouse and black screen set. All substrates containing manure are recommended for bocaiúva seedlings formation. The pure cassava branch is not indicated for seedling, even using chemical fertilizer.

Evaluation of thermorregulatory capacity of dairy buffaloes using infrared thermography

ABSTRACT The objective of this study was to evaluate the thermoregulatory response of dairy buffaloes in pre-milking and post-milking. To identify animal thermoregulatory capacity, skin surface temperatures were taken by an infrared thermometer (SST), a thermographic camera (MTBP) as well as respiratory rate records (RR). Black Globe and Humidity Index (BGHI), radiating thermal load (RTL) and enthalpy (H) were used to characterize the thermal environment. Artificial Neural Networks analyzed those indices as well as animal physiological data, using a single layer trained with the least mean square (LMS) algorithm. The results indicated that pre-milking and post-milking environments reached BGHI, RR, SST and MTBP values above thermal neutrality zone for buffaloes. In addition, limits of surface skin temperatures were mostly influenced by changing ambient conditions to the detriment of respiratory rates. It follows that buffaloes are sensitive to environmental changes and their skin temperatures are the best indicators of thermal comfort in relation to respiratory rate.

Estimation of aircraft aerodynamic derivatives using Extended Kalman Filter

Design of flight control laws, verification of performance predictions, and the implementation of flight simulations are tasks that require a mathematical model of the aircraft dynamics. The dynamical models are characterized by coefficients (aerodynamic derivatives) whose values must be determined from flight tests. This work outlines the use of the Extended Kalman Filter (EKF) in obtaining the aerodynamic derivatives of an aircraft. The EKF shows several advantages over the more traditional least-square method (LS). Among these the most important are: there are no restrictions on linearity or in the form which the parameters appears in the mathematical model describing the system, and it is not required that these parameters be time invariant. The EKF uses the statistical properties of the process and the observation noise, to produce estimates based on the mean square error of the estimates themselves. Differently, the LS minimizes a cost function based on the plant output behavior. Results for the estimation of some longitudinal aerodynamic derivatives from simulated data are presented.

Forecasting of wind speeds and directions with artificial neural networks

In this master’s thesis, wind speeds and directions were modeled with the aim of developing suitable models for hourly, daily, weekly and monthly forecasting. Artificial Neural Networks implemented in MATLAB software were used to perform the forecasts. Three main types of artificial neural network were built, namely: Feed forward neural networks, Jordan Elman neural networks and Cascade forward neural networks. Four sub models of each of these neural networks were also built, corresponding to the four forecast horizons, for both wind speeds and directions. A single neural network topology was used for each of the forecast horizons, regardless of the model type. All the models were then trained with real data of wind speeds and directions collected over a period of two years in the municipal region of Puumala in Finland. Only 70% of the data was used for training, validation and testing of the models, while the second last 15% of the data was presented to the trained models for verification. The model outputs were then compared to the last 15% of the original data, by measuring the mean square errors and sum square errors between them. Based on the results, the feed forward networks returned the lowest generalization errors for hourly, weekly and monthly forecasts of wind speeds; Jordan Elman networks returned the lowest errors when used for forecasting of daily wind speeds. Cascade forward networks gave the lowest errors when used for forecasting daily, weekly and monthly wind directions; Jordan Elman networks returned the lowest errors when used for hourly forecasting. The errors were relatively low during training of the models, but shot up upon simulation with new inputs. In addition, a combination of hyperbolic tangent transfer functions for both hidden and output layers returned better results compared to other combinations of transfer functions. In general, wind speeds were more predictable as compared to wind directions, opening up opportunities for further research into building better models for wind direction forecasting.

The effect of an aerobic training program on the electrical remodeling of the heart: high-frequency components of the signal-averaged electrocardiogram are predictors of the maximal aerobic power

Increased heart rate variability (HRV) and high-frequency content of the terminal region of the ventricular activation of signal-averaged ECG (SAECG) have been reported in athletes. The present study investigates HRV and SAECG parameters as predictors of maximal aerobic power (VO2max) in athletes. HRV, SAECG and VO2max were determined in 18 high-performance long-distance (25 ± 6 years; 17 males) runners 24 h after a training session. Clinical visits, ECG and VO2max determination were scheduled for all athletes during thew training period. A group of 18 untrained healthy volunteers matched for age, gender, and body surface area was included as controls. SAECG was acquired in the resting supine position for 15 min and processed to extract average RR interval (Mean-RR) and root mean squared standard deviation (RMSSD) of the difference of two consecutive normal RR intervals. SAECG variables analyzed in the vector magnitude with 40-250 Hz band-pass bi-directional filtering were: total and 40-µV terminal (LAS40) duration of ventricular activation, RMS voltage of total (RMST) and of the 40-ms terminal region of ventricular activation. Linear and multivariate stepwise logistic regressions oriented by inter-group comparisons were adjusted in significant variables in order to predict VO2max, with a P < 0.05 considered to be significant. VO2max correlated significantly (P < 0.05) with RMST (r = 0.77), Mean-RR (r = 0.62), RMSSD (r = 0.47), and LAS40 (r = -0.39). RMST was the independent predictor of VO2max. In athletes, HRV and high-frequency components of the SAECG correlate with VO2max and the high-frequency content of SAECG is an independent predictor of VO2max.

Manipulating Greek musical modes and tempo affects perceived musical emotion in musicians and nonmusicians

The combined influence of tempo and mode on emotional responses to music was studied by crossing 7 changes in mode with 3 changes in tempo. Twenty-four musicians aged 19 to 25 years (12 males and 12 females) and 24 nonmusicians aged 17 to 25 years (12 males and 12 females) were required to perform two tasks: 1) listening to different musical excerpts, and 2) associating an emotion to them such as happiness, serenity, fear, anger, or sadness. ANOVA showed that increasing the tempo strongly affected the arousal (F(2,116) = 268.62, mean square error (MSE) = 0.6676, P < 0.001) and, to a lesser extent, the valence of emotional responses (F(6,348) = 8.71, MSE = 0.6196, P < 0.001). Changes in modes modulated the affective valence of the perceived emotions (F(6,348) = 4.24, MSE = 0.6764, P < 0.001). Some interactive effects were found between tempo and mode (F (1,58) = 115.6, MSE = 0.6428, P < 0.001), but, in most cases, the two parameters had additive effects. This finding demonstrates that small changes in the pitch structures of modes modulate the emotions associated with the pieces, confirming the cognitive foundation of emotional responses to music.

An analysis of decoupling procedures in generating thermal Green's functions of O([lambda]â ´) by the Zubarev equation of motion method

The Zubarev equation of motion method has been applied to an anharmonic crystal of O( ,,4). All possible decoupling schemes have been interpreted in order to determine finite temperature expressions for the one phonon Green's function (and self energy) to 0()\4) for a crystal in which every atom is on a site of inversion symmetry. In order to provide a check of these results, the Helmholtz free energy expressions derived from the self energy expressions, have been shown to agree in the high temperature limit with the results obtained from the diagrammatic method. Expressions for the correlation functions that are related to the mean square displacement have been derived to 0(1\4) in the high temperature limit.

Altered sensory-weighting mechanisms is observed in adolescents with idiopathic scoliosis

Affiliation: Paul Allard : Département de kinésiologie, Université de Montréal

Efficient estimation using the characteristic function : theory and applications with high frequency data

The attached file is created with Scientific Workplace Latex

Imputation en présence de données contenant des zéros

L’imputation simple est très souvent utilisée dans les enquêtes pour compenser pour la non-réponse partielle. Dans certaines situations, la variable nécessitant l’imputation prend des valeurs nulles un très grand nombre de fois. Ceci est très fréquent dans les enquêtes entreprises qui collectent les variables économiques. Dans ce mémoire, nous étudions les propriétés de deux méthodes d’imputation souvent utilisées en pratique et nous montrons qu’elles produisent des estimateurs imputés biaisés en général. Motivé par un modèle de mélange, nous proposons trois méthodes d’imputation et étudions leurs propriétés en termes de biais. Pour ces méthodes d’imputation, nous considérons un estimateur jackknife de la variance convergent vers la vraie variance, sous l’hypothèse que la fraction de sondage est négligeable. Finalement, nous effectuons une étude par simulation pour étudier la performance des estimateurs ponctuels et de variance en termes de biais et d’erreur quadratique moyenne.

Inférence robuste à la présence des valeurs aberrantes dans les enquêtes

Cette thèse comporte trois articles dont un est publié et deux en préparation. Le sujet central de la thèse porte sur le traitement des valeurs aberrantes représentatives dans deux aspects importants des enquêtes que sont : l’estimation des petits domaines et l’imputation en présence de non-réponse partielle. En ce qui concerne les petits domaines, les estimateurs robustes dans le cadre des modèles au niveau des unités ont été étudiés. Sinha & Rao (2009) proposent une version robuste du meilleur prédicteur linéaire sans biais empirique pour la moyenne des petits domaines. Leur estimateur robuste est de type «plugin», et à la lumière des travaux de Chambers (1986), cet estimateur peut être biaisé dans certaines situations. Chambers et al. (2014) proposent un estimateur corrigé du biais. En outre, un estimateur de l’erreur quadratique moyenne a été associé à ces estimateurs ponctuels. Sinha & Rao (2009) proposent une procédure bootstrap paramétrique pour estimer l’erreur quadratique moyenne. Des méthodes analytiques sont proposées dans Chambers et al. (2014). Cependant, leur validité théorique n’a pas été établie et leurs performances empiriques ne sont pas pleinement satisfaisantes. Ici, nous examinons deux nouvelles approches pour obtenir une version robuste du meilleur prédicteur linéaire sans biais empirique : la première est fondée sur les travaux de Chambers (1986), et la deuxième est basée sur le concept de biais conditionnel comme mesure de l’influence d’une unité de la population. Ces deux classes d’estimateurs robustes des petits domaines incluent également un terme de correction pour le biais. Cependant, ils utilisent tous les deux l’information disponible dans tous les domaines contrairement à celui de Chambers et al. (2014) qui utilise uniquement l’information disponible dans le domaine d’intérêt. Dans certaines situations, un biais non négligeable est possible pour l’estimateur de Sinha & Rao (2009), alors que les estimateurs proposés exhibent un faible biais pour un choix approprié de la fonction d’influence et de la constante de robustesse. Les simulations Monte Carlo sont effectuées, et les comparaisons sont faites entre les estimateurs proposés et ceux de Sinha & Rao (2009) et de Chambers et al. (2014). Les résultats montrent que les estimateurs de Sinha & Rao (2009) et de Chambers et al. (2014) peuvent avoir un biais important, alors que les estimateurs proposés ont une meilleure performance en termes de biais et d’erreur quadratique moyenne. En outre, nous proposons une nouvelle procédure bootstrap pour l’estimation de l’erreur quadratique moyenne des estimateurs robustes des petits domaines. Contrairement aux procédures existantes, nous montrons formellement la validité asymptotique de la méthode bootstrap proposée. Par ailleurs, la méthode proposée est semi-paramétrique, c’est-à-dire, elle n’est pas assujettie à une hypothèse sur les distributions des erreurs ou des effets aléatoires. Ainsi, elle est particulièrement attrayante et plus largement applicable. Nous examinons les performances de notre procédure bootstrap avec les simulations Monte Carlo. Les résultats montrent que notre procédure performe bien et surtout performe mieux que tous les compétiteurs étudiés. Une application de la méthode proposée est illustrée en analysant les données réelles contenant des valeurs aberrantes de Battese, Harter & Fuller (1988). S’agissant de l’imputation en présence de non-réponse partielle, certaines formes d’imputation simple ont été étudiées. L’imputation par la régression déterministe entre les classes, qui inclut l’imputation par le ratio et l’imputation par la moyenne sont souvent utilisées dans les enquêtes. Ces méthodes d’imputation peuvent conduire à des estimateurs imputés biaisés si le modèle d’imputation ou le modèle de non-réponse n’est pas correctement spécifié. Des estimateurs doublement robustes ont été développés dans les années récentes. Ces estimateurs sont sans biais si l’un au moins des modèles d’imputation ou de non-réponse est bien spécifié. Cependant, en présence des valeurs aberrantes, les estimateurs imputés doublement robustes peuvent être très instables. En utilisant le concept de biais conditionnel, nous proposons une version robuste aux valeurs aberrantes de l’estimateur doublement robuste. Les résultats des études par simulations montrent que l’estimateur proposé performe bien pour un choix approprié de la constante de robustesse.

Use of mirage effect for the detection of phase transitions in solids

The phenomenon of mirage effect suffered by a He-Ne laser beam has been utilized to detect phase transitions in solids. It has been observed that anomalous fluctuations of large amplitude occur in the signal level near the transition temperature. The mean square value of the fluctuation is found to exhibit a well-defined peak at this point. Results of measurements made in the case of crystals of TGS ((NH2CH2COOH)3.H2SO4) and a ceramic sample (BaTiO3) are given to illustrate this technique.