No description available.

[pt] Em obras de maior porte e grande responsabilidade (portos, barragens, usinas nucleares, etc.), a quantidade de instrumentações pode se tornar suficiente para permitir a construção de modelos de variabilidade temporal das propriedades de interesse com base em redes neurais artificiais. No caso de barragens, o monitoramento através da instalação de um sistema de instrumentação desempenha um papel fundamental na avaliação do comportamento destas estruturas, tanto durante o período de construção quanto no período de operação. Neste trabalho empregou-se a técnica de redes neurais temporais (RNT) para análise, modelagem e previsão dos valores de vazão na barragem Funil, do sistema Furnas Centrais Elétricas, a partir dos dados de instrumentações disponíveis no período compreendido entre 02/09/1985 e 25/02/2002. As redes neurais temporais empregadas foram: RNT com arquitetura feedforward associada a técnica de janelamento, RNT recorrente Elman, RNT FIR e RNT Jordan. Adicionalmente, foram utilizadas duas técnicas para análise das séries temporais: os modelos de Box & Jenkins (1970) e métodos geoestatísticos, com a finalidade de comparar com o desempenho das RNT´s. Nesta pesquisa estuda-se ainda a geração de intervalos de confiança para RNT e para métodos geoestatísticos. As previsões de vazão analisadas neste trabalho, envolvendo o comportamento da barragem Funil, apresentaram resultados satisfatórios tanto os obtidos pelos modelos de redes neurais temporais como pelos de Box & Jenkins e métodos geoestatísticos. / [en] In works of great responsibility (ports, dams, nuclear power, etc.), the amount of instrumentation data may allow the construction of models for the temporary variability of the properties of interest based on neural network techniques. In case of dams, the monitoring through the installation of an instrumentation system plays a fundamental part in the evaluation of the behavior of these structures, during the construction period as well as in the operation period. In this work the technique of temporal neural networks (TNN) was used for analysis, modeling and forecast of the water discharges values in the Funil dam, from Furnas Centrais Elétricas system, starting from the data of available instrumentation in the period between 02/09/1985 and 25/02/2002. The temporal neural networks used in this research were the following: TNN with feedforward architecture and the windowing technique, recursive TNN Elman, TNN FIR and TNN Jordan. Two additional techniques (Box & Jenkins and geostatistical models) were employed for analysis of the time series with the purpose to compare the results obtained with neural networks. In this research the generation of confidence intervals for TNN and geostatistical methods were also investigated. The discharge values forecasts analyzed in this work for the Funil dam presented satisfactory results, with respect to the neural network, Box & Jenkins and geostatistical methods.

The unique problems encountered when analyzing weather data sets - that is, measurements taken while conducting a meteorological experiment- have forced statisticians to reconsider the conventional analysis methods and investigate permutation test procedures. The problems encountered when analyzing weather data sets are simulated for a Monte Carlo study, and the results of the parametric and permutation t-tests are compared with regard to significance level, power, and the average coilfidence interval length. Seven population distributions are considered - three are variations of the normal distribution, and the others the gamma, the lognormal, the rectangular and empirical distributions. The normal distribution contaminated with zero measurements is also simulated. In those simulated situations in which the variances are unequal, the permutation test procedure was performed using other test statistics, namely the Scheffe, Welch and Behrens-Fisher test statistics. / Mathematical Sciences / M. Sc. (Statistics)

Les bandes de fréquences utilisées conventionnellement pour les systèmes fixes de télécommunication par satellites (bandes C et Ku i.e. 4-15 GHz) sont congestionnées. Néanmoins, le marché des télécommunications civil et de défense accuse une demande de plus en plus importante en services multimédia haut-débit. Par conséquent, l'augmentation de la fréquence porteuse vers les bandes Ka et Q/V (20-40/50 GHz)est activement étudiée. Pour des fréquences supérieures à 5 GHz, la propagation des signaux radioélectriques souffre de l'atténuation troposphérique. Parmi les différents contributeurs à l'affaiblissement troposphérique total(atténuation, scintillation, dépolarisation, température de bruit du ciel), les précipitations jouent un rôle prépondérant. Pour compenser la détérioration des conditions de propagation, des techniques de compensation des affaiblissements (FMT: Fade Mitigation Technique) permettant d'adapter en temps réel les caractéristiques du système en fonction de l'état du canal de propagation doivent être employées. Une alternative à l'utilisation de séries temporelles expérimentales peu nombreuses est la génération de séries temporelles synthétiques d'atténuation due à la pluie et d'atténuation totale représentatives d'une liaison donnée.Le manuscrit est organisé autour de cinq articles. La première contribution est dédiée à la modélisation temporelle de l'affaiblissement troposphérique total. Le deuxième article porte sur des améliorations significatives du modèle de génération de séries temporelles d'atténuation due à la pluie recommandé par l'UITR.Les trois contributions suivantes constituent une analyse critique et une modélisation de la variabilité des statistiques du 1er ordre utilisées lors des tests des modèles de canal. La variance de l'estimateur statistique des distributions cumulatives complémentaires de l'atténuation due à la pluie et de l'intensité de précipitation est alors mise en évidence. Un modèle à application mondiale paramétré au moyen de données expérimentales est proposé. Celui-ci permet, d'une part, d'estimer les intervalles de confiance associés aux mesures de propagation et d'autre part, de quantifier le risque en termes de disponibilité annuelle associée à la prédiction d'une marge de propagation donnée. Cette approche est étendue aux variabilités des statistiques jointes. Elle permet alors une évaluation statistique de l'impact des techniques de diversité de site sur les performances systèmes, tant à microéchelle(quelques kms) qu'à macro-échelle (quelques centaines de kms). / Nowadays, C and Ku bands used for fixed SATCOM systems are totally congested. However, the demand of the end users for high data rate multimedia services is increasing. Consequently, the use of higher frequency bands (Ka: 20 GHz and Q/V 40/50 GHz) is under investigation. For frequencies higher than 5 GHz, radiowave propagation is strongly affected by tropospheric attenuation. Among the different contributors, rain is the most significant. To compensate the deterioration of the propagation channel, Fade Mitigation Techniques (FMT) are used. The lack of experimental data needed to optimize the real-time control loops of FMT leads tothe use of rain attenuation and total attenuation time series synthesizers. The manuscript is a compilation of five articles. The first contribution is dedicated to the temporal modelling of total impairments. The second article aims at providing significant improvements on the rain attenuation time series synthesizer recommended by ITU-R. The last three contributions are a critical analysis and a modelling of the variability observed on the 1st order statistics used to validate propagation channel models. The variance of the statistical estimator of the complementary cumulative distribution functions of rainfall rate and rain attenuation is highlighted. A worldwide model parameterized in compliance with propagation measurements is proposed. It allows the confidence intervals to be estimated and the risk on a required availability associated with a given propagation margin prediction to be quantified. This approach is extended to the variability of joint statistics. It allows the impact of site diversity techniques on system performances at small scale (few kms) and large scale (few hundred of kms) to be evaluated.

The diploma thesis describes the bootstrap method and its applications in the estimate accuracy statement, in the confidence intervals generation and in the testing of statistical hypotheses. Further the method of the discrete probability estimation of the categorical quantity is presented, making use the gradient of the quasi-norm hereof distribution. On concrete examples the bootstrap method is applied in the confidence intervals forming of the categorical quantity probability function. The diploma thesis was supported by the project of MŠMT of the Czech Republic no. 1M06047 "Centre for Quality and Reliability of Production", by the grant of Grant Agency of the Czech Republic (Czech Science Foundation) reg. no. 103/08/1658 "Advanced optimum design of composed concrete structures" and by the research plan of MŠMT of the Czech Republic no. MSM0021630519 "Progressive reliable and durable structures".

The diploma thesis describes the bootstrap method and its applications in the confidence intervals generation, in the testing of statistical hypotheses and in the regression analysis. We present the confidence interval for individual value. Further the method of discrete probability estimation of the categorical quantity is presented, making use the gradient and the line estimate.

Die Kapitel 1 bis 6 im ersten Teil dieses Skriptes beruhen auf einer Vorlesung Ökonometrie I, die zuletzt im WS 2001/02 gehalten wurde, die Kapitel 7 bis 16 beruhen auf einer Vorlesung Ökonometrie II, die zuletzt im SS 2006 gehalten wurde. Das achte Kapitel enthält eine komprimierte Zusammenfassung der Ergebnisse aus dem Teil Ökonometrie I.

Supervising students at a distance presents numerous social, mental, professional, and individual challenges on the student- supervisor relationship, and on the substance, progress, and conveyance. From the literature review, several tools and technologies are developed to improve academic quality; however, most of these tools and technologies focus on journal articles’ quality rather than student/supervisor relationships. This study aims to develop an academic rating index (ARI) that will show a supervisor’s review by students and provide an interactive forum. The application will serve as an academic supervision teaching-level index that provides an aggregated measure of supervisors’ past and current impact. Thus, the ARI aims to aggregate all academic supervisor ratings and the number of ratings that they received in the entire academic career to complement their citation index. The study will use quantitative coding and programming tools to ensure a good quality system in the development phase. The application and findings of the study contribute to academic service quality. / Operations Management / M. Tech. (Information Technology)

Classical and Bayesian methods for interval estimation of the ratio of two independent Poisson rates are examined and compared in terms of their exact coverage properties. Two methods to determine sampling effort requirements are derived.

This thesis is a case study in collaboration with the company Getswish AB. GetswishAB provides the mobile application and payment service Swish with the purpose ofdelivering smooth money transfers for individuals and companies in Sweden. About80 percent of the Swedish population are connected to Swish, and the majority seethe service as an apparent part of everyday life. This work studies a small part of alltransactions that take place daily between individuals and companies. Specifically, thispaper examines which factors affect the Swish transaction amount (TA) to companieswithin five different industries. The five industries studied are: Sports, leisure,and entertainment activities; Restaurant, catering, and bar activities; Retail trade,except for motor vehicles and motorcycles; Trade and repair of motor vehicles andmotorcycles; and Telecommunications. In combination with descriptive analysis andseasonality studies, a multiple linear regression model is used to evaluate patternsin the amount transferred to companies within the various industries. The responsevariable is the daily aggregated TA and the seven responding regressors examined are:i) The number of employees of the company, ii) The revenue of the company, iii) Thedate for registration to Swish service for companies, iv) The age of the customers, v) Thegender of the customers, vi) The number of transactions, and vii) The transaction date.The estimated parameters for each regressor are studied to evaluate correlations withthe TA. This thesis states that it is possible to construct a model from the regressorsanalyzed, which can predict the amount with an explanation degree of above 85% forfour of the five industries. The model constructed for the motor vehicle industry nevergives satisfactory results and must be further investigated to conclude. / Detta examensarbete är en fallstudie i samarbete med företaget GetSwish AB.GetSwish AB tillhandahåller mobilapplikationen och betaltjänsten Swish, vars syfteär att leverera smidig pengaöverföring för privatpersoner och företag i Sverige. Idagär cirka 80 procent av Sveriges befolkning anslutna till Swish och majoriteten sertjänsten som en självklar del av vardagen. Detta arbete kommer dock endast fokuserapå en liten del av alla transaktioner som dagligen sker mellan privatpersoner ochföretag. Specifikt undersöker denna rapport vilka faktorer som påverkar Swishstransaktionsbelopp till företag inom fem olika branscher. De fem branschernasom studeras är: Sport-, fritids- och nöjesverksamhet; Restaurang-, catering ochbarverksamhet; Detaljhandel utom med motorfordon och motorcyklar; Handelsamt reparation av motorfordon och motorcyklar; och Telekommunikation. Ikombination med en deskriptiv analys och säsongsstudier skapades en multipel linjärregressionsmodell för att utvärdera mönster i transaktionsbeloppet från kund tillföretag inom de olika branscherna. Responsvariablen är det dagliga aggregeradebeloppet och de förklarande variablerna som undersöktes var: antalet anställda,omsättning, datum för registrering till Swish för företag, kundernas ålder och könsamt antal transaktioner och transaktionsdatum. De skattade parametrarna förvarje regressor studerades för att utvärdera magnitud samt positiva eller negativakorrelationer med beloppet. Denna rapport visar att det är möjligt att konstrueraen modell från de analyserade regressorerna som kan förutsäga beloppet med enförklaringsgrad på över 85% för fyra av de fem branscherna och kan användas föratt förutspå beloppen på de dagliga transaktionerna. Modellen som konstruerats förfordonsindustrin gav aldrig tillfredsställande resultat och bör undersökas vidare innanslutsatser dras.