The realm of manufacturing is replete with instances of uncertainties in job processing times, machine statuses (up or down), demand fluctuations, due dates of jobs and job priorities. These uncertainties stem from the inability to gather accurate information about the various parameters (e.g., processing times, product demand) or to gain complete control over the different manufacturing processes that are involved. Hence, it becomes imperative on the part of a production manager to take into account the impact of uncertainty on the performance of the system on hand. This uncertainty, or variability, is of considerable importance in the scheduling of production tasks. A scheduling problem is primarily to allocate the jobs and determine their start times for processing on a single or multiple machines (resources) for the objective of optimizing a performance measure of interest. If the problem parameters of interest e.g., processing times, due dates, release dates are deterministic, the scheduling problem is relatively easier to solve than for the case when the information is uncertain about these parameters. From a practical point of view, the knowledge of these parameters is, most often than not, uncertain and it becomes necessary to develop a stochastic model of the scheduling system in order to analyze its performance. Investigation of the stochastic scheduling literature reveals that the preponderance of the work reported has dealt with optimizing the expected value of the performance measure. By focusing only on the expected value and ignoring the variance of the measure used, the scheduling problem becomes purely deterministic and the significant ramifications of schedule variability are essentially neglected. In many a practical cases, a scheduler would prefer to have a stable schedule with minimum variance than a schedule that has lower expected value and unknown (and possibly high) variance. Hence, it becomes apparent to define schedule efficiencies in terms of both the expectation and variance of the performance measure used. It could be easily perceived that the primary reasons for neglecting variance are the complications arising out of variance considerations and the difficulty of solving the underlying optimization problem. Moreover, research work to develop closed-form expressions or methodologies to determine the variance of the performance measures is very limited in the literature. However, conceivably, such an evaluation or analysis can only help a scheduler in making appropriate decisions in the face of uncertain environment. Additionally, these expressions and methodologies can be incorporated in various scheduling algorithms to determine efficient schedules in terms of both the expectation and variance. In our research work, we develop such analytic expressions and methodologies to determine the expectation and variance of different performance measures of a schedule. The performance measures considered are both completion time and tardiness based measures. The scheduling environments considered in our analysis involve a single machine, parallel machines, flow shops and job shops. The processing times of the jobs are modeled as independent random variables with known probability density functions. With the schedule given a priori, we develop closed-form expressions or devise methodologies to determine the expectation and variance of the performance measures of interest. We also describe in detail the approaches that we used for the various scheduling environments mentioned earlier. The developed expressions and methodologies were programmed in MATLAB R12 and illustrated with a few sample problems. It is our understanding that knowing the variance of the performance measure in addition to its expected value would aid in determining the appropriate schedule to use in practice. A scheduler would be in a better position to base his/her decisions having known the variability of the schedules and, consequently, can strike a balance between the expected value and variance. / Master of Science

Les systèmes mécaniques soumis et excités par vibrations sont les candidats naturels à être modélisé par des systèmes linéaires invariables dans le temps. La localisation de dommages utilisant les paramètres modaux évalués à partir de données de vibration ambiantes mesurées grâce à de capteurs est possible notamment par l'approche nommée Stochastic Dynamic Damage Location Vector (SDDLV), où l'emplacement des dommages est empiriquement relié aux positions où le stress est proche de zéro. La première contribution dans cette thèse montre comment l'incertitude sur les paramètres du système d'état peut être utilisée pour déduire des bornes d'incertitude sur les résidus de localisation de dommages, ceci afin de décider de l'emplacement de dommage utilisant un test d'hypothèse. Dans la deuxième contribution, la méthode de localisation de dommages est étendue pour être robuste au choix des variables de Laplace utilisées dans cette méthode. Ceci est obtenue en agrégeant statistiquement les résultats à valeurs différentes dans le domaine de Laplace. L'influence Line Damage Location (ILDL) est une approche complémentaire du SDDLV où l'angle entre les sous-espaces principaux est calculé et les dommages sont empiriquement localisés aux points près du zéro. L'approche développée pour la SDDLV est étendue à cette nouvelle approche, l'ILDL. Les méthodes proposées sont validées et appliquées avec succès pour la localisation de dommages dans des structures civiles. / Mechanical systems under vibration excitation are prime candidate for being modeled by linear time invariant systems. Damage localization using both finite element information and modal parameters estimated from ambient vibration data collected from sensors is possible by the Stochastic Dynamic Damage Location Vector (SDDLV) approach, where the damage location is empirically related to positions where the stress is close to zero. The first contribution in this thesis shows how the uncertainty in the estimates of the state space system can be used to derive uncertainty bounds on the damage localization residuals to decide about the damage location with a hypothesis test using one chosen Laplace value. In the second contribution, the damage localization method is extended with a statistical framework and robustness of the localization information is achieved by aggregating results at different values in the Laplace domain. The Influence Line Damage Location (ILDL) is a complementary approach of the SDDLV where the subspace angle is computed and damage is empirically located at points near zero. The last contribution describes how robustness of the localization information is achieved by aggregating results at different values in the Laplace domain based on the previous two contributions. The proposed methods are validated and successfully applied to damage localization of several applications in civil structures.

Orientador: Carlos Roberto Padovani / Banca: Adriano Wagner Ballarin / Banca: José Carlos Martinez / Banca: Jacinta Ludovico Zamboti / Banca: Marie Oshiiwa / Resumo: Este trabalho foi desenvolvido com os objetivos de avaliar a divergência genética de 12 populações de girassol do Banco de Germoplasma da EMBRAPA /Soja de Londrina por meio de técnicas multivariadas; divulgar tópicos recentes e interessantes das técnicas multivariadas que não são explorados nos trabalhos científicos de melhoramento de plantas e orientar a escolha de populações para cruzamentos nos programas de melhoramento genético da cultura de girassol. O modelo experimental constitui-se de delineamento bloco casualizado envolvendo 12 variedades de girassol avaliadas sob cinco caracteres morfoagronômicos. Por meio da análise univariada foi verificada diferença significativa (p<0,05) dos tratamentos para todos caracteres. A aplicação dos componentes principais permitiu a redução bidimensional, com a explicação de 82,5% da variação total. O número de componentes foi avaliado pelo critério de Kaiser e critério Scree-test. A visualização da divergência genética proporcionada pelos escores das duas primeiras variáveis canônicas, evidenciaram grupos geneticamente diferentes. Ambas técnicas apontaram concordância nos resultados. Com base nas estimativas da distância Mahalanobis e distância euclideana foi realizada a análise de agrupamento adotando-se três algoritmos hierárquicos. Para determinar o número de grupos adotou-se o dendrograma, a análise do nível de fusão e a análise do comportamento de similaridade. Para validação utilizou-se o critério de Wilks dentro de cada grupo e gráficos multivariados auxiliaram na interpretação dos resultados. Pode-se concluir pela existência da divergência genética, detectando-se quatro grupos geneticamente diferentes e caracterizado pelos escores médios. / Abstract: The objective of this work was to evaluate genetic divergence in 12 sunflower populations from EMBRAPA/ Londrina Soybean Germplasm Bank, using multivariate techniques, to discuss recent and interesting topics related to the multivariate techniques donþt found in plant improvement scientific papers, and to offer guidelines on how to choose populations for sunflower genetic improvement crossing programs. The experiment included a totally block casualized design, with twelve sunflower varieties, evaluated according to 5 morphoagronomics traits. The univariate analysis showed a significant difference (p<0,05) among treatments for all the traits. Application of main components allowed for a bi-dimensional reduction, with 82,5% of the total variation. The number of components were evaluated by the Kaiser and Scree-test criteria. Genetic divergence visualization provided by the two first canonical variables showed genetically different groups. Both techniques showed the same results. Based on Mahalanobis and Euclidean distance estimates, a clustering analysis was carried out using three hierarchicals algorithms. A dendrogram, a fusion level analysis and a similarity behavior analysis were conducted to determine the number of groups. Validation used the Wilks criteria inside each group, while multivariate graphs helped with data interpretation. Results from this study showed genetic divergence in four groups characterized by average/mean scores. / Doutor

As avaliações sensoriais tomam cada vez mais sua posição de importância dentro dos centros produtores e vendedores de alimentos e de outros produtos. Nestes, o objetivo final dos trabalhos realizados nas áreas de desenvolvimento, produção e `marketing\' e o consumidor, cuja avaliação se baseia, principalmente, na aceitabilidade e custos dos produtos. Nesses experimentos, uma serie de tratamentos e dada para cada provador, e um problema relevante e que a variável resposta dependa não só do tratamento aplicado atualmente, mas também do anterior seguido a ele, chamados de efeitos residuais. Visando uma melhor qualidade do produto, analises cada vez mais rigorosas são exigidas. Assim, um método frequentemente utilizado e o da analise descritiva, que tem por objetivo descrever e avaliar a intensidade dos atributos sensoriais dos produtos avaliados, orientando eventuais modificações das características das mesmas a m de atender as exigências do consumidor. Realizada por pessoas treinadas, com habilidade de discriminar, recebendo o nome de analise descritiva quantitativa (ADQ). Consequentemente, dadas as limitações quanto ao numero de provas sucessivas de degustação e presença frequente de efeitos residuais, o planejamento e analise dos experimentos para ADQ adquirem importância fundamental. Assim, de modo a resolver o problema apresentado, Williams (1949) apresentou os delineamentos quadrados latinos balanceados para vizinhança que, de forma geral, garantem que os efeitos residuais dos tratamentos não exerçam influência sobre a comparação dos efeitos dos tratamentos. Métodos adequados de construção, aleatorizacão e analise, utilizando o método ADQ de tais delineamentos são descritos e adaptados para o problema. São apresentados, analisados e discutidos, ainda, os resultados de um experimento de analise sensorial de diferentes cachaças, planejado e conduzido pela autora. Assim, com os resultados obtidos, concluiu-se que, para o planejamento de ensaios para a análise descritiva quantitativa (ADQ), os quadrados latinos balanceados para vizinhança, com a última coluna repetida, são uma alternativa importante / The sensory evaluations are increasingly taking its position of importance within the centers producers and sellers of food and other products. In these, the ultimate goal of the work in the areas of development, production and \'marketing\' is the consumer, whose evaluation is based mainly on the acceptability and cost of products. In these experiments, a series of treatments is given to each panelist, and a major problem is that the response depends not only on the treatment currently applied, but on the former followed by him. For a better quality product, analyzes increasingly stringent are required. Therefore, a method often used is descriptive analysis, which aims to describe and evaluate the intensity of sensory attributes of the products evaluated, guiding future modications of the same characteristics in order to meet consumer demands.Performed by trained people, with ability to discriminate, receiving the name of quantitative descriptive analysis (QDA). Therefore, given the limitations on the number of successive tasting trials and frequent presence of residual eects, planning and analysing the experiments for QDA are fundamentaly important. Thus, in order to solve the problem presented, Williams (1949) presented the Latin square design balanced for neighborhood that, in general, ensuring that the residual eects of the treatments do not in uence the comparison of treatment eects. Appropriate methods of construction, randomization and analysis, using the method of QDA such designs are described and adapted to the problem. Are presented, analyzed and discussed, yet, the results of an experiment of sensory analysis of dierent brandy, planned and conducted by the author. So with these results, we concluded that, for the planning of tests to quantitative descriptive analysis (QDA), the Latin squares balanced for neighborhoods, and repeated the last column, are an important alternative.

This study sought to determine the effect upon Tukey's Honestly Significant Difference (HSD) statistic of concurrently violating the assumptions of homogeneity of variance and equal sample sizes. Two forms for the unequal sample size problem were investigated. Kramer's form and the harmonic mean approach were the two unequal sample size procedures studied. The study employed a Monte Carlo simulation procedure which varied sample sizes with a heterogeneity of variance condition. Four thousand experiments were generated. Findings of this study were based upon the empirically obtained significance levels. Five conclusions were reached in this study. The first conclusion was that for the conditions of this study the Kramer form of the HSD statistic is not robust at the .05 or .01 nominal level of significance. A second conclusion was that the harmonic mean form of the HSD statistic is not robust at the .05 and .01 nominal level of significance. A general conclusion reached from all the findings formed the third conclusion. It was that the Kramer form of the HSD test is the preferred procedure under combined assumption violations of variance heterogeneity and unequal sample sizes. Two additional conclusions are based on related findings. The fourth conclusion was that for the combined assumption violations in this study, the actual significance levels (probability levels) were less-than the nominal significance levels when the magnitude of the unequal variances were positively related to the magnitude of the unequal sample sizes. The fifth and last conclusion was that for the concurrent assumption violation of variance heterogeneity and unequal sample sizes, the actual significance levels significantly exceed the nominal significance levels when the magnitude of the unequal variances are negatively related to the magnitude of the unequal sample sizes.

This master's thesis deals with the cost planning and cost control in construction company specializing mainly in road construction works. The theoretical part concerns first with the description of cost planning process and its specifics in analysed company. The objective of cost control is then to carry out the variance analysis by selected performances and to give further recommendations for adjusting of standards of direct costs, based on achieved results from undertaken analysis. The last part deals with the design of appropriate method for cost control procedure, based on the Pareto principle and setting of tolerance intervals for cost amount. Excess of these intervals requires additional control of these costs and explanation of reasons, why this increased variance exists.

Brain Computer Interface (BCI) is a direct communication channel between brain and computer. It allows the users to control the environment without the need to control muscle activity [1-2]. P300-Speller is a well known and widely used BCI system that was developed by Farwell and Donchin in 1988 [3]. The accuracy level of the P300-BCI Speller as measured by the percent of communicated characters correctly identified by the system depends on the ability to detect the P300 event related potential (ERP) component among the ongoing electroencephalography (EEG) signal. Different techniques have been tested to reduce the number of trials needed to be averaged together to allow the reliable detection of the P300 response. Some of them have achieved high accuracies in multiple-trial P300 response detection. However the accuracy of single trial P300 response detection still needs to be improved. In this research, two single trial P300 response classification methods were designed. One is based on independent component analysis (ICA) with blind tracking and the other is based on variance analysis. The purpose of both methods is to detect a chosen character in real-time in the P300-BCI speller. The experimental results demonstrate that the proposed methods dramatically reduce the signal processing time, improve the data communication rate, and achieve overall accuracy of 79.1% for ICA based method and 84.8% for variance analysis based method in single trial P300 response classification task. Both methods showed better performance than that of the single trial stepwise linear discriminant analysis (SWLDA), which has been considered as the most accurate and practical technique working with P300-BCI Speller.

Mechanical systems under vibration excitation are prime candidate for being modeled by linear time invariant systems. Damage localization using both finite element information and modal parameters estimated from ambient vibration data collected from sensors is possible by the Stochastic Dynamic Damage Location Vector (SDDLV) approach, where the damage location is empirically related to positions where the stress is close to zero. The first contribution in this thesis shows how the uncertainty in the estimates of the state space system can be used to derive uncertainty bounds on the damage localization residuals to decide about the damage location with a hypothesis test using one chosen Laplace value. In the second contribution, the damage localization method is extended with a statistical framework and robustness of the localization information is achieved by aggregating results at different values in the Laplace domain. The Influence Line Damage Location (ILDL) is a complementary approach of the SDDLV where the subspace angle is computed and damage is empirically located at points near zero. The last contribution describes how robustness of the localization information is achieved by aggregating results at different values in the Laplace domain based on the previous two contributions. The proposed methods are validated and successfully applied to damage localization of several applications in civil structures.

Στη διπλωματική εργασία περιγράφονται και αναπτύσονται δύο στατιστικές μέθοδοι ανάλυσης δεδομένων, Γραμμική Παλινδρόμηση με ποιοτικές μεταβλητές και Ανάλυση διασποράς με έναν και ακολούθως με δύο παράγοντες. Στη συνέχεια οι παραπάνω μέθοδοι εφαρμόζονται σε πραγματικά δεδομένα που προέρχονται από δείγματα νερού ενός κολπίσκου και μελετάται ο βαθμός επίδρασης 3 διαφορετικών βροχοπτώσεων στο pH του νερού. Η εφαρμογή των μεθόδων γίνεται με τη χρήση του στατιστικού πακέτου SPSS. / The thesis described and developed the data analysis of two statistical methods, Linear Regression with qualitative variables and ANOVA one-way analysis, then ANOVA two-way. Moreover, the former methods are applied to real data from gulf water samples and studied the degree of influence of 3 different rainfalls in the water pH. The application of the methods is done using the SPSS statistical package.

Made available in DSpace on 2014-06-11T19:28:58Z (GMT). No. of bitstreams: 0 Previous issue date: 2006-06-23Bitstream added on 2014-06-13T19:16:56Z : No. of bitstreams: 1 landim_kt_me_sjc.pdf: 2945410 bytes, checksum: dc611c58884c00b0e53c9d1dcae05bbe (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Este estudo avaliou a influência da ciclagem mecânica na resistência de união ao cisalhamento entre cerâmicas infiltradas por vidro para infra-estrutura (In-Ceram Alumina - Vita Zahnfabrik e In-Ceram Zircônia - Vita Zahnfabrik) e uma cerâmica vítrea de recobrimento (VITA VM7 - Vita Zahnfabrik). Foram preparadas vinte e quatro amostras cilíndricas nas dimensões de 4mm de diâmetro por 5mm de altura para cada cerâmica de infra-estrutura. Posteriormente, a cerâmica de recobrimento estético foi aplicada, resultando em corpos-de-prova com 4mm de diâmetro e 9mm de altura, os quais foram divididos em 4 grupos: ICA; ICAM; ICZ e ICZM. Os grupos ICAM e ICZM receberam ciclagem mecânica, com força de 50N, freqüência de 1Hz, durante 20000 ciclos. O ensaio de cisalhamento foi realizado em máquina de ensaio universal (modelo DL - 1000, EMIC - Equipamentos e Sistemas LTDA., São José dos Pinhais - PR - Brasil) com velocidade de 0,5mm/min e as amostras carregadas até a fratura. As interfaces das amostras pós-fratura foram analisadas em estereomicroscópio (20x) e microscopia eletrônica de varredura. As médias e desvios padrão obtidos foram: ICA (30,04 l 11,74); ICAM (32,17 l 9,59); ICZ (44,33 l 11,47); ICZM (43,52 l 8,33). Os dados obtidos (MPa) foram analisados estatisticamente por meio de análise de variância (ANOVA) dois fatores e teste de Tukey (P<0,05). Os resultados mostraram diferença estatisticamente significante entre os grupos In-Ceram Alumina e In-Ceram Zircônia, porém a ciclagem mecânica não influenciou na resistência de união entre as cerâmicas de infra-estrutura e de recobrimento estético estudadas / This study evaluated the influence of cyclic loading on shear bond strength between two glass-infiltrated ceramics for substructure (In-Ceram Alumina - Vita Zahnfabrik and In-Ceram Zirconia - Vita Zahnfabrik) and one glass veneer ceramic (VITA VM7 - Vita Zahnfabrik). Twenty four cylindrical samples with 4mm diameter per 5mm high was to prepare for each ceramics for substructure. Subsequently, the venner ceramic was applied to ceramic substructure, resulting in 4mm diameter per 9mm high specimens. They were divided in four groups ICA; ICAM; ICZ and ICZM. The groups ICAM and ICZM where cyclic loadind from 50N, 1Hz during 20000 cycles. Shear bond testing was performed in a universal testing machine (DL - 1000 model, EMIC - Equipamentos e Sistemas LTDA., São José dos Pinhais - PR - Brasil), with crosshead speed of 0,5mm/min and the specimens were loaded until failure. The interfaces of representative fractured specimens of each group were examined with microscopy (20x) and scanning electron microscopy. The mean values and standard deviations were: ICA (30,04 l 11,74); ICAM: (32,17 l 9,59); ICZ: (44,33 l 11,47); ICZM: (43,52 l 8,33). Data for shear bond strength (MPa) where statistically analysed by variance analysis (ANOVA) two factors and Tukey's test (P<0,05). The results showed statistically significant differences between the groups In-Ceram Alumina and In-Ceram Zirconia, however the cyclic loading effect was not influenced on bond strength between ceramics for substructure and veneer ceramic studied