Zugl.: Bern, Univ., Diss., 2005

Orientador: Carlos Lenz César / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Física Gleb Wataghin / Made available in DSpace on 2018-09-01T14:53:04Z (GMT). No. of bitstreams: 1 Camacho_LudwingFerneyMarenco_M.pdf: 18964058 bytes, checksum: fa65aaa210a9f9f4dbd93261b64da143 (MD5) Previous issue date: 2017 / Resumo: Apresenta-se um novo método efetivo para analisar um sistema de Deputados usando o formalismo da teoria de redes. Construiu-se uma matriz com os resultados anuais da votação nominal da Câmara dos Deputados do Brasil desde 2007 até 2015. Através da medida do coeficiente de correlação entre os conjuntos anuais de votação nominal, calculou-se uma rede de Deputados. Encontrando a Árvore Geradora Mínima da rede de Deputados características generais do sistema podem visualiza-se. Especificamente, expõe-se a postura de concordância - oposição, as conexões individuais entre os Deputados, a fidelidade partidária e uma nova maneira de observar os projetos de lei aprovados ou rejeitados, assim como sua evolução no tempo. Devido ao bom comportamento de correlação observado entre os Deputados, prova-se que cinco ou seis partidos políticos são suficientes para capturar toda a diversidade política existente na Câmara dos Deputados do Brasil. Além disso, propõe-se que a distribuição de probabilidade dos valores de correlação da Câmara dos Deputados do Brasil é uma combinação de distribuições logísticas. Enuncia-se também, um novo método de ordenar matrizes de correlação baseado no resultado da Árvore Geradora Mínima / Abstract: A new effective method for analysing a Representatives¿ system from the network formalism is presented. A matrix with the annual results of roll - call vote of the Brazilian House of Representatives from 2007 to 2015 was constructed. By measuring the correlation coefficient between each pair of annual roll - call vote sets a Representatives¿ network was computed. For extracting the Minimal Spanning Tree of the Representatives' network general features of this system arises. Specifically, the concordance - opposition stance, the individual connections among Representatives, the partisan fidelity and a new way to identify the approved and disapproved draft bills, as well as, its time evolution are disclosed. A well-define correlation behaviour among Representatives is observed, in fact, we prove that five or six political parties are sufficient to encapsulate all political diversity in the Brazilian House of Representatives. In addition, we propose that the probability distribution of correlation values in the Brazilian House of Representatives is a combination of logistic distributions. Besides that, a new method for re-ordering correlation matrices based on the result of the Minimal Spanning Tree is enunciated / Mestrado / Física / Mestre em Física / 1490097/2015 / CAPES

Component failures can result in catastrophic behaviors in safety critical embedded systems, sometimes resulting in loss of life. Component failures can be treated as off nominal behaviors (ONBs) with respect to the components and sub systems involved in an embedded system. A lot of research is being carried out to tackle the problem of ONBs. These approaches are mainly focused on the states (i.e., desired and undesired states of a system at a given point of time to detect ONBs). In this paper, an approach is discussed to detect component failures and critical components of an embedded system. The approach is based on fault tree analysis (FTA), applied to the requirements specification of embedded systems at design time to find out the relationship between individual component failures and overall system failure. FTA helps in determining both qualitative and quantitative relationship between component failures and system failure. Analyzing the system at design time helps in detecting component failures and critical components and helps in devising strategies to mitigate component failures at design time and improve overall safety and reliability of a system.

Increasing societal demand for automation has led to considerable efforts to control large-scale complex systems, especially in the area of autonomous intelligent control methods. The control system of a large-scale complex system needs to satisfy four system level requirements: robustness, flexibility, reusability, and scalability. Corresponding to the four system level requirements, there arise four major challenges. First, it is difficult to get accurate and complete information. Second, the system may be physically highly distributed. Third, the system evolves very quickly. Fourth, emergent global behaviors of the system can be caused by small disturbances at the component level. The Multi-Agent Based Control (MABC) method as an implementation of distributed intelligent control has been the focus of research since the 1970s, in an effort to solve the above-mentioned problems in controlling large-scale complex systems. However, to the author's best knowledge, all MABC systems for large-scale complex systems with significant uncertainties are problem-specific and thus difficult to extend to other domains or larger systems. This situation is partly due to the control architecture of multiple agents being determined by agent to agent coupling and interaction mechanisms. Therefore, the research objective of this dissertation is to develop a comprehensive, generalized framework for the control system design of general large-scale complex systems with significant uncertainties, with the focus on distributed control architecture design and distributed inference engine design. A Hybrid Multi-Agent Based Control (HyMABC) architecture is proposed by combining hierarchical control architecture and module control architecture with logical replication rings. First, it decomposes a complex system hierarchically; second, it combines the components in the same level as a module, and then designs common interfaces for all of the components in the same module; third, replications are made for critical agents and are organized into logical rings. This architecture maintains clear guidelines for complexity decomposition and also increases the robustness of the whole system. Multiple Sectioned Dynamic Bayesian Networks (MSDBNs) as a distributed dynamic probabilistic inference engine, can be embedded into the control architecture to handle uncertainties of general large-scale complex systems. MSDBNs decomposes a large knowledge-based system into many agents. Each agent holds its partial perspective of a large problem domain by representing its knowledge as a Dynamic Bayesian Network (DBN). Each agent accesses local evidence from its corresponding local sensors and communicates with other agents through finite message passing. If the distributed agents can be organized into a tree structure, satisfying the running intersection property and d-sep set requirements, globally consistent inferences are achievable in a distributed way. By using different frequencies for local DBN agent belief updating and global system belief updating, it balances the communication cost with the global consistency of inferences. In this dissertation, a fully factorized Boyen-Koller (BK) approximation algorithm is used for local DBN agent belief updating, and the static Junction Forest Linkage Tree (JFLT) algorithm is used for global system belief updating. MSDBNs assume a static structure and a stable communication network for the whole system. However, for a real system, sub-Bayesian networks as nodes could be lost, and the communication network could be shut down due to partial damage in the system. Therefore, on-line and automatic MSDBNs structure formation is necessary for making robust state estimations and increasing survivability of the whole system. A Distributed Spanning Tree Optimization (DSTO) algorithm, a Distributed D-Sep Set Satisfaction (DDSSS) algorithm, and a Distributed Running Intersection Satisfaction (DRIS) algorithm are proposed in this dissertation. Combining these three distributed algorithms and a Distributed Belief Propagation (DBP) algorithm in MSDBNs makes state estimations robust to partial damage in the whole system. Combining the distributed control architecture design and the distributed inference engine design leads to a process of control system design for a general large-scale complex system. As applications of the proposed methodology, the control system design of a simplified ship chilled water system and a notional ship chilled water system have been demonstrated step by step. Simulation results not only show that the proposed methodology gives a clear guideline for control system design for general large-scale complex systems with dynamic and uncertain environment, but also indicate that the combination of MSDBNs and HyMABC can provide excellent performance for controlling general large-scale complex systems.

This thesis mainly focuses on algorithmic and combinatorial questions related to some geometric problems on graphs. In the last part of this thesis, a graph coloring problem is also discussed. Boxicity and Cubicity: These are graph parameters dealing with geomet-ric representations of graphs in higher dimensions. Both these parameters are known to be NP-Hard to compute in general and are even hard to approximate within an O(n1− ) factor for any > 0, under standard complexity theoretic assumptions. We studied algorithmic questions for these problems, for certain graph classes, to yield efficient algorithms or approximations. Our results include a polynomial time constant factor approximation algorithm for computing the cubicity of trees and a polynomial time constant (≤ 2.5) factor approximation algorithm for computing the boxicity of circular arc graphs. As far as we know, there were no constant factor approximation algorithms known previously, for computing boxicity or cubicity of any well known graph class for which the respective parameter value is unbounded. We also obtained parameterized approximation algorithms for boxicity with various edit distance parameters. An o(n) factor approximation algorithm for computing the boxicity and cubicity of general graphs also evolved as an interesting corollary of one of these parameterized algorithms. This seems to be the first sub-linear factor approximation algorithm known for computing the boxicity and cubicity of general graphs. Planar grid-drawings of outerplanar graphs: A graph is outerplanar, if it has a planar embedding with all its vertices lying on the outer face. We give an efficient algorithm to 2-vertex-connect any connected outerplanar graph G by adding more edges to it, in order to obtain a supergraph of G such that the resultant graph is still outerplanar and its pathwidth is within a constant times the pathwidth of G. This algorithm leads to a constant factor approximation algorithm for computing minimum height planar straight line grid-drawings of outerplanar graphs, extending the existing algorithm known for 2-vertex connected outerplanar graphs. n−1 3 Maximum matchings in triangle distance Delaunay graphs: Delau-nay graphs of point sets are well studied in Computational Geometry. Instead of the Euclidean metric, if the Delaunay graph is defined with respect to the convex distance function defined by an equilateral triangle, it is called a Trian-gle Distance Delaunay graph. TD-Delaunay graphs are known to be equivalent to geometric spanners called half-Θ6 graphs. It is known that classical Delaunay graphs of point sets always contain a near perfect matching, for non-degenerate point sets. We show that Triangle Distance Delaunay graphs of a set of n points in general position will always l m contain a matching of size and this bound is tight. We also show that Θ6 graphs, a class of supergraphs of half-Θ6 graphs, can have at most 5n − 11 edges, for point sets in general position. Heterochromatic Paths in Edge Colored Graphs: Conditions on the coloring to guarantee the existence of long heterochromatic paths in edge col-ored graphs is a well explored problem in literature. The objective here is to obtain a good lower bound for λ(G) - the length of a maximum heterochro-matic path in an edge-colored graph G, in terms of ϑ(G) - the minimum color degree of G under the given coloring. There are graph families for which λ(G) = ϑ(G) − 1 under certain colorings, and it is conjectured that ϑ(G) − 1 is a tight lower bound for λ(G). We show that if G has girth is at least 4 log2(ϑ(G))+2, then λ(G) ≥ ϑ(G)− 2. It is also proved that a weaker requirement that G just does not contain four-cycles is enough to guarantee that λ(G) is at least ϑ(G) −o(ϑ(G)). Other special cases considered include lower bounds for λ(G) in edge colored bipartite graphs, triangle-free graphs and graphs without heterochromatic triangles.

Indiana University-Purdue University Indianapolis (IUPUI) / Symptoms of post-traumatic stress disorder (PTSD) are a common comorbidity in veterans seeking treatment of chronic musculoskeletal pain (CMP). However, little is known regarding the mutual influence of PTSD and CMP in this population. Using cross-sectional and longitudinal data from a randomized clinical trial evaluating a stepped care intervention for CMP in Iraq/Afghanistan veterans (ESCAPE), this dissertation examined the relationships between PTSD and CMP along with other factors including depression, anxiety, catastrophizing and health-related quality of life. The Classification and Regression Tree (CART) analysis was conducted to identify key factors associated with baseline PTSD besides CMP severity. A series of statistical analyses including logistical regression analysis, mixed model repeated measure analysis, confirmatory factor analysis and cross-lagged panel analysis via structural equation modeling were conducted to test five competing models of PTSD symptom clusters, and to examine the mutual influences of PTSD symptom clusters and CMP outcomes. Results showed baseline pain intensity and pain disability predicted PTSD at 9 months. And baseline PTSD predicted improvement of pain disability at 9 months. Moreover, direct relationships were found between PTSD and the disability component of CMP, and indirect relationships were found between PTSD, CMP and CMP components (intensity and disability) mediated by depression, anxiety and pain catastrophizing. Finally, the coexistence of PTSD and more severe pain was associated with worse SF-36 Physical Component Summary (PCS) and Mental Component Summary (MCS) scores. Together these findings provided empirical support for the mutual maintenance theory.

Indiana University-Purdue University Indianapolis (IUPUI) / Magnetic resonance (MR) spectroscopy is a neuroimaging technique. It is widely used to quantify the concentration of important metabolites in a brain tissue. Imbalance in concentration of brain metabolites has been found to be associated with development of neurological impairment. There has been increasing trend of using MR spectroscopy as a diagnosis tool for neurological disorders. We established statistical methodology to analyze data obtained from the MR spectroscopy in the context of the HIV associated neurological disorder. First, we have developed novel methodology to study the association of marker of neurological disorder with MR spectrum from brain and how this association evolves with time. The entire problem fits into the framework of scalar-on-function regression model with individual spectrum being the functional predictor. We have extended one of the existing cross-sectional scalar-on-function regression techniques to longitudinal set-up. Advantage of proposed method includes: 1) ability to model flexible time-varying association between response and functional predictor and (2) ability to incorporate prior information. Second part of research attempts to study the influence of the clinical and demographic factors on the progression of brain metabolites over time. In order to understand the influence of these factors in fully non-parametric way, we proposed LongCART algorithm to construct regression tree with longitudinal data. Such a regression tree helps to identify smaller subpopulations (characterized by baseline factors) with differential longitudinal profile and hence helps us to identify influence of baseline factors. Advantage of LongCART algorithm includes: (1) it maintains of type-I error in determining best split, (2) substantially reduces computation time and (2) applicable even observations are taken at subject-specific time-points. Finally, we carried out an in-depth analysis of longitudinal changes in the brain metabolite concentrations in three brain regions, namely, white matter, gray matter and basal ganglia in chronically infected HIV patients enrolled in HIV Neuroimaging Consortium study. We studied the influence of important baseline factors (clinical and demographic) on these longitudinal profiles of brain metabolites using LongCART algorithm in order to identify subgroup of patients at higher risk of neurological impairment. / Partial research support was provided by the National Institutes of Health grants U01-MH083545, R01-CA126205 and U01-CA086368