Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2017-11-13T14:25:31Z No. of bitstreams: 2 Dissertação - Victor Martin de Oliveira - 2017.pdf: 4224923 bytes, checksum: df22172ea97d67bc99001b28fa5e6c8a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-11-13T14:26:03Z (GMT) No. of bitstreams: 2 Dissertação - Victor Martin de Oliveira - 2017.pdf: 4224923 bytes, checksum: df22172ea97d67bc99001b28fa5e6c8a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-11-13T14:26:03Z (GMT). No. of bitstreams: 2 Dissertação - Victor Martin de Oliveira - 2017.pdf: 4224923 bytes, checksum: df22172ea97d67bc99001b28fa5e6c8a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-10-18 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / In the context of interactive art, which the spectators become interactors as well, technological development promotes new types of interaction and relations between the art and the human. The project “C³ – Cubos Interativos” (C³ project) rises in this context, created by Media Lab -- UFG with the philosophy of interpersonal and interactive relations, using art and technology. The project consists of three real cubes, which can be handled by users and produce feedback through light and sound effects. The users may communicate with one another and interact with the cubes in order to discover their behaviors and the possible reactions to the interactive activities. However, the cubes behaviors are created manually through the codification of a state machine, being a complex and time consuming task. On the other hand, the Interactive Evolutionary Computation (IEC) is an area of research that can be applied to the composition of artistic elements by using evolutionary algorithms and human interaction. One down point of the IEC is the human fatigue, what makes prohibitive the processing of many evolutionary cycles. Some techniques can be applied to avoid this problem, for example, the use of surrogate functions. This work aims to unite aspects of interactive art and interactive evolutionary computation, with the objective of providing a new way of creating behaviors that represents interesting and pleasant compositions to the C³ cubes. To achieve this goal, we propose the evolution of the C³ cubes state machines using IEC assisted by a surrogate function. A simulation environment for the C³ project was developed, in which the users can interact with virtual cubes and evaluate their behaviors, guiding the evolutionary approach. An experiment with the approach involving a group of users from UFG resulted in more complex and interesting C³ projects. / No contexto de arte interativa, em que o espectador se torna também um interator, avanços tecnológicos proporcionam novos tipos de interações e relações entre a arte e o ser humano. O projeto “C³ – Cubos Interativos” (projeto C³) surge neste contexto, criado no Media Lab -- UFG com a filosofia de relação interpessoal e interativa utilizando-se da arte e da tecnologia. Ele consiste de três cubos reais, os quais podem ser manipulados por usuários e que produzem um feedback através de efeitos luminosos e sonoros. Os usuários interagem entre si e com os cubos, a fim de descobrir seus comportamentos e as possíveis reações às atividades interativas. No entanto, a programação de comportamentos para os cubos é realizada manualmente através da codificação de uma máquina de estados, o que requer tempo e é uma tarefa complexa. Por outro lado, a computação evolutiva interativa (CEI) é uma área de pesquisa que pode ser empregada para composição de elementos artísticos pela utilização de algoritmos evolutivos e da interação humana. Uma desvantagem desta abordagem é a fadiga humana, impossibilitando assim a evolução de muitas gerações. Algumas técnicas podem ser utilizadas para contornar tal problema, como o uso de funções surrogate. Este trabalho tem por objetivo unir aspectos de arte interativa e computação evolutiva interativa, com o intuito de proporcionar uma nova forma de criação de comportamentos que caracterizem composições interessantes e agradáveis de forma automática, para os cubos do projeto C³. Para tanto, a abordagem proposta utiliza da CEI assistida por uma função surrogate, para a evolução das máquinas de estados presentes nos cubos C³. Também, é empregado um ambiente de simulação para o projeto C³, no qual usuários podem interagir com cubos virtuais e avaliar seus comportamentos, guiando o processo evolutivo. Um experimento foi realizado com um grupo de usuários da UFG, resultando em projetos C³ mais complexos e interessantes.

The focus of this dissertation is on improving decision-maker trade-offs and the development of a new constrained methodology for multiple response surface optimization. There are three key components of the research: development of the necessary conditions and assumptions associated with constrained multiple response surface optimization methodologies; development of a new constrained multiple response surface methodology; and demonstration of the new method. The necessary conditions for and assumptions associated with constrained multiple response surface optimization methods were identified and found to be less restrictive than requirements previously described in the literature. The conditions and assumptions required for a constrained method to find the most preferred non-dominated solution are to generate non-dominated solutions and to generate solutions consistent with decision-maker preferences among the response objectives. Additionally, if a Lagrangian constrained method is used, the preservation of convexity is required in order to be able to generate all non-dominated solutions. The conditions required for constrained methods are significantly fewer than those required for combined methods. Most of the existing constrained methodologies do not incorporate any provision for a decision-maker to explicitly determine the relative importance of the multiple objectives. Research into the larger area of multi-criteria decision-making identified the interactive surrogate worth trade-off algorithm as a potential methodology that would provide that capability in multiple response surface optimization problems. The ISWT algorithm uses an ε-constraint formulation to guarantee a non-dominated solution, and then interacts with the decision-maker after each iteration to determine the preference of the decision-maker in trading-off the value of the primary response for an increase in value of a secondary response. The current research modified the ISWT algorithm to develop a new constrained multiple response surface methodology that explicitly accounts for decision-maker preferences. The new Modified ISWT (MISWT) method maintains the essence of the original method while taking advantage of the specific properties of multiple response surface problems to simplify the application of the method. The MISWT is an accessible computer-based implementation of the ISWT. Five test problems from the multiple response surface optimization literature were used to demonstrate the new methodology. It was shown that this methodology can handle a variety of types and numbers of responses and independent variables. Furthermore, it was demonstrated that the methodology can be successful using a priori information from the decision-maker about bounds or targets or can use the extreme values obtained from the region of operability. In all cases, the methodology explicitly considered decision-maker preferences and provided non-dominated solutions. The contribution of this method is the removal of implicit assumptions and includes the decision-maker in explicit trade-offs among multiple objectives or responses.

This thesis deals with the application of optimisation based Validation and Verification (V&V) analysis on aerospace vehicles in order to determine their worst case performance metrics. To this end, three aerospace models relating to satellite and launcher vehicles provided by European Space Agency (ESA) on various projects are utilised. As a means to quicken the process of optimisation based V&V analysis, surrogate models are developed using polynomial chaos method. Surro- gate models provide a quick way to ascertain the worst case directions as computation time required for evaluating them is very small. A sin- gle evaluation of a surrogate model takes less than a second. Another contribution of this thesis is the evaluation of operational safety margin metric with the help of surrogate models. Operational safety margin is a metric defined in the uncertain parameter space and is related to the distance between the nominal parameter value and the first instance of performance criteria violation. This metric can help to gauge the robustness of the controller but requires the evaluation of the model in the constraint function and hence could be computationally intensive. As surrogate models are computationally very cheap, they are utilised to rapidly compute the operational safety margin metric. But this metric focuses only on finding a safe region around the nominal parameter value and the possibility of other disjoint safe regions are not explored. In order to find other safe or failure regions in the param- eter space, the method of Bernstein expansion method is utilised on surrogate polynomial models to help characterise the uncertain param- eter space into safe and failure regions. Furthermore, Binomial failure analysis is used to assign failure probabilities to failure regions which might help the designer to determine if a re-design of the controller is required or not. The methodologies of optimisation based V&V, surrogate modelling, operational safety margin, Bernstein expansion method and risk assessment have been combined together to form the WCAT-II MATLAB toolbox.

Surrogate organisms have been used to study highly pathogenic organisms, or organisms that cannot be cultured in the laboratory. Surrogates are selected based on multiple similarities to the pathogen, such as morphology, genome size and structure, and environmental characteristics. This dissertation utilized MS2 coliphage as a surrogate for norovirus and Ebola virus in three environments. MS2 is an icosahedral, single-stranded RNA bacteriophage. It is a male-specific coliphage that infects the bacteria Escherichia coli. Its properties, such as morphology and survival in the environment, have been likened to those of many enteric viruses. Because of this, it has been used as a surrogate for pathogenic enteric viruses for disinfection testing on surfaces, in water and in food; modeling the movement and survival of pathogens in different environments; and transfer properties from surfaces. This dissertation utilized MS2 as a surrogate in three different studies. In the first, MS2 is used as a surrogate for human enteric viruses in irrigation canals to predict the re-suspension of pathogenic viruses from bed sediment into overlying irrigation water using a flume to re-create field conditions in the laboratory. MS2 re-suspension into the overlying water was characterized at varying flow rates and velocities using two sediment types. Its overall re-suspension was not statistically significantly different (p > 0.05) between flow rates. The additional studies in this dissertation used MS2 as a surrogate for Ebola virus in human waste. Ebola virus is a BSL-4 organism that is spread through direct contact with bodily fluids. It is found in bodily fluids in concentrations between 10^5.5 and 10⁸ genome copies per milliliter. In the first study using MS2 as a surrogate for Ebola virus, efficacies of four disinfectants were tested using 10¹² PFU of MS2 in one liter containing 2.25% (w/v) organic matter at three contact times (1, 15 and 30 minutes). The purpose of this study was to assess the disinfectants on reducing virus in waste before toilet flushing. Peracetic acid and quaternary ammonium formulation were found to reduce the concentration of MS2 in the toilet bowl the fastest (within one minute) with the greatest reduction (2.26 and 1.99 log₁₀), when compared with the other disinfectants. Reductions observed from hydrogen peroxide were significantly less than those from peracetic acid and quaternary ammonium (p < 0.05). The contamination of restroom surfaces by MS2 was also evaluated after toilet flushing with and without disinfectant treatment. All four disinfectants were found to significantly reduce the viral concentrations on fomites after 15 minutes of contact (p < 0.05). Despite disinfectant use, three sites were contaminated in 100% of trials (N = 18). These were the toilet bowl rim, the toilet seat top and underside. The final study evaluated the inactivation of MS2 and several other viruses by thermophilic and mesophilic anaerobic digestion. Little information is available on the influence of the wastewater treatment process, specifically anaerobic digestion, on emerging viruses, such as Ebola virus. It is important to evaluate this process due to the environmental disposal and discharge of wastewater and solids into the environment. All viruses were recoverable after mesophilic digestion (reductions from 1.8-6.6 log₁₀ per mL), except the lipid-containing bacteriophage Φ6. Thermophilic digestion inactivated all viruses significantly (p = 0.0011) more than mesophilic digestion. The reductions by thermophilic digestion ranged from 2.8-7.1 log₁₀ per mL. The inactivation between the initial concentration and both digestion types was statistically significant (p = 0.007).

This thesis presents a novel evolutionary optimisation algorithm that can improve the quality of solutions in simulation-based optimisation. Simulation-based optimisation is the process of finding optimal parameter settings without explicitly examining each possible configuration of settings. An optimisation algorithm generates potential configurations and sends these to the simulation, which acts as an evaluation function. The evaluation results are used to refine the optimisation such that it eventually returns a high-quality solution. The algorithm described in this thesis integrates multi-objective optimisation, parallelism, surrogate usage, and noise handling in a unique way for dealing with simulation-based optimisation problems incurred by these characteristics. In order to handle multiple, conflicting optimisation objectives, the algorithm uses a Pareto approach in which the set of best trade-off solutions is searched for and presented to the user. The algorithm supports a high degree of parallelism by adopting an asynchronous master-slave parallelisation model in combination with an incremental population refinement strategy. A surrogate evaluation function is adopted in the algorithm to quickly identify promising candidate solutions and filter out poor ones. A novel technique based on inheritance is used to compensate for the uncertainties associated with the approximative surrogate evaluations. Furthermore, a novel technique for multi-objective problems that effectively reduces noise by adopting a dynamic procedure in resampling solutions is used to tackle the problem of real-world unpredictability (noise). The proposed algorithm is evaluated on benchmark problems and two complex real-world problems of manufacturing optimisation. The first real-world problem concerns the optimisation of a production cell at Volvo Aero, while the second one concerns the optimisation of a camshaft machining line at Volvo Cars Engine. The results from the optimisations show that the algorithm finds better solutions for all the problems considered than existing, similar algorithms. The new techniques for dealing with surrogate imprecision and noise used in the algorithm are identified as key reasons for the good performance.

Traffic safety is one of the most essential aspects of transportation engineering. However, most crash prediction models are statistically-based prediction methods, which require significant efforts in crash data collection and may not be applied in particular traffic environments due to the limitation of data sources. Traditional traffic conflict studies are mostly field-based studies depending on manual counting, which is also labor-intensive and oftentimes inaccurate. Nowadays, simulation tools are widely utilized in traffic conflict studies. However, there is not a surrogate indicator that is widely accepted in conflict studies. The primary objective of this research is to develop such a reliable surrogate measure for simulation-based conflict studies. An indicator named Aggregated Crash Propensity Index (ACPI) is proposed to address this void. A Probabilistic model named Crash Propensity Model (CPM) is developed to determine the crash probability of simulated conflicts by introducing probability density functions of reaction time and maximum braking rates. The CPM is able to generate the ACPI for three different conflict types: crossing, rear-end and lane change. A series of comparative and field-based analysis efforts are undertaken to evaluate the accuracy of the proposed metric. Intersections are simulated with the VISSIM micro simulation and the output is processed through SSAM to extract useful conflict data to be used as the entry into CPM model. In the comparative analysis, three studies are conducted to evaluate the safety effect of specific changes in intersection geometry and operations. The comparisons utilize the existing Highway Safety Manual (HSM) processes to determine whether ACPI can identify the same trends as those observed in the HSM. The ACPI outperforms time-to-collision-based indicators and tracks the values suggested by the HSM in terms of identifying the relative safety among various scenarios. In field-based analysis, the Spearman’s rank tests indicate that ACPI is able to identify the relative safety among traffic facilities/treatments. Moreover, ACPI-based prediction models are well fitted, suggesting its potential to be directly link to real crash. All efforts indicate that ACPI is a promising surrogate measure of safety for simulation-based studies.

<p>Semi-natural grasslands, which are a declining and fragmented habitat in Europe, contain a high biodiversity, and are therefore of interest to conservation. This thesis examines how plant diversity is influenced by the landscape context, and how plant and fungal diversity can be targeted by practical conservation using indicator species and congruence between species groups. Reproduction and recruitment of the dioecious herb <i>Antennaria dioica </i>was also investigated, providing a case study on how fragmentation and habitat degradation may affect grassland plants.</p><p>Grassland size and heterogeneity were of greater importance for plant diversity in semi-natural grassland, than present or historical connectivity to other grasslands, or landscape characteristics. Larger grasslands were more heterogeneous than smaller grasslands, being the likely reason for the species-area relationship.</p><p>A detailed study on <i>A. dioica </i>discovered that sexual reproduction and recruitment may be hampered due to skewed sex-ratios. Sex-ratios were more skewed in small populations, suggesting that dioecious plants are likely to be particularly sensitive to reduced grassland size and fragmentation.</p><p>A study on indicators of plant species richness, used in a recent survey of remaining semi-natural grasslands in Sweden, revealed several problems. A high percentage of all indicator species were missed by the survey, removing an otherwise significant correlation between indicator species and plant species richness. Also, a null model showed that the chosen indicator species did not perform significantly better than species chosen at random from the available species pool, questioning the selection of the indicators in the survey. Diversity patterns of the threatened fungal genus <i>Hygrocybe</i> were not congruent with plant species richness or composition. Plants are thus a poor surrogate group for Hygrocybe fungi, and probably also for other grassland fungi. Implications from this thesis are that conservation of semi-natural grasslands should target several species groups, and that an appropriate scale for plant conservation may be local rather than regional.</p>

We present a unifying framework for the global optimization of functions which are expensive to evaluate. The framework is based on a Bayesian interpretation of radial basis function interpolation which incorporates existing methods such as Kriging, Gaussian process regression and neural networks. This viewpoint enables the application of Bayesian decision theory to derive a sequential global optimization algorithm which can be extended to include existing algorithms of this type in the literature. By posing the optimization problem as a sequence of sampling decisions, we optimize a general cost function at each stage of the algorithm. An extension to multi-stage decision processes is also discussed. The key idea of the framework is to replace the underlying expensive function by a cheap surrogate approximation. This enables the use of existing branch and bound techniques to globally optimize the cost function. We present a rigorous analysis of the canonical branch and bound algorithm in this setting as well as newly developed algorithms for other domains including convex sets. In particular, by making use of Lipschitz continuity of the surrogate approximation, we develop an entirely new algorithm based on overlapping balls. An application of the framework to the integration of expensive functions over rectangular domains and spherical surfaces in low dimensions is also considered. To assess performance of the framework, we apply it to canonical examples from the literature as well as an industrial model problem from oil reservoir simulation.

Evolutionary algorithms are one of the most successful methods for solving non-traditional optimization problems. As they employ only function values of the objective function, evolutionary algorithms converge much more slowly than optimization methods for smooth functions. This property of evolutionary algorithms is particularly disadvantageous in the context of costly and time-consuming empirical way of obtaining values of the objective function. However, evolutionary algorithms can be substantially speeded up by employing a sufficiently accurate regression model of the empirical objective function. This thesis provides a survey of utilizability of regression trees and their ensembles as a surrogate model to accelerate convergence of evolutionary optimization.

In the present work, we study possibilities of using artificial neural networks for accelerating of evolutionary algorithms. Improving consists in decreasing in number of calls to the fitness function, the evaluation of which is in some kinds of optimization problems very time- consuming and expensive. We use neural network as a regression model, which serves for fitness estimation in a run of evolutionary algorithm. Together with the regression model, we work also with the real fitness function, which we use for re-evaluation of individuals that are selecting according to a beforehand chosen strategy. These individuals re-evaluated by the real fitness function are used for improving the regression model. Because a significant number of individuals are evaluated only with the regression model, the number of calls to the real fitness function, that is needed for finding of a good solution of the optimization problem, is substantially reduced.