New methods for generating populations in Markov network based EDAs: Decimation strategies and model-based template recombination

Methods for generating a new population are a fundamental component of estimation of distribution algorithms (EDAs). They serve to transfer the information contained in the probabilistic model to the new generated population. In EDAs based on Markov networks, methods for generating new populations usually discard information contained in the model to gain in efficiency. Other methods like Gibbs sampling use information about all interactions in the model but are computationally very costly. In this paper we propose new methods for generating new solutions in EDAs based on Markov networks. We introduce approaches based on inference methods for computing the most probable configurations and model-based template recombination. We show that the application of different variants of inference methods can increase the EDAs’ convergence rate and reduce the number of function evaluations needed to find the optimum of binary and non-binary discrete functions.

Regularized model learning in EDAs for continuous and multi-objective optimization

Probabilistic modeling is the de�ning characteristic of estimation of distribution algorithms (EDAs) which determines their behavior and performance in optimization. Regularization is a well-known statistical technique used for obtaining an improved model by reducing the generalization error of estimation, especially in high-dimensional problems. `1-regularization is a type of this technique with the appealing variable selection property which results in sparse model estimations. In this thesis, we study the use of regularization techniques for model learning in EDAs. Several methods for regularized model estimation in continuous domains based on a Gaussian distribution assumption are presented, and analyzed from di�erent aspects when used for optimization in a high-dimensional setting, where the population size of EDA has a logarithmic scale with respect to the number of variables. The optimization results obtained for a number of continuous problems with an increasing number of variables show that the proposed EDA based on regularized model estimation performs a more robust optimization, and is able to achieve signi�cantly better results for larger dimensions than other Gaussian-based EDAs. We also propose a method for learning a marginally factorized Gaussian Markov random �eld model using regularization techniques and a clustering algorithm. The experimental results show notable optimization performance on continuous additively decomposable problems when using this model estimation method. Our study also covers multi-objective optimization and we propose joint probabilistic modeling of variables and objectives in EDAs based on Bayesian networks, speci�cally models inspired from multi-dimensional Bayesian network classi�ers. It is shown that with this approach to modeling, two new types of relationships are encoded in the estimated models in addition to the variable relationships captured in other EDAs: objectivevariable and objective-objective relationships. An extensive experimental study shows the e�ectiveness of this approach for multi- and many-objective optimization. With the proposed joint variable-objective modeling, in addition to the Pareto set approximation, the algorithm is also able to obtain an estimation of the multi-objective problem structure. Finally, the study of multi-objective optimization based on joint probabilistic modeling is extended to noisy domains, where the noise in objective values is represented by intervals. A new version of the Pareto dominance relation for ordering the solutions in these problems, namely �-degree Pareto dominance, is introduced and its properties are analyzed. We show that the ranking methods based on this dominance relation can result in competitive performance of EDAs with respect to the quality of the approximated Pareto sets. This dominance relation is then used together with a method for joint probabilistic modeling based on `1-regularization for multi-objective feature subset selection in classi�cation, where six di�erent measures of accuracy are considered as objectives with interval values. The individual assessment of the proposed joint probabilistic modeling and solution ranking methods on datasets with small-medium dimensionality, when using two di�erent Bayesian classi�ers, shows that comparable or better Pareto sets of feature subsets are approximated in comparison to standard methods.

Extreme temperatures and emergency department admissions for childhood asthma in Brisbane, Australia

Objectives To examine the effect of extreme temperatures on emergency department admissions (EDAs) for childhood asthma. Methods An ecological design was used in this study. A Poisson linear regression model combined with a distributed lag non-linear model was used to quantify the effect of temperature on EDAs for asthma among children aged 0–14 years in Brisbane, Australia, during January 2003–December 2009, while controlling for air pollution, relative humidity, day of the week, season and long-term trends. The model residuals were checked to identify whether there was an added effect due to heat waves or cold spells. Results There were 13 324 EDAs for childhood asthma during the study period. Both hot and cold temperatures were associated with increases in EDAs for childhood asthma, and their effects both appeared to be acute. An added effect of heat waves on EDAs for childhood asthma was observed, but no added effect of cold spells was found. Male children and children aged 0–4 years were most vulnerable to heat effects, while children aged 10–14 years were most vulnerable to cold effects. Conclusions Both hot and cold temperatures seemed to affect EDAs for childhood asthma. As climate change continues, children aged 0–4 years are at particular risk for asthma.

Extreme temperatures and paediatric emergency department admissions

Background Children are particularly vulnerable to the effects of extreme temperatures. Objective To examine the relationship between extreme temperatures and paediatric emergency department admissions (EDAs) in Brisbane, Australia, during 2003–2009. Methods A quasi-Poisson generalised linear model combined with a distributed lag non-linear model was used to examine the relationships between extreme temperatures and age-, gender- and cause-specific paediatric EDAs, while controlling for air pollution, relative humidity, day of the week, influenza epidemics, public holiday, season and long-term trends. The model residuals were checked to identify whether there was an added effect due to heat waves or cold spells. Results There were 131 249 EDAs among children during the study period. Both high (RR=1.27; 95% CI 1.12 to 1.44) and low (RR=1.81; 95% CI 1.66 to 1.97) temperatures were significantly associated with an increase in paediatric EDAs in Brisbane. Male children were more vulnerable to temperature effects. Children aged 0–4 years were more vulnerable to heat effects and children aged 10–14 years were more sensitive to both hot and cold effects. High temperatures had a significant impact on several paediatric diseases, including intestinal infectious diseases, respiratory diseases, endocrine, nutritional and metabolic diseases, nervous system diseases and chronic lower respiratory diseases. Low temperatures were significantly associated with intestinal infectious diseases, respiratory diseases and endocrine, nutritional and metabolic diseases. An added effect of heat waves on childhood chronic lower respiratory diseases was seen, but no added effect of cold spells was found. Conclusions As climate change continues, children are at particular risk of a variety of diseases which might be triggered by extremely high temperatures. This study suggests that preventing the effects of extreme temperature on children with respiratory diseases might reduce the number of EDAs.

Computational fluid dynamics simulation and turbomachinery code validation of a high pressure ratio radial-inflow turbine

The present study explores reproducing the closest geometry of a high pressure ratio single stage radial-inflow turbine applied in the Sundstrans Power Systems T-100 Multipurpose Small Power Unit. The commercial software ANSYS-Vista RTD along with a built in module, BladeGen, is used to conduct a meanline design and create 3D geometry of one flow passage. Carefully examining the proposed design against the geometrical and experimental data, ANSYS-TurboGrid is applied to generate computational mesh. CFD simulations are performed with ANSYS-CFX in which three-dimensional Reynolds-Averaged Navier-Stokes equations are solved subject to appropriate boundary conditions. Results are compared with numerical and experimental data published in the literature in order to generate the exact geometry of the existing turbine and validate the numerical results against the experimental ones.

Empirical vehicle-to-vehicle pathloss modeling in highway, suburban and urban environments at 5.8GHz

In this paper, we present a pathloss characterization for vehicle-to-vehicle (V2V) communications based on empirical data collected from extensive measurement campaign performed under line-of-sight (LOS), non-line-of-sight (NLOS) and varying traffic densities. The experiment was conducted in three different V2V propagation environments: highway, suburban and urban at 5.8GHz. We developed pathloss models for each of the three different V2V environments considered. Based on a log-distance power law model, the values for the pathloss exponent and the standard deviation of shadowing were reported. The average pathloss exponent ranges from 1.77 for highway, 1.68 for the urban to 1.53 for the suburban environment. The reported results can contribute to vehicular network (VANET) simulators and can be used by system designers to develop, evaluate and validate new protocols and system designs under realistic propagation conditions.

Antenna selection in spatial modulation systems

Novel transmit antenna selection techniques are conceived for Spatial Modulation (SM) systems and their symbol error rate (SER) performance is investigated. Specifically, low-complexity Euclidean Distance optimized Antenna Selection (EDAS) and Capacity Optimized Antenna Selection (COAS) are studied. It is observed that the COAS scheme gives a better SER performance than the EDAS scheme. We show that the proposed antenna selection based SM systems are capable of attaining a significant gain in signal-to-noise ratio (SNR) compared to conventional SM systems, and also outperform the conventional MIMO systems employing antenna selection at both low and medium SNRs.

Quantifying the Transmit Diversity Order of Euclidean Distance Based Antenna Selection in Spatial Modulation

In this letter, we quantify the transmit diversity order of the SM system operating in a closed-loop scenario. Specifically, the SM system relying on Euclidean distance based antenna subset selection (EDAS) is considered and the achievable diversity gain is evaluated. Furthermore, the resultant trade-off between the achievable diversity gain and switching gain is studied. Simulation results confirm our theoretical results. Specifically, at a symbol error rate of about 10(-4) the signal-to-noise ratio gain achieved by EDAS is about 7 dB in case of 16-QAM and about 5 dB in case of 64-QAM.

Avances en algoritmos de estimación de distribuciones. Alternativas en el aprendizaje y representación de problemas

131 p.: graf.

Using network mesures to test evolved NK-landscapes

In this paper we empirically investigate which are the structural characteristics that can help to predict the complexity of NK-landscape instances for estimation of distribution algorithms. To this end, we evolve instances that maximize the estimation of distribution algorithm complexity in terms of its success rate. Similarly, instances that minimize the algorithm complexity are evolved. We then identify network measures, computed from the structures of the NK-landscape instances, that have a statistically significant difference between the set of easy and hard instances. The features identified are consistently significant for different values of N and K.

Mateda-2.0: Estimation of Distribution Algorithms in MATLAB

This paper describes Mateda-2.0, a MATLAB package for estimation of distribution algorithms (EDAs). This package can be used to solve single and multi-objective discrete and continuous optimization problems using EDAs based on undirected and directed probabilistic graphical models. The implementation contains several methods commonly employed by EDAs. It is also conceived as an open package to allow users to incorporate different combinations of selection, learning, sampling, and local search procedures. Additionally, it includes methods to extract, process and visualize the structures learned by the probabilistic models. This way, it can unveil previously unknown information about the optimization problem domain. Mateda-2.0 also incorporates a module for creating and validating function models based on the probabilistic models learned by EDAs.

Extending Distance-based Ranking Models In Estimation of Distribution Algorithms

Recently, probability models on rankings have been proposed in the field of estimation of distribution algorithms in order to solve permutation-based combinatorial optimisation problems. Particularly, distance-based ranking models, such as Mallows and Generalized Mallows under the Kendall’s-t distance, have demonstrated their validity when solving this type of problems. Nevertheless, there are still many trends that deserve further study. In this paper, we extend the use of distance-based ranking models in the framework of EDAs by introducing new distance metrics such as Cayley and Ulam. In order to analyse the performance of the Mallows and Generalized Mallows EDAs under the Kendall, Cayley and Ulam distances, we run them on a benchmark of 120 instances from four well known permutation problems. The conducted experiments showed that there is not just one metric that performs the best in all the problems. However, the statistical test pointed out that Mallows-Ulam EDA is the most stable algorithm among the studied proposals.

Algoritmos multi-objetivos para la optimización de una secuencia de matrices generadoras en computación cuántica topológica

Quantum Computing is a relatively modern field which simulates quantum computation conditions. Moreover, it can be used to estimate which quasiparticles would endure better in a quantum environment. Topological Quantum Computing (TQC) is an approximation for reducing the quantum decoherence problem1, which is responsible for error appearance in the representation of information. This project tackles specific instances of TQC problems using MOEAs (Multi-objective Optimization Evolutionary Algorithms). A MOEA is a type of algorithm which will optimize two or more objectives of a problem simultaneously, using a population based approach. We have implemented MOEAs that use probabilistic procedures found in EDAs (Estimation of Distribution Algorithms), since in general, EDAs have found better solutions than ordinary EAs (Evolutionary Algorithms), even though they are more costly. Both, EDAs and MOEAs are population-based algorithms. The objective of this project was to use a multi-objective approach in order to find good solutions for several instances of a TQC problem. In particular, the objectives considered in the project were the error approximation and the length of a solution. The tool we used to solve the instances of the problem was the multi-objective framework PISA. Because PISA has not too much documentation available, we had to go through a process of reverse-engineering of the framework to understand its modules and the way they communicate with each other. Once its functioning was understood, we began working on a module dedicated to the braid problem. Finally, we submitted this module to an exhaustive experimentation phase and collected results.