Algoritmos meméticos en problemas de investigación operativa

En este artículo se plantea la resolución de un problema de Investigación Operativa utilizando PHPSimplex (herramienta online de resolución de problemas de optimización utilizando el método Simplex), Solver de Microsoft Excel y un prototipo híbrido que combina las teorías de los Algoritmos Genéticos con una técnica heurística de búsqueda local. La hibridación de estas dos técnicas es conocida como Algoritmo Memético. Este prototipo será capaz de resolver problemas de Optimización con función de maximización o minimización conocida, superando las restricciones que se planteen. Los tres métodos conseguirán buenos resultados ante problemas sencillos de Investigación Operativa, sin embargo, se propone otro problema en el cual el Algoritmo Memético y la herramienta Solver de Microsoft Excel, alcanzarán la solución óptima. La resolución del problema utilizando PHPSimplex resultará inviable. El objetivo, además de resolver el problema propuesto, es comparar cómo se comportan los tres métodos anteriormente citados ante el problema y cómo afrontan las dificultades que éste presenta. Además, este artículo pretende dar a conocer diferentes técnicas de apoyo a la toma de decisiones, con la intención de que se utilicen cada vez más en el entorno empresarial sustentando, de esta manera, las decisiones mediante la matemática o la Inteligencia Artificial y no basándose únicamente en la experiencia.

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

131 p.: graf.

Implementación de algoritmos de Inteligencia Swarm con fines didácticos

Con este proyecto hemos querido proporcionar un conjunto de recursos útiles para la impartición de un curso de Swarm Intelligence enfocado a la Particle Swarm Optimization (PSO). Estos recursos constan de una aplicación en NetLogo para poder experimentar, ejecutar y visualizar los diferentes modelos de la PSO, un review de la Swarm Intelligence profundizando en la PSO y una ontología de PSO que incluye los recursos bibliográficos necesarios para la investigación y la escritura de artículos.

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.

Human Endogenous Retrovirus HERV-Fc1 Association with Multiple Sclerosis Susceptibility: A Meta-Analysis

Background: Human endogenous retroviruses (HERVs) are repetitive sequences derived from ancestral germ-line infections by exogenous retroviruses and different HERV families have been integrated in the genome. HERV-Fc1 in chromosome X has been previously associated with multiple sclerosis (MS) in Northern European populations. Additionally, HERV-Fc1 RNA levels of expression have been found increased in plasma of MS patients with active disease. Considering the North-South latitude gradient in MS prevalence, we aimed to evaluate the role of HERV-Fc1on MS risk in three independent Spanish cohorts. Methods: A single nucleotide polymorphism near HERV-Fc1, rs391745, was genotyped by Taqman chemistry in a total of 2473 MS patients and 3031 ethnically matched controls, consecutively recruited from: Northern (569 patients and 980 controls), Central (883 patients and 692 controls) and Southern (1021 patients and 1359 controls) Spain. Our results were pooled in a meta-analysis with previously published data. Results: Significant associations of the HERV-Fc1 polymorphism with MS were observed in two Spanish cohorts and the combined meta-analysis with previous data yielded a significant association [rs391745 C-allele carriers: p(M-H) = 0.0005; ORM-H (95% CI) = 1.27 (1.11-1.45)]. Concordantly to previous findings, when the analysis was restricted to relapsing remitting and secondary progressive MS samples, a slight enhancement in the strength of the association was observed [p(M-H) = 0.0003, ORM-H (95% CI) = 1.32 (1.14-1.53)]. Conclusion: Association of the HERV-Fc1 polymorphism rs391745 with bout-onset MS susceptibility was confirmed in Southern European cohorts.

Contributions to Ensemble Classifiers with Image Analysis Applications

134 p.