Solving competitive location problems via memetic algorithms. High performance computing approaches.

Solving competitive location problems via memetic algorithms. High performance computing approaches.

Author: Juana López Redondo

Publisher: Universidad Almería

Published: 2009-02-19

Total Pages: 293

ISBN-13: 848240914X

DOWNLOAD EBOOK

La localización de servicios (“Facility location” en inglés) pretende encontrar el emplazamiento de uno o más centros (servicios) de modo que se optimice una determinada función objetivo. Dicha función objetivo puede, por ejemplo, tratar de minimizar el coste de transporte, proporcionar a los clientes un servicio de forma equitativa, capturar la mayor cuota de mercado posible, etc. La localización de servicios abarca muchos campos, como la investigación operativa, la ingeniería industrial, la geografía, la economía, las matemáticas, el marketing, el planning urbanístico, además de otros muchos campos relacionados. Existen muchos problemas de localización en la vida real, como por ejemplo, la localización de hospitales, de colegios o vertederos, por nombrar algunos. Para ser capaces de obtener soluciones a los problemas de localización, es necesario desarrollar/diseñar un modelo que represente la realidad lo más fielmente posible. Dichos modelos pueden llegar a ser realmente difíciles de tratar. Muchos algoritmos de optimización global, exactos y heurísticos han sido propuestos para resolver problemas de localización. Los algoritmos exactos se caracterizan por ser capaces de obtener el óptimo global con una cierta precisión. Sin embargo, suelen ser altamente costosos desde el punto de vista computacional, lo que implica que, en determinados casos, sea imposible aplicarlos para resolver un problema. Los algoritmos heurísticos se alzan entonces como una buena alternativa. No obstante, en determinadas circunstancias, los requerimientos computacionales son tan elevados, que el uso de algoritmos heurísticos ejecutándose en procesadores estándares no es suficiente. En tales situaciones, la computación de altas prestaciones es necesaria. Esta tesis, “Solving competitive location problems via memetic algorithms. High performance computing approaches” (Algoritmos meméticos para problemas de localización competitiva. Computación de altas prestaciones), proporciona, por un lado, algoritmos heurísticos capaces de resolver problemas de localización, tanto en el dominio continuo como en el discreto y, por otro lado, técnicas paralelas que permiten reducir el tiempo de ejecución, resolver problemas más grandes, e incluso en ocasiones mejorar la calidad de las soluciones. Esta tesis incluye tres partes bien diferenciadas, cada una de las cuales se divide en varios capítulos. La primera parte Preliminaries (Preliminares), está compuesta por tres capítulos que revisan el estado actual de la optimización global, de la computación de altas prestaciones y de la ciencia de la localización, respectivamente. El Capítulo 1 comienza con la definición de los problemas de optimización, y continúa con la introducción de diferentes métodos heurísticos para tratar con ellos. El Capítulo 2 describe brevemente algunas de las arquitecturas paralelas y de los modelos de programación paralelos. Finalmente, en el Capítulo 3, se describen y analizan los principales ingredientes de la localización de servicios, y se presenta una revisión sobre problemas de localización continuos y discretos. La segunda parte de la tesis, Solving continuous location problems (Resolviendo problemas de localización continua), comienza en el Capítulo 4, donde se presenta un problema de localización competitiva en el plano y se revisan dos técnicas previamente propuestas en la literatura para resolverlo. Posteriormente, se describe una nuevo algoritmo evolutivo para resolver óptimamente el problema, llamado UEGO, y se comparan todas las alternativas. Finalmente, varias estrategias paralelas basadas en el algoritmo UEGO son analizadas y evaluadas. En el Capítulo 5, el problema de localizar un solo centro en el plano, se extiende al caso en el que la cadena o empresa quiere emplazar más de un servicio. Para abordar este problema, se adapta el algoritmo UEGO presentado en el Capítulo 4, además de otras técnicas descritas en la literatura. A través de un extenso estudio computational, todas los algoritmos son comparados y se concluye que UEGO es el mejor de todos ellos, tanto por su eficiencia como por su efectividad. UEGO es usado para realizar un estudio de sensibilidad con el fin de chequear los cambios de diseño/localización óptima cuando los parámetros del modelo cambian. Finalmente, se presentan y evalúan varias técnicas paralelas para tratar el problema de localización de varios centros. El Capítulo 6 está dedicado al problema de líder-seguidor. En dicho problema, tras la localización del líder, el competidor reacciona localizando otro nuevo centro en el lugar que maximice su propio beneficio. El objetivo del líder es encontrar la solución que maximice su beneficio, sabiendo que posteriormente, la competencia localizará un nuevo centro. Por tanto, hay que resolver dos problemas simultáneamente: el problema del seguidor, también denominado medianoide, y el problema del líder o centroide. El modelo del problema del líder-seguidor se describe al principio del capítulo. Posteriormente, se proponen y evalúan varios algoritmos para resolver tanto el problema del medianoide como el del centroide. El capítulo finaliza con la paralelización de uno de los algoritmos propuestos. La tercera parte de la tesis, Solving discrete location problems (Resolviendo problemas de localización discreta), comienza en el Capítulo 7 con una introducción sobre algunos problemas de localización discreta. Este capítulo analiza aquellos casos en los que dichos problemas podrían presentar varias soluciones óptimas. Además, se muestra cómo un usuario experimentado podría obtenerlas, y se establecen algunos criterios para seleccionar una solución óptima entre diferentes alternativas. El capítulo finaliza con la descripción del algoritmo MSH, un heurístico ampliamente usado en la literatura para la resolución de problemas de localización discreta. El Capítulo 8 describe un algoritmo genético multimodal, GASUB, capaz de resolver varios problemas de localización discreta. El algoritmo tiene diferentes parámetros de entrada que pueden ser ajustados para alcanzar diferentes metas. En este capítulo, el objetivo es obtener al menos una solución óptima, pero invirtiendo el menor esfuerzo (tiempo) computacional posible. Para tal fin, se lleva a cabo un estudio previo y se determina el conjunto de parámetros adecuado. GASUB, con este conjunto de parámetros, es comparado con el optimizador Xpress-MP y con la heurística MSH, los cuales son capaces de obtener un único óptimo global (de manera directa). Sin embargo, teniendo en cuenta que los problemas de localización discreta considerados en esta tesis pueden tener más de una solución óptima, en el Capítulo 9 se analiza la posibilidad de explotar las propiedades multimodales de GASUB. Con este fin, se propone un nuevo conjunto de parámetros, con el que GASUB es nuevamente evaluado. Finalmente, se da una paralelización de GASUB y se estudian algunas de las soluciones globales encontradas por los algoritmos. La tesis finaliza con un resumen sobre los principales resultados obtenidos y sobre la líneas de investigación futura.


Swarm, Evolutionary, and Memetic Computing and Fuzzy and Neural Computing

Swarm, Evolutionary, and Memetic Computing and Fuzzy and Neural Computing

Author: Aleš Zamuda

Publisher: Springer Nature

Published: 2020-01-02

Total Pages: 224

ISBN-13: 3030378381

DOWNLOAD EBOOK

This volume constitutes the thoroughly refereed post-conference proceedings of the 7th International Conference on Swarm, Evolutionary, and Memetic Computing, SEMCCO 2019, and 5th International Conference on Fuzzy and Neural Computing, FANCCO 2019, held in Maribor, Slovenia, in July 2019. The 18 full papers presented in this volume were carefully reviewed and selected from a total of 31 submissions for inclusion in the proceedings. The papers cover a wide range of topics in swarm, evolutionary, memetic and other intelligent computing algorithms and their real world applications in problems selected from diverse domains of science and engineering.


Business and Consumer Analytics: New Ideas

Business and Consumer Analytics: New Ideas

Author: Pablo Moscato

Publisher: Springer

Published: 2019-05-30

Total Pages: 1000

ISBN-13: 3030062228

DOWNLOAD EBOOK

This two-volume handbook presents a collection of novel methodologies with applications and illustrative examples in the areas of data-driven computational social sciences. Throughout this handbook, the focus is kept specifically on business and consumer-oriented applications with interesting sections ranging from clustering and network analysis, meta-analytics, memetic algorithms, machine learning, recommender systems methodologies, parallel pattern mining and data mining to specific applications in market segmentation, travel, fashion or entertainment analytics. A must-read for anyone in data-analytics, marketing, behavior modelling and computational social science, interested in the latest applications of new computer science methodologies. The chapters are contributed by leading experts in the associated fields.The chapters cover technical aspects at different levels, some of which are introductory and could be used for teaching. Some chapters aim at building a common understanding of the methodologies and recent application areas including the introduction of new theoretical results in the complexity of core problems. Business and marketing professionals may use the book to familiarize themselves with some important foundations of data science. The work is a good starting point to establish an open dialogue of communication between professionals and researchers from different fields. Together, the two volumes present a number of different new directions in Business and Customer Analytics with an emphasis in personalization of services, the development of new mathematical models and new algorithms, heuristics and metaheuristics applied to the challenging problems in the field. Sections of the book have introductory material to more specific and advanced themes in some of the chapters, allowing the volumes to be used as an advanced textbook. Clustering, Proximity Graphs, Pattern Mining, Frequent Itemset Mining, Feature Engineering, Network and Community Detection, Network-based Recommending Systems and Visualization, are some of the topics in the first volume. Techniques on Memetic Algorithms and their applications to Business Analytics and Data Science are surveyed in the second volume; applications in Team Orienteering, Competitive Facility-location, and Visualization of Products and Consumers are also discussed. The second volume also includes an introduction to Meta-Analytics, and to the application areas of Fashion and Travel Analytics. Overall, the two-volume set helps to describe some fundamentals, acts as a bridge between different disciplines, and presents important results in a rapidly moving field combining powerful optimization techniques allied to new mathematical models critical for personalization of services. Academics and professionals working in the area of business anyalytics, data science, operations research and marketing will find this handbook valuable as a reference. Students studying these fields will find this handbook useful and helpful as a secondary textbook.


Handbook of Heuristics

Handbook of Heuristics

Author: Rafael Martí

Publisher: Springer

Published: 2017-01-16

Total Pages: 3000

ISBN-13: 9783319071237

DOWNLOAD EBOOK

Heuristics are strategies using readily accessible, loosely applicable information to control problem solving. Algorithms, for example, are a type of heuristic. By contrast, Metaheuristics are methods used to design Heuristics and may coordinate the usage of several Heuristics toward the formulation of a single method. GRASP (Greedy Randomized Adaptive Search Procedures) is an example of a Metaheuristic. To the layman, heuristics may be thought of as ‘rules of thumb’ but despite its imprecision, heuristics is a very rich field that refers to experience-based techniques for problem-solving, learning, and discovery. Any given solution/heuristic is not guaranteed to be optimal but heuristic methodologies are used to speed up the process of finding satisfactory solutions where optimal solutions are impractical. The introduction to this Handbook provides an overview of the history of Heuristics along with main issues regarding the methodologies covered. This is followed by Chapters containing various examples of local searches, search strategies and Metaheuristics, leading to an analyses of Heuristics and search algorithms. The reference concludes with numerous illustrations of the highly applicable nature and implementation of Heuristics in our daily life. Each chapter of this work includes an abstract/introduction with a short description of the methodology. Key words are also necessary as part of top-matter to each chapter to enable maximum search engine optimization. Next, chapters will include discussion of the adaptation of this methodology to solve a difficult optimization problem, and experiments on a set of representative problems.


Multi-Objective Memetic Algorithms

Multi-Objective Memetic Algorithms

Author: Chi-Keong Goh

Publisher: Springer Science & Business Media

Published: 2009-02-26

Total Pages: 399

ISBN-13: 354088050X

DOWNLOAD EBOOK

The application of sophisticated evolutionary computing approaches for solving complex problems with multiple conflicting objectives in science and engineering have increased steadily in the recent years. Within this growing trend, Memetic algorithms are, perhaps, one of the most successful stories, having demonstrated better efficacy in dealing with multi-objective problems as compared to its conventional counterparts. Nonetheless, researchers are only beginning to realize the vast potential of multi-objective Memetic algorithm and there remain many open topics in its design. This book presents a very first comprehensive collection of works, written by leading researchers in the field, and reflects the current state-of-the-art in the theory and practice of multi-objective Memetic algorithms. "Multi-Objective Memetic algorithms" is organized for a wide readership and will be a valuable reference for engineers, researchers, senior undergraduates and graduate students who are interested in the areas of Memetic algorithms and multi-objective optimization.


Handbook of Memetic Algorithms

Handbook of Memetic Algorithms

Author: Ferrante Neri

Publisher: Springer Science & Business Media

Published: 2011-10-18

Total Pages: 376

ISBN-13: 3642232469

DOWNLOAD EBOOK

Memetic Algorithms (MAs) are computational intelligence structures combining multiple and various operators in order to address optimization problems. The combination and interaction amongst operators evolves and promotes the diffusion of the most successful units and generates an algorithmic behavior which can handle complex objective functions and hard fitness landscapes. “Handbook of Memetic Algorithms” organizes, in a structured way, all the the most important results in the field of MAs since their earliest definition until now. A broad review including various algorithmic solutions as well as successful applications is included in this book. Each class of optimization problems, such as constrained optimization, multi-objective optimization, continuous vs combinatorial problems, uncertainties, are analysed separately and, for each problem, memetic recipes for tackling the difficulties are given with some successful examples. Although this book contains chapters written by multiple authors, a great attention has been given by the editors to make it a compact and smooth work which covers all the main areas of computational intelligence optimization. It is not only a necessary read for researchers working in the research area, but also a useful handbook for practitioners and engineers who need to address real-world optimization problems. In addition, the book structure makes it an interesting work also for graduate students and researchers is related fields of mathematics and computer science.


Introduction to Evolutionary Computing

Introduction to Evolutionary Computing

Author: A.E. Eiben

Publisher: Springer Science & Business Media

Published: 2007-08-06

Total Pages: 328

ISBN-13: 9783540401841

DOWNLOAD EBOOK

The first complete overview of evolutionary computing, the collective name for a range of problem-solving techniques based on principles of biological evolution, such as natural selection and genetic inheritance. The text is aimed directly at lecturers and graduate and undergraduate students. It is also meant for those who wish to apply evolutionary computing to a particular problem or within a given application area. The book contains quick-reference information on the current state-of-the-art in a wide range of related topics, so it is of interest not just to evolutionary computing specialists but to researchers working in other fields.


Handbook of Natural Computing

Handbook of Natural Computing

Author: Grzegorz Rozenberg

Publisher: Springer

Published: 2012-07-09

Total Pages: 2052

ISBN-13: 9783540929093

DOWNLOAD EBOOK

Natural Computing is the field of research that investigates both human-designed computing inspired by nature and computing taking place in nature, i.e., it investigates models and computational techniques inspired by nature and also it investigates phenomena taking place in nature in terms of information processing. Examples of the first strand of research covered by the handbook include neural computation inspired by the functioning of the brain; evolutionary computation inspired by Darwinian evolution of species; cellular automata inspired by intercellular communication; swarm intelligence inspired by the behavior of groups of organisms; artificial immune systems inspired by the natural immune system; artificial life systems inspired by the properties of natural life in general; membrane computing inspired by the compartmentalized ways in which cells process information; and amorphous computing inspired by morphogenesis. Other examples of natural-computing paradigms are molecular computing and quantum computing, where the goal is to replace traditional electronic hardware, e.g., by bioware in molecular computing. In molecular computing, data are encoded as biomolecules and then molecular biology tools are used to transform the data, thus performing computations. In quantum computing, one exploits quantum-mechanical phenomena to perform computations and secure communications more efficiently than classical physics and, hence, traditional hardware allows. The second strand of research covered by the handbook, computation taking place in nature, is represented by investigations into, among others, the computational nature of self-assembly, which lies at the core of nanoscience, the computational nature of developmental processes, the computational nature of biochemical reactions, the computational nature of bacterial communication, the computational nature of brain processes, and the systems biology approach to bionetworks where cellular processes are treated in terms of communication and interaction, and, hence, in terms of computation. We are now witnessing exciting interaction between computer science and the natural sciences. While the natural sciences are rapidly absorbing notions, techniques and methodologies intrinsic to information processing, computer science is adapting and extending its traditional notion of computation, and computational techniques, to account for computation taking place in nature around us. Natural Computing is an important catalyst for this two-way interaction, and this handbook is a major record of this important development.


Cellular Learning Automata: Theory and Applications

Cellular Learning Automata: Theory and Applications

Author: Reza Vafashoar

Publisher: Springer Nature

Published: 2020-07-24

Total Pages: 377

ISBN-13: 3030531414

DOWNLOAD EBOOK

This book highlights both theoretical and applied advances in cellular learning automata (CLA), a type of hybrid computational model that has been successfully employed in various areas to solve complex problems and to model, learn, or simulate complicated patterns of behavior. Owing to CLA’s parallel and learning abilities, it has proven to be quite effective in uncertain, time-varying, decentralized, and distributed environments. The book begins with a brief introduction to various CLA models, before focusing on recently developed CLA variants. In turn, the research areas related to CLA are addressed as bibliometric network analysis perspectives. The next part of the book presents CLA-based solutions to several computer science problems in e.g. static optimization, dynamic optimization, wireless networks, mesh networks, and cloud computing. Given its scope, the book is well suited for all researchers in the fields of artificial intelligence and reinforcement learning.


Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications

Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications

Author: Management Association, Information Resources

Publisher: IGI Global

Published: 2016-07-26

Total Pages: 1810

ISBN-13: 1522507892

DOWNLOAD EBOOK

As technology continues to become more sophisticated, mimicking natural processes and phenomena also becomes more of a reality. Continued research in the field of natural computing enables an understanding of the world around us, in addition to opportunities for man-made computing to mirror the natural processes and systems that have existed for centuries. Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications takes an interdisciplinary approach to the topic of natural computing, including emerging technologies being developed for the purpose of simulating natural phenomena, applications across industries, and the future outlook of biologically and nature-inspired technologies. Emphasizing critical research in a comprehensive multi-volume set, this publication is designed for use by IT professionals, researchers, and graduate students studying intelligent computing.