This book constitutes the proceedings of the 11th International Conference on Swarm Intelligence, ANTS 2018, held in Rome, Italy, in October 2018.The 24 full papers and 12 short papers presented in this volume were carefully reviewed and selected from 69 submissions. They are devoted to the field of swarm intelligence as a whole, without any bias towards specific research directions.

This book constitutes the proceedings of the 9th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2014. This volume contains 17 full papers, 9 short papers, and 7 extended abstracts carefully selected out of 55 submissions. The papers cover empirical and theoretical research in swarm intelligence such as: behavioral models of social insects or other animal societies, ant colony optimization, particle swarm optimization, swarm robotics systems.

This book constitutes the proceedings of the 9th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2014. This volume contains 17 full papers, 9 short papers, and 7 extended abstracts carefully selected out of 55 submissions. The papers cover empirical and theoretical research in swarm intelligence such as: behavioral models of social insects or other animal societies, ant colony optimization, particle swarm optimization, swarm robotics systems.

This book constitutes the proceedings of the 10th International Conference on Swarm Intelligence, ANTS 2016, held in Brussels, Belgium, in September 2016. The 18 full papers and 7 short papers presented in this volume were carefully reviewed and selected from 47 submissions. They are devoted to the field of swarm intelligence as a whole, without any bias towards specific research directions.

1 With its fourth edition, the ANTS series of workshops has changed its name. Theoriginal"ANTS-FromAntColoniestoArti?cialAnts:InternationalWo- shop on Ant Algorithms" has become "ANTS - International Workshop on Ant Colony Optimization and Swarm Intelligence". This change is mainly due to the following reasons. First, the term "ant algorithms" was slower in spreading in the research community than the term "swarm intelligence", while at the sametime research inso-calledswarm robotics wasthesubjectofincreasingactivity:itwastherefore an obvious choice to substitute the term ant algorithms with the more accepted and used term swarm intelligence. Second, although swarm intelligence research has undoubtedly produced a 2 number of interesting and promising research directions , we think it is fair to say that its most successful strand is the one known as "ant colony optimi- tion".Ant colony optimization, ?rst introducedin the early1990sasa noveltool fortheapproximatesolutionofdiscreteoptimizationproblems,hasrecentlyseen an explosion in the number of its applications, both to academic and real-world problems, and is currently being extended to the realm of continuous optimi- tion (a few papers on this subject being published in these proceedings).It is therefore a reasonable choice to have the term ant colony optimization as part of the workshop name.

ANTS – The International Workshop on Ant Colony Optimization and Swarm Intelligence is now at its ?fth edition. The series started in 1998 with the - ganization of ANTS 1998. At that time the goal was to gather in a common meeting those researchers interested in ant colony optimization: more than 50 researchers from around the world joined for the ?rst time in Brussels, Belgium, to discuss ant colony optimization and swarm intelligence related research. A selectionofthebest paperspresentedatthe workshopwaspublished asa special issue of the Future Generation Computer Systems journal (Vol. 16, No. 8, 2000). Two years later, ANTS 2000, organized again in Brussels, attracted more than 70 participants. The 41 extended abstracts presented as talks or posters at the workshopwere collected in a booklet distributed to participants, and a selection of the best papers was published as a special section of the IEEE Transactions on Evolutionary Computation (Vol. 6, No. 4, 2002). After these ?rst two successful editions, it was decided to make of ANTS a seriesofbiannualeventswitho?cialworkshopproceedings.Thethirdandfourth editions were organized in September 2002 and September 2004, respectively. Proceedings were published by Springer within the Lecture Notes in Computer Science (LNCS) series. The proceedings of ANTS 2002, LNCS Volume 2463, contained 36 contri- tions: 17 full papers, 11 short papers, and 8 extended abstracts,selected out of a total of 52 submissions. Those of ANTS 2004, LNCS Volume 3172, contained 50 contributions:22 full papers, 19 shortpapers, and 9 extended abstracts,selected out of a total of 79 submissions.

ANTS – The International Workshop on Ant Colony Optimization and Swarm Intelligence is now at its ?fth edition. The series started in 1998 with the - ganization of ANTS 1998. At that time the goal was to gather in a common meeting those researchers interested in ant colony optimization: more than 50 researchers from around the world joined for the ?rst time in Brussels, Belgium, to discuss ant colony optimization and swarm intelligence related research. A selectionofthebest paperspresentedatthe workshopwaspublished asa special issue of the Future Generation Computer Systems journal (Vol. 16, No. 8, 2000). Two years later, ANTS 2000, organized again in Brussels, attracted more than 70 participants. The 41 extended abstracts presented as talks or posters at the workshopwere collected in a booklet distributed to participants, and a selection of the best papers was published as a special section of the IEEE Transactions on Evolutionary Computation (Vol. 6, No. 4, 2002). After these ?rst two successful editions, it was decided to make of ANTS a seriesofbiannualeventswitho?cialworkshopproceedings.Thethirdandfourth editions were organized in September 2002 and September 2004, respectively. Proceedings were published by Springer within the Lecture Notes in Computer Science (LNCS) series. The proceedings of ANTS 2002, LNCS Volume 2463, contained 36 contri- tions: 17 full papers, 11 short papers, and 8 extended abstracts,selected out of a total of 52 submissions. Those of ANTS 2004, LNCS Volume 3172, contained 50 contributions:22 full papers, 19 shortpapers, and 9 extended abstracts,selected out of a total of 79 submissions.

Stochastic local search (SLS) algorithms enjoy great popularity as powerful and versatile tools for tackling computationally hard decision and optimization pr- lems from many areas of computer science, operations research, and engineering. To a large degree, this popularity is based on the conceptual simplicity of many SLS methods and on their excellent performance on a wide gamut of problems, ranging from rather abstract problems of high academic interest to the very s- ci?c problems encountered in many real-world applications. SLS methods range from quite simple construction procedures and iterative improvement algorithms to more complex general-purpose schemes, also widely known as metaheuristics, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition, and overall resembled more an art than a science. However, in recent years it has become evident that at the core of this development task there is a highly complex engineering process, which combines various aspects of algorithm design with empirical analysis techniques and problem-speci?c background, and which relies heavily on knowledge from a number of disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics. This development process needs to be - sisted by a sound methodology that addresses the issues arising in the various phases of algorithm design, implementation, tuning, and experimental eval- tion.

Stochastic local search (SLS) algorithms enjoy great popularity as powerful and versatile tools for tackling computationally hard decision and optimization pr- lems from many areas of computer science, operations research, and engineering. To a large degree, this popularity is based on the conceptual simplicity of many SLS methods and on their excellent performance on a wide gamut of problems, ranging from rather abstract problems of high academic interest to the very s- ci?c problems encountered in many real-world applications. SLS methods range from quite simple construction procedures and iterative improvement algorithms to more complex general-purpose schemes, also widely known as metaheuristics, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition, and overall resembled more an art than a science. However, in recent years it has become evident that at the core of this development task there is a highly complex engineering process, which combines various aspects of algorithm design with empirical analysis techniques and problem-speci?c background, and which relies heavily on knowledge from a number of disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics. This development process needs to be - sisted by a sound methodology that addresses the issues arising in the various phases of algorithm design, implementation, tuning, and experimental eval- tion.

The series of biannual international conferences “ANTS – International C- ference on Ant Colony Optimization and Swarm Intelligence”, now in its sixth edition, was started ten years ago, with the organization of ANTS’98. As some readers might recall, the ?rst edition of ANTS was titled “ANTS’98 – From Ant Colonies to Arti?cial Ants: First International Workshop on Ant Colony Op- mization. ” In fact, at that time the focus was mainly on ant colony optimization (ACO), the ?rst swarm intelligence algorithm to go beyond a pure scienti?c interest and to enter the realm of real-world applications. Interestingly, in the ten years after the ?rst edition there has been a gr- ing interest not only for ACO, but for a number of other studies that belong more generally to the area of swarmintelligence. The rapid growth of the swarm intelligence ?eld is attested by a number of indicators. First, the number of s- missions and participants to the ANTS conferences has steadily increased over the years. Second, a number of international conferences in computational - telligence and related disciplines organize workshops on subjects such as swarm intelligence, ant algorithms, ant colony optimization, and particle swarm op- mization. Third, IEEE startedorganizing,in 2003,the IEEE SwarmIntelligence Symposium (in order to maintain unity in this growing ?eld, we are currently establishingacooperationagreementbetweenIEEE SISandANTSsoastohave 1 IEEE SIS in odd years and ANTS in even years). Last, the Swarm Intelligence journal was born.

The series of biannual international conferences “ANTS – International C- ference on Ant Colony Optimization and Swarm Intelligence”, now in its sixth edition, was started ten years ago, with the organization of ANTS’98. As some readers might recall, the ?rst edition of ANTS was titled “ANTS’98 – From Ant Colonies to Arti?cial Ants: First International Workshop on Ant Colony Op- mization. ” In fact, at that time the focus was mainly on ant colony optimization (ACO), the ?rst swarm intelligence algorithm to go beyond a pure scienti?c interest and to enter the realm of real-world applications. Interestingly, in the ten years after the ?rst edition there has been a gr- ing interest not only for ACO, but for a number of other studies that belong more generally to the area of swarmintelligence. The rapid growth of the swarm intelligence ?eld is attested by a number of indicators. First, the number of s- missions and participants to the ANTS conferences has steadily increased over the years. Second, a number of international conferences in computational - telligence and related disciplines organize workshops on subjects such as swarm intelligence, ant algorithms, ant colony optimization, and particle swarm op- mization. Third, IEEE startedorganizing,in 2003,the IEEE SwarmIntelligence Symposium (in order to maintain unity in this growing ?eld, we are currently establishingacooperationagreementbetweenIEEE SISandANTSsoastohave 1 IEEE SIS in odd years and ANTS in even years). Last, the Swarm Intelligence journal was born.

Metaheuristics are a relatively new but already established approachto c- binatorial optimization. A metaheuristic is a generic algorithmic template that can be used for ?nding high quality solutions of hard combinatorial - timization problems. To arrive at a functioning algorithm, a metaheuristic needs to be con?gured: typically some modules need to be instantiated and someparametersneedto betuned.Icallthese twoproblems"structural"and "parametric" tuning, respectively. More generally, I refer to the combination of the two problems as "tuning". Tuning is crucial to metaheuristic optimization both in academic research andforpracticalapplications.Nevertheless,relativelylittle researchhasbeen devoted to the issue. This book shows that the problem of tuning a me- heuristic can be described and solved as a machine learning problem. Using the machine learning perspective, it is possible to give a formal de?nitionofthetuningproblemandtodevelopagenericalgorithmfortuning metaheuristics.Moreover,fromthemachinelearningperspectiveitispossible tohighlightsome?awsinthecurrentresearchmethodologyandtostatesome guidelines for future empirical analysis in metaheuristics research.This book is based on my doctoral dissertation and contains results I have obtained starting from 2001 while working within the Metaheuristics Net- 1 work. During these years I have been a?liated with two research groups: INTELLEKTIK, Technische Universitat Darmstadt, Darmstadt, Germany and IRIDIA, Universite Libre de Bruxelles, Brussels, Belgium. I am the- fore grateful to the research directors of these two groups: Prof. Wolfgang Bibel, Dr. Thomas Stutzle, Prof. Philippe Smets, Prof. Hugues Bersini, and Prof. Marco Dorigo.

Stochastic local search (SLS) algorithms are established tools for the solution of computationally hard problems arising in computer science, business adm- istration, engineering, biology, and various other disciplines. To a large extent, their success is due to their conceptual simplicity, broad applicability and high performance for many important problems studied in academia and enco- tered in real-world applications. SLS methods include a wide spectrum of te- niques, ranging from constructive search procedures and iterative improvement algorithms to more complex SLS methods, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search, and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition. In recent years, it has become - creasingly evident that success with SLS algorithms depends not merely on the adoption and e?cient implementation of the most appropriate SLS technique for a given problem, but also on the mastery of a more complex algorithm - gineering process. Challenges in SLS algorithm development arise partly from the complexity of the problems being tackled and in part from the many - grees of freedom researchers and practitioners encounter when developing SLS algorithms. Crucial aspects in the SLS algorithm development comprise al- rithm design, empirical analysis techniques, problem-speci?c background, and background knowledge in several key disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics.

Stochastic local search (SLS) algorithms are established tools for the solution of computationally hard problems arising in computer science, business adm- istration, engineering, biology, and various other disciplines. To a large extent, their success is due to their conceptual simplicity, broad applicability and high performance for many important problems studied in academia and enco- tered in real-world applications. SLS methods include a wide spectrum of te- niques, ranging from constructive search procedures and iterative improvement algorithms to more complex SLS methods, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search, and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition. In recent years, it has become - creasingly evident that success with SLS algorithms depends not merely on the adoption and e?cient implementation of the most appropriate SLS technique for a given problem, but also on the mastery of a more complex algorithm - gineering process. Challenges in SLS algorithm development arise partly from the complexity of the problems being tackled and in part from the many - grees of freedom researchers and practitioners encounter when developing SLS algorithms. Crucial aspects in the SLS algorithm development comprise al- rithm design, empirical analysis techniques, problem-speci?c background, and background knowledge in several key disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics.

Metaheuristics are a relatively new but already established approachto c- binatorial optimization. A metaheuristic is a generic algorithmic template that can be used for ?nding high quality solutions of hard combinatorial - timization problems. To arrive at a functioning algorithm, a metaheuristic needs to be con?gured: typically some modules need to be instantiated and someparametersneedto betuned.Icallthese twoproblems"structural"and "parametric" tuning, respectively. More generally, I refer to the combination of the two problems as "tuning". Tuning is crucial to metaheuristic optimization both in academic research andforpracticalapplications.Nevertheless,relativelylittle researchhasbeen devoted to the issue. This book shows that the problem of tuning a me- heuristic can be described and solved as a machine learning problem. Using the machine learning perspective, it is possible to give a formal de?nitionofthetuningproblemandtodevelopagenericalgorithmfortuning metaheuristics.Moreover,fromthemachinelearningperspectiveitispossible tohighlightsome?awsinthecurrentresearchmethodologyandtostatesome guidelines for future empirical analysis in metaheuristics research.This book is based on my doctoral dissertation and contains results I have obtained starting from 2001 while working within the Metaheuristics Net- 1 work. During these years I have been a?liated with two research groups: INTELLEKTIK, Technische Universitat Darmstadt, Darmstadt, Germany and IRIDIA, Universite Libre de Bruxelles, Brussels, Belgium. I am the- fore grateful to the research directors of these two groups: Prof. Wolfgang Bibel, Dr. Thomas Stutzle, Prof. Philippe Smets, Prof. Hugues Bersini, and Prof. Marco Dorigo.

These proceedings contain the papers presented at ANTS 2010, the 7th Int- national Conference on Swarm Intelligence, organized by IRIDIA, CoDE, U- versiteLibre de Bruxelles,Brussels, Belgium, during September 8-10,2010.The ANTS series started in 1998 with the First International Workshop on Ant Colony Optimization (ANTS 1998), which attracted more than 50 participants. Since then ANTS, which is held bi-annually, has gradually become an inter- tional forum for researchers in the wider ?eld of swarm intelligence. In the past (since 2004), this development has been acknowledged by the inclusion of the term"SwarmIntelligence" (nextto"AntColonyOptimization")intheconference title. This year's ANTS conference was o?cially devoted to the ?eld of swarm intelligence as a whole, without any bias towards speci?c research directions. As a result, the title of the conference was changed to "The International Conf- ence on SwarmIntelligence." This name change is already in place this year,and future ANTS conferences will continue to use the new title. Thisvolumecontainsthebestpapersselectedoutof99submissions.Ofthese, 28 were accepted as full-length papers, while 27 were accepted as short papers.This corresponds to an overall acceptance rate of 56%. Also included in this volume are 14 extended abstracts. Of the full-length papers, 15 were selected for oral presentation at the c- ference. All other contributions, including short papers and extended abstracts, werepresentedin the formof poster presentations.Following the conference,the journal Swarm Intelligence will publish extended versions of some of the best papers presented at the conference.

This book constitutes the proceedings of the 8th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2012.This volume contains 15 full papers, 20 short papers, and 7 extended abstracts carefully selected out of 81 submissions. The papers cover various topics of swarm intelligence.

This book constitutes the proceedings of the 8th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2012.This volume contains 15 full papers, 20 short papers, and 7 extended abstracts carefully selected out of 81 submissions. The papers cover various topics of swarm intelligence.

This book constitutes the proceedings of the 11th International Conference on Swarm Intelligence, ANTS 2018, held in Rome, Italy, in October 2018.The 24 full papers and 12 short papers presented in this volume were carefully reviewed and selected from 69 submissions. They are devoted to the field of swarm intelligence as a whole, without any bias towards specific research directions.

This book constitutes the proceedings of the 9th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2014. This volume contains 17 full papers, 9 short papers, and 7 extended abstracts carefully selected out of 55 submissions. The papers cover empirical and theoretical research in swarm intelligence such as: behavioral models of social insects or other animal societies, ant colony optimization, particle swarm optimization, swarm robotics systems.

This book constitutes the proceedings of the 9th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2014. This volume contains 17 full papers, 9 short papers, and 7 extended abstracts carefully selected out of 55 submissions. The papers cover empirical and theoretical research in swarm intelligence such as: behavioral models of social insects or other animal societies, ant colony optimization, particle swarm optimization, swarm robotics systems.

This book constitutes the proceedings of the 10th International Conference on Swarm Intelligence, ANTS 2016, held in Brussels, Belgium, in September 2016. The 18 full papers and 7 short papers presented in this volume were carefully reviewed and selected from 47 submissions. They are devoted to the field of swarm intelligence as a whole, without any bias towards specific research directions.

1 With its fourth edition, the ANTS series of workshops has changed its name. Theoriginal"ANTS-FromAntColoniestoArti?cialAnts:InternationalWo- shop on Ant Algorithms" has become "ANTS - International Workshop on Ant Colony Optimization and Swarm Intelligence". This change is mainly due to the following reasons. First, the term "ant algorithms" was slower in spreading in the research community than the term "swarm intelligence", while at the sametime research inso-calledswarm robotics wasthesubjectofincreasingactivity:itwastherefore an obvious choice to substitute the term ant algorithms with the more accepted and used term swarm intelligence. Second, although swarm intelligence research has undoubtedly produced a 2 number of interesting and promising research directions , we think it is fair to say that its most successful strand is the one known as "ant colony optimi- tion".Ant colony optimization, ?rst introducedin the early1990sasa noveltool fortheapproximatesolutionofdiscreteoptimizationproblems,hasrecentlyseen an explosion in the number of its applications, both to academic and real-world problems, and is currently being extended to the realm of continuous optimi- tion (a few papers on this subject being published in these proceedings).It is therefore a reasonable choice to have the term ant colony optimization as part of the workshop name.

ANTS – The International Workshop on Ant Colony Optimization and Swarm Intelligence is now at its ?fth edition. The series started in 1998 with the - ganization of ANTS 1998. At that time the goal was to gather in a common meeting those researchers interested in ant colony optimization: more than 50 researchers from around the world joined for the ?rst time in Brussels, Belgium, to discuss ant colony optimization and swarm intelligence related research. A selectionofthebest paperspresentedatthe workshopwaspublished asa special issue of the Future Generation Computer Systems journal (Vol. 16, No. 8, 2000). Two years later, ANTS 2000, organized again in Brussels, attracted more than 70 participants. The 41 extended abstracts presented as talks or posters at the workshopwere collected in a booklet distributed to participants, and a selection of the best papers was published as a special section of the IEEE Transactions on Evolutionary Computation (Vol. 6, No. 4, 2002). After these ?rst two successful editions, it was decided to make of ANTS a seriesofbiannualeventswitho?cialworkshopproceedings.Thethirdandfourth editions were organized in September 2002 and September 2004, respectively. Proceedings were published by Springer within the Lecture Notes in Computer Science (LNCS) series. The proceedings of ANTS 2002, LNCS Volume 2463, contained 36 contri- tions: 17 full papers, 11 short papers, and 8 extended abstracts,selected out of a total of 52 submissions. Those of ANTS 2004, LNCS Volume 3172, contained 50 contributions:22 full papers, 19 shortpapers, and 9 extended abstracts,selected out of a total of 79 submissions.

ANTS – The International Workshop on Ant Colony Optimization and Swarm Intelligence is now at its ?fth edition. The series started in 1998 with the - ganization of ANTS 1998. At that time the goal was to gather in a common meeting those researchers interested in ant colony optimization: more than 50 researchers from around the world joined for the ?rst time in Brussels, Belgium, to discuss ant colony optimization and swarm intelligence related research. A selectionofthebest paperspresentedatthe workshopwaspublished asa special issue of the Future Generation Computer Systems journal (Vol. 16, No. 8, 2000). Two years later, ANTS 2000, organized again in Brussels, attracted more than 70 participants. The 41 extended abstracts presented as talks or posters at the workshopwere collected in a booklet distributed to participants, and a selection of the best papers was published as a special section of the IEEE Transactions on Evolutionary Computation (Vol. 6, No. 4, 2002). After these ?rst two successful editions, it was decided to make of ANTS a seriesofbiannualeventswitho?cialworkshopproceedings.Thethirdandfourth editions were organized in September 2002 and September 2004, respectively. Proceedings were published by Springer within the Lecture Notes in Computer Science (LNCS) series. The proceedings of ANTS 2002, LNCS Volume 2463, contained 36 contri- tions: 17 full papers, 11 short papers, and 8 extended abstracts,selected out of a total of 52 submissions. Those of ANTS 2004, LNCS Volume 3172, contained 50 contributions:22 full papers, 19 shortpapers, and 9 extended abstracts,selected out of a total of 79 submissions.

Stochastic local search (SLS) algorithms enjoy great popularity as powerful and versatile tools for tackling computationally hard decision and optimization pr- lems from many areas of computer science, operations research, and engineering. To a large degree, this popularity is based on the conceptual simplicity of many SLS methods and on their excellent performance on a wide gamut of problems, ranging from rather abstract problems of high academic interest to the very s- ci?c problems encountered in many real-world applications. SLS methods range from quite simple construction procedures and iterative improvement algorithms to more complex general-purpose schemes, also widely known as metaheuristics, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition, and overall resembled more an art than a science. However, in recent years it has become evident that at the core of this development task there is a highly complex engineering process, which combines various aspects of algorithm design with empirical analysis techniques and problem-speci?c background, and which relies heavily on knowledge from a number of disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics. This development process needs to be - sisted by a sound methodology that addresses the issues arising in the various phases of algorithm design, implementation, tuning, and experimental eval- tion.

Stochastic local search (SLS) algorithms enjoy great popularity as powerful and versatile tools for tackling computationally hard decision and optimization pr- lems from many areas of computer science, operations research, and engineering. To a large degree, this popularity is based on the conceptual simplicity of many SLS methods and on their excellent performance on a wide gamut of problems, ranging from rather abstract problems of high academic interest to the very s- ci?c problems encountered in many real-world applications. SLS methods range from quite simple construction procedures and iterative improvement algorithms to more complex general-purpose schemes, also widely known as metaheuristics, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition, and overall resembled more an art than a science. However, in recent years it has become evident that at the core of this development task there is a highly complex engineering process, which combines various aspects of algorithm design with empirical analysis techniques and problem-speci?c background, and which relies heavily on knowledge from a number of disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics. This development process needs to be - sisted by a sound methodology that addresses the issues arising in the various phases of algorithm design, implementation, tuning, and experimental eval- tion.

The series of biannual international conferences “ANTS – International C- ference on Ant Colony Optimization and Swarm Intelligence”, now in its sixth edition, was started ten years ago, with the organization of ANTS’98. As some readers might recall, the ?rst edition of ANTS was titled “ANTS’98 – From Ant Colonies to Arti?cial Ants: First International Workshop on Ant Colony Op- mization. ” In fact, at that time the focus was mainly on ant colony optimization (ACO), the ?rst swarm intelligence algorithm to go beyond a pure scienti?c interest and to enter the realm of real-world applications. Interestingly, in the ten years after the ?rst edition there has been a gr- ing interest not only for ACO, but for a number of other studies that belong more generally to the area of swarmintelligence. The rapid growth of the swarm intelligence ?eld is attested by a number of indicators. First, the number of s- missions and participants to the ANTS conferences has steadily increased over the years. Second, a number of international conferences in computational - telligence and related disciplines organize workshops on subjects such as swarm intelligence, ant algorithms, ant colony optimization, and particle swarm op- mization. Third, IEEE startedorganizing,in 2003,the IEEE SwarmIntelligence Symposium (in order to maintain unity in this growing ?eld, we are currently establishingacooperationagreementbetweenIEEE SISandANTSsoastohave 1 IEEE SIS in odd years and ANTS in even years). Last, the Swarm Intelligence journal was born.

The series of biannual international conferences “ANTS – International C- ference on Ant Colony Optimization and Swarm Intelligence”, now in its sixth edition, was started ten years ago, with the organization of ANTS’98. As some readers might recall, the ?rst edition of ANTS was titled “ANTS’98 – From Ant Colonies to Arti?cial Ants: First International Workshop on Ant Colony Op- mization. ” In fact, at that time the focus was mainly on ant colony optimization (ACO), the ?rst swarm intelligence algorithm to go beyond a pure scienti?c interest and to enter the realm of real-world applications. Interestingly, in the ten years after the ?rst edition there has been a gr- ing interest not only for ACO, but for a number of other studies that belong more generally to the area of swarmintelligence. The rapid growth of the swarm intelligence ?eld is attested by a number of indicators. First, the number of s- missions and participants to the ANTS conferences has steadily increased over the years. Second, a number of international conferences in computational - telligence and related disciplines organize workshops on subjects such as swarm intelligence, ant algorithms, ant colony optimization, and particle swarm op- mization. Third, IEEE startedorganizing,in 2003,the IEEE SwarmIntelligence Symposium (in order to maintain unity in this growing ?eld, we are currently establishingacooperationagreementbetweenIEEE SISandANTSsoastohave 1 IEEE SIS in odd years and ANTS in even years). Last, the Swarm Intelligence journal was born.

Metaheuristics are a relatively new but already established approachto c- binatorial optimization. A metaheuristic is a generic algorithmic template that can be used for ?nding high quality solutions of hard combinatorial - timization problems. To arrive at a functioning algorithm, a metaheuristic needs to be con?gured: typically some modules need to be instantiated and someparametersneedto betuned.Icallthese twoproblems"structural"and "parametric" tuning, respectively. More generally, I refer to the combination of the two problems as "tuning". Tuning is crucial to metaheuristic optimization both in academic research andforpracticalapplications.Nevertheless,relativelylittle researchhasbeen devoted to the issue. This book shows that the problem of tuning a me- heuristic can be described and solved as a machine learning problem. Using the machine learning perspective, it is possible to give a formal de?nitionofthetuningproblemandtodevelopagenericalgorithmfortuning metaheuristics.Moreover,fromthemachinelearningperspectiveitispossible tohighlightsome?awsinthecurrentresearchmethodologyandtostatesome guidelines for future empirical analysis in metaheuristics research.This book is based on my doctoral dissertation and contains results I have obtained starting from 2001 while working within the Metaheuristics Net- 1 work. During these years I have been a?liated with two research groups: INTELLEKTIK, Technische Universitat Darmstadt, Darmstadt, Germany and IRIDIA, Universite Libre de Bruxelles, Brussels, Belgium. I am the- fore grateful to the research directors of these two groups: Prof. Wolfgang Bibel, Dr. Thomas Stutzle, Prof. Philippe Smets, Prof. Hugues Bersini, and Prof. Marco Dorigo.

Stochastic local search (SLS) algorithms are established tools for the solution of computationally hard problems arising in computer science, business adm- istration, engineering, biology, and various other disciplines. To a large extent, their success is due to their conceptual simplicity, broad applicability and high performance for many important problems studied in academia and enco- tered in real-world applications. SLS methods include a wide spectrum of te- niques, ranging from constructive search procedures and iterative improvement algorithms to more complex SLS methods, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search, and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition. In recent years, it has become - creasingly evident that success with SLS algorithms depends not merely on the adoption and e?cient implementation of the most appropriate SLS technique for a given problem, but also on the mastery of a more complex algorithm - gineering process. Challenges in SLS algorithm development arise partly from the complexity of the problems being tackled and in part from the many - grees of freedom researchers and practitioners encounter when developing SLS algorithms. Crucial aspects in the SLS algorithm development comprise al- rithm design, empirical analysis techniques, problem-speci?c background, and background knowledge in several key disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics.

Stochastic local search (SLS) algorithms are established tools for the solution of computationally hard problems arising in computer science, business adm- istration, engineering, biology, and various other disciplines. To a large extent, their success is due to their conceptual simplicity, broad applicability and high performance for many important problems studied in academia and enco- tered in real-world applications. SLS methods include a wide spectrum of te- niques, ranging from constructive search procedures and iterative improvement algorithms to more complex SLS methods, such as ant colony optimization, evolutionary computation, iterated local search, memetic algorithms, simulated annealing, tabu search, and variable neighborhood search. Historically, the development of e?ective SLS algorithms has been guided to a large extent by experience and intuition. In recent years, it has become - creasingly evident that success with SLS algorithms depends not merely on the adoption and e?cient implementation of the most appropriate SLS technique for a given problem, but also on the mastery of a more complex algorithm - gineering process. Challenges in SLS algorithm development arise partly from the complexity of the problems being tackled and in part from the many - grees of freedom researchers and practitioners encounter when developing SLS algorithms. Crucial aspects in the SLS algorithm development comprise al- rithm design, empirical analysis techniques, problem-speci?c background, and background knowledge in several key disciplines and areas, including computer science, operations research, arti?cial intelligence, and statistics.

Metaheuristics are a relatively new but already established approachto c- binatorial optimization. A metaheuristic is a generic algorithmic template that can be used for ?nding high quality solutions of hard combinatorial - timization problems. To arrive at a functioning algorithm, a metaheuristic needs to be con?gured: typically some modules need to be instantiated and someparametersneedto betuned.Icallthese twoproblems"structural"and "parametric" tuning, respectively. More generally, I refer to the combination of the two problems as "tuning". Tuning is crucial to metaheuristic optimization both in academic research andforpracticalapplications.Nevertheless,relativelylittle researchhasbeen devoted to the issue. This book shows that the problem of tuning a me- heuristic can be described and solved as a machine learning problem. Using the machine learning perspective, it is possible to give a formal de?nitionofthetuningproblemandtodevelopagenericalgorithmfortuning metaheuristics.Moreover,fromthemachinelearningperspectiveitispossible tohighlightsome?awsinthecurrentresearchmethodologyandtostatesome guidelines for future empirical analysis in metaheuristics research.This book is based on my doctoral dissertation and contains results I have obtained starting from 2001 while working within the Metaheuristics Net- 1 work. During these years I have been a?liated with two research groups: INTELLEKTIK, Technische Universitat Darmstadt, Darmstadt, Germany and IRIDIA, Universite Libre de Bruxelles, Brussels, Belgium. I am the- fore grateful to the research directors of these two groups: Prof. Wolfgang Bibel, Dr. Thomas Stutzle, Prof. Philippe Smets, Prof. Hugues Bersini, and Prof. Marco Dorigo.

These proceedings contain the papers presented at ANTS 2010, the 7th Int- national Conference on Swarm Intelligence, organized by IRIDIA, CoDE, U- versiteLibre de Bruxelles,Brussels, Belgium, during September 8-10,2010.The ANTS series started in 1998 with the First International Workshop on Ant Colony Optimization (ANTS 1998), which attracted more than 50 participants. Since then ANTS, which is held bi-annually, has gradually become an inter- tional forum for researchers in the wider ?eld of swarm intelligence. In the past (since 2004), this development has been acknowledged by the inclusion of the term"SwarmIntelligence" (nextto"AntColonyOptimization")intheconference title. This year's ANTS conference was o?cially devoted to the ?eld of swarm intelligence as a whole, without any bias towards speci?c research directions. As a result, the title of the conference was changed to "The International Conf- ence on SwarmIntelligence." This name change is already in place this year,and future ANTS conferences will continue to use the new title. Thisvolumecontainsthebestpapersselectedoutof99submissions.Ofthese, 28 were accepted as full-length papers, while 27 were accepted as short papers.This corresponds to an overall acceptance rate of 56%. Also included in this volume are 14 extended abstracts. Of the full-length papers, 15 were selected for oral presentation at the c- ference. All other contributions, including short papers and extended abstracts, werepresentedin the formof poster presentations.Following the conference,the journal Swarm Intelligence will publish extended versions of some of the best papers presented at the conference.

This book constitutes the proceedings of the 8th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2012.This volume contains 15 full papers, 20 short papers, and 7 extended abstracts carefully selected out of 81 submissions. The papers cover various topics of swarm intelligence.

This book constitutes the proceedings of the 8th International Conference on Swarm Intelligence, held in Brussels, Belgium, in September 2012.This volume contains 15 full papers, 20 short papers, and 7 extended abstracts carefully selected out of 81 submissions. The papers cover various topics of swarm intelligence.