Human Assisted Learning by Evolutionary Multi-Objective Optimization

Contents 1. Introduction 2. Evolutionary Multi-objective Optimization (EMO) 3. A Brief Time-line of the Development of EMO Methodologies 4. Elitist EMO: NSGA-II 5. Applications of EMO 6. Recent Developments in EMO 7. Conclusions Acknowledgments Glossary Bibliography Biographical Sketch Summary In the past three decades, evolutionary algorithms (EAs) have been found to be extremely useful in solving various search and optimization problems. Although much of the early advancements and applications concentrated in solving single-objective optimization problems, researchers realized the potential and niche of EAs is handling multi-objective optimization problems vis-a-vis their classical counterparts. Suggested in the beginning of nineties, evolutionary multi-objective optimization (EMO) algorithms are now routinely used in solving problems with multiple conflicting objectives in various branches of engineering, science and commerce. In this chapter, we provide an overview of EMO methodologies by first presenting principles of EMO through an illustration of one specific algorithm and its application to an interesting real-world bi-objective optimization problem. Thereafter, we provide a list of recent research and application developments of EMO to provide a picture of some salient advancements in EMO research. The development and application of EMO to multiobjective optimization problems and their continued extensions to solve other related problems has elevated the EMO research to a level which may now undoubtedly be termed as an active field of research with a wide range of theoretical and practical research and application opportunities. Hopefully, this chapter should motivate readers to pay more attention to their growing field of evolutionary multi-objective optimization methods and their scopes in practice.