IEEE Toronto Section

IEEE

Achieving Balance Between Convergence and Diversity in Evolutionary Multiobjective Optimization

Monday, April 23rd at 10:00 a.m., Dr. Kwong Tak Wu Sam, Professor, City University of Hong Kong, will be presenting “Achieving Balance Between Convergence and Diversity in Evolutionary Multiobjective Optimization”.

Day & Time: Monday, April 23rd, 2018
10:00 a.m. ‐ 11:00 a.m.

Speaker: Dr. Kwong Tak Wu Sam, Professor
City University of Hong Kong

Location: UOIT (2000 Simcoe Street North, Oshawa L1H7K4 ON)
Room: UA2130

Contact: hossam.gabbar@ieee.org

Abstract: Nowadays, many real world problems are multi-objective in nature in the sense that multiple conflicting criteria need to be optimized simultaneously. As a consequence, instead of a global optimal solution in the case of single-objective optimization, usually, the optimum of multi-objective optimization corresponds to a set of so called Pareto optimal solutions for which no solutions can win in all objectives, due to the conflict between objectives. Evolutionary Multi-objective Optimization (EMO) algorithms have been widely used in practice for solving these multi-objective optimization problems for several reasons. At first, EMO approaches can tackle problems with nonlinear, non-differentiable, or noisy objective functions. Secondly, the population based search manner opens new opportunities in dealing with multi-objective optimization problems by searching for multiple alternatives simultaneously. Therefore, EMO has become one of the most active research areas in evolutionary computation. In this talk, I will first give an in–depth introduction to the EMO field and subsequently presented ourrecent developments which are 1) Adaptive Operator Selection (AOS)aims to provide the on-line autonomous control of the operator that should be applied at each instant of the search.This work proposes a bandit based AOS method, Fitness-Rate-Rank-based Multi-Armed Bandit (FRRMAB) to track the dynamics of the search process, it uses a sliding window to record the recent fitness improvement rates achieved by the operators, while employing a decaying mechanism to increase the selection probability of the best operator. Our experimental results demonstrate that FRRMAB is robust and its operator selection is reasonable,and 2) Asimple and effective stable matching (STM) model to coordinate the selection processinMultiobjective Evolutionary Algorithm based on DecompositionMOEA/D. In this model, subproblem agents can express their preferences over the solution agents, and vice versa. The stable outcome produced by the STM model matches each subproblem with onesingle solution, and it tradeoffs convergence and diversity of the evolutionary search. In addition, a two-level stable matching-based selection is proposed to further guarantee the diversity of the population. More specifically, the first level of stable matching only matches a solution to one of its most preferred subproblems and the second level of stable matching is responsible for matching the solutions to the remaining subproblems. Experimental studies demonstrate that the proposed selection scheme is effective and competitive comparing to other state-of-the-art selection schemes for MOEA/D.In both works, the techniques for achieving balance between convergence and diversity in evolutionary multiobjective optimizationare presented.

Biography: Sam Kwong received the B.Sc. degree from the State University of New York at Buffalo, Buffalo, NY, in 1983, the M.A.Sc. degree in electrical engineering from the University of Waterloo, Waterloo, ON, Canada, in 1985, and the Ph.D. degree from the Fernuniversität Hagen, Hagen, Germany, in 1996. From 1985 to 1987, he was a Diagnostic Engineer with Control Data Canada, where he designed the diagnostic software to detect the manufacture faults of the VLSI chips in the Cyber 430 machine. He later joined the Bell Northern Research Canada as a Member of Scientific Staff, where he worked on both the DMS-100 voice network and the DPN-100 data network project. In 1990, he joined the City University of Hong Kong as a Lecturer in the Department of Electronic Engineering. He iscurrently an Associate Professor in the Department of Computer Science. He was responsible of the software design of the first handheld GSM mobile phone consultancy project in which it was one of the largest consultancy projects at the City University of Hong Kong in 1996. He coauthored three research books on genetic algorithms, eight book chapters, and over 200 technical papers. He has been a consultant to several companies in telecommunications. Prof. Kwong was awarded the Best Paper Award for his paperentitled “Multiobjective Optimization of Radio-to-Fiber Repeater Placement Using a Jumping Gene Algorithm” at the IEEE International Conference on Industrial Technology (ICIT’05), Hong Kong, in 2005. In addition, he received the Best Paper Award at the 1999 BioInformatics Workshop, Tokyo, for the paper entitled “A Compression Algorithm for DNA Sequences and Its Application in Genome Comparison” in recognition of his outstanding contribution to the conference. Currently, he is the Associate Editor for the IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, the IEEE TRANSACTIONS ON INDUSTRIAL electronics, IEEE transactions on Evolutionary Computation, the Journal of Information Science. Currently, he is the Head and Professor of the department of Computer Science, City University of Hong Kong. Prof. Kwong was elevated to IEEE fellow for his contributions on Optimization Techniques for Cybernetics and Video coding in 2014.

Comments are closed.