CEC 2013 Fiesta Americana Grand Coral Beach Hotel Grand Coral Ballroom Chichen Itza and Tulum Isla Contoy Isla Mujeres Ruinas del Rey Cozumel and Hel-Ha Kayaking and Windsurfing Tres rios and Actun Chen


Opposition-Based Soft Computing

Dr. Shahryar Rahnamayan
Department of Electrical, Computer, and Software Engineering
Faculty of Engineering and Applied Science
University of Ontario Institute of Technology (UOIT)

Opposition-Based Soft Computing

Dr. Hamid R. Tizhoosh
Department of Systems Design Engineering
University of Waterloo


Footprints of the opposition concept can be observed in many areas around us. But it has sometimes been known by different names. Opposite particles in physics, complement of an event in probability, absolute or relative complement in set theory, and thesis and antithesis in dialectic just are some examples to mention. But for the first time, recently, Opposition-Based Learning (OBL) was proposed and then the opposition-based approaches have been introduced in variant soft computing areas. All of them have tried to enhance optimization or leaning process by utilizing an opposition scheme. Opposition-based evolutionary algorithms, opposition-based neural networks, and also opposition-based reinforcement learning are some efforts in this direction. Since 2005, more than 150 papers have been published about the opposition-based algorithms; which have been received more than 1500 citations so far.

This tutorial will introduce Opposition-Based Computation (OBC) in general and also its possible variant applications in enhancing soft computing techniques, such as evolutionary computation, fuzzy systems, reinforcement learning, and artificial neural networks. In this tutorial, well-designed demos will be presented to visualize that how opposition-based approaches work and accelerate convergence rate. The presentation would be fully interactive to cover all related experiments, mathematical proofs, and intuitive explanations of the opposition-based schemes and methods, such as ODE, OANN, OACO, OSA, and OPSO. This tutorial is highly beneficial to all researchers who try to enhance the performance of the soft computing techniques using recently proposed successful opposition-based learning schemes.

Outline of the contents:

                  - Introduction to Opposition-Based Learning (OBL)
                  - Opposite Versus Pure Random Points
                  - Mathematical, Simulation-based, and Intuitive-based Explanation of OBL
                  - Type I and Type II Oppositions with Corresponding Applications
                  - Variant Type I Opposition Schemes
                  - Opposition-Based Soft Computing: ODE, OPSO, OACO, OANN, OABC, OBBO, OPILA
                  - OBL and Multi-Objective Optimization
                  - Not Explored Objectives Beyond Acceleration
                  - OBL’s Real-world Applications
                  - Challenges and Open to Research Directions


Dr. Shahryar Rahnamayan received his B.Sc. and M.S. degrees both with honors in software engineering. In 2007, he received his Ph.D. degree in the field of evolutionary computation from University of Waterloo (UW), Canada. The opposition-based differential evolution (ODE) was proposed in his PhD thesis and received more than 350 citations since 2008. Inspired from ODE, more than 100 papers have been published. Before joining to the faculty of engineering and applied science, University of Ontario Institute of Technology (UOIT), Canada, as a tenure-track faculty member, he was a postdoctoral fellow at Simon Fraser University (SFU), Canada. His research includes evolutionary algorithms, image processing, artificial intelligent, and opposition-based soft computing. Dr. Rahnamayan was awarded the Ontario Graduate Scholarship (OGS), President’s Graduate Scholarship (PGS), NSERC’s Japan Society for the Promotion of Science (JSPS) Fellowship, NSERC’s Industrial R&D Fellowship (IRDF), NSERC’s Visiting Fellowship in Canadian Government Laboratories (VF), and the Canadian Institute of Health Research (CIHR) Fellowship for two times. He has published more than 75 papers, received more than 850 citations.


Dr. Hamid Tizhoosh received the M.S. degree in electrical engineering with a major in computer science from University of Technology, Aachen, Germany, in 1995. From 1993 to 1996, he worked at Management of Intelligent Technologies Ltd., Aachen, Germany in the field of industrial image processing. Dr. Tizhoosh received his Ph.D. degree from University of Magdeburg, Germany, in2000 with the subject of fuzzy processing of medical images. Dr. Tizhoosh was active as the scientist in the engineering department of IPS (Image Processing Systems Inc., now PhotonDynamics), Markham, Canada, until 2001. For six months, he visited the Knowledge/Intelligence Systems Laboratory, University of Toronto, Canada. Since September 2001, he is a faculty member at the department of Systems Design Engineering, University of Waterloo, Canada. At the same time, he has been the Chief Technology Officer and Chief Executive Officer of Segasist Technologies, a software company (Toronto, Canada) developing innovative software for medical image analysis. His research encompasses machine intelligence and computer vision. Dr. Tizhoosh has extensive experience in medical imaging including x-ray, magnetic resonance and ultrasound imaging. Dr. Tizhoosh is the author of two books, 14 book chapters, and more than 100 journal/conference papers.


The length of the tutorial:
two hours.


Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer