Plenary Speakers
Collective Neurodynamic Optimization: A New Paradigm of Hybrid Intelligence
[Abstract] The past three decades witnessed the birth and growth of neurodynamic optimization which has emerged and matured as a powerful approach to real-time optimization due to its inherent nature of parallel and distributed information processing and the hardware realizability. Despite the success, almost all existing neurodynamic approaches work well only for convex and generalized-convex optimization problems with unimodal objective functions. Effective neurodynamic approach to constrained global optimization with multimodal objective functions is rarely available. In the meantime, population-based evolutionary and similar nature-inspired approaches emerged as prevailing methods for global optimization with many success stories in benchmark studies. Nevertheless, the heuristic and stochastic natures of their algorithms may limit their theoretical underpinnings. Both neurodynamic and evolutionary optimization approaches have their merits and limitations. For example, neurodynamic approaches are good at constrained and precise local search with proven convergence, but prone to trapping at local minima; whereas evolutionary-like approaches are good at global search, but weak at constraint handling and guaranteed optimality. Given the pros and cons of the two types of computationally intelligent optimization methods, it is natural to integrate them into ones toward hybrid intelligence. In this talk, starting with the idea and motivation of neurodynamic optimization, I will review the historic review and present the state of the art of neurodynamic optimization with many models for convex and generalized convex optimization. In particular, I will present a new population-based neurodynamic approach to constrained global optimization in the presence of nonconvexity. By deploying a population of neurodynamic models at a lower level coordinated by using some information exchange rules (such as PSO) at a upper level, it will be shown that many constrained global optimization problems could be solved effectively and efficiently. [Biography] Jun Wang is a Professor and the Director of the Computational Intelligence Laboratory in the Department of Mechanical and Automation Engineering at the Chinese University of Hong Kong. Prior to this position, he held various academic positions at Dalian University of Technology, Case Western Reserve University, and University of North Dakota. He also held various short-term visiting positions at USAF Armstrong Laboratory (1995), RIKEN Brain Science Institute (2001), Huazhong University of Science and Technology (2006–2007), and Shanghai Jiao Tong University (2008-2011) as a Changjiang Chair Professor. Since 2011, he is a National Thousand-Talent Chair Professor at Dalian University of Technology on a part-time basis. He received a B.S. degree in electrical engineering and an M.S. degree in systems engineering from Dalian University of Technology, Dalian, China. He received his Ph.D. degree in systems engineering from Case Western Reserve University, Cleveland, Ohio, USA. His current research interests include neural networks and their applications. He published over 170 journal papers, 15 book chapters, 11 edited books, and numerous conference papers in these areas. He is the Editor-in-Chief of the IEEE Transactions on Cybernetics since 2014 and a member of the editorial board of Neural Networks since 2012. He also served as an Associate Editor of the IEEE Transactions on Neural Networks (1999-2009), IEEE Transactions on Cybernetics and its predecessor (2003-2013), and IEEE Transactions on Systems, Man, and Cybernetics – Part C (2002–2005), as a member of the editorial advisory board of International Journal of Neural Systems (2006-2013), as a guest editor of special issues of European Journal of Operational Research (1996), International Journal of Neural Systems (2007), Neurocomputing (2008, 2014), and International Journal of Fuzzy Systems (2010, 2011). He was an organizer of several international conferences such as the General Chair of the 13th International Conference on Neural Information Processing (2006) and the 2008 IEEE World Congress on Computational Intelligence, and a Program Chair of the IEEE International Conference on Systems, Man, and Cybernetics (2012). He has been an IEEE Computational Intelligence Society Distinguished Lecturer (2010-2012, 2014-2016). In addition, he served as President of Asia Pacific Neural Network Assembly (APNNA) in 2006 and many organizations such as IEEE Fellow Committee (2011-2012); IEEE Computational Intelligence Society Awards Committee (2008, 2012, 2014), IEEE Systems, Man, and Cybernetics Society Board of Directors (2013-2015), He is an IEEE Fellow, IAPR Fellow, and a recipient of an IEEE Transactions on Neural Networks Outstanding Paper Award and APNNA Outstanding Achievement Award in 2011, Natural Science Awards from Shanghai Municipal Government (2009) and Ministry of Education of China (2011), and Neural Networks Pioneer Award from IEEE Computational Intelligence Society (2014), among others. |
Advances in Intelligent Situation Assessment with Application to Connected Vehicular Network System [Abstract] Drivers distraction has been shown to be the main cause in road accidents making it a major issue in designing safer driving environment for next generation connected car systems. In this presentation, we propose a comprehensive framework to address the problem of road safety by tackling it from a high-level information fusion standpoint, considering the Vehicular Ad-hoc Networks (VANET) as the deployment platform. The proposed framework relies on the Multi-Entity Bayesian Networks (MEBN), which exploits the expressiveness of ?rst-order logic for semantic relations, and the strength of the Bayesian networks in handling uncertainty for purposes of driving situation assessment. To model inherent conceptual and structural ambiguity, which would represent certain type of entity relationship, a fuzzy logic extension of the MEBN, is also proposed. To demonstrate and assess the capabilities of the proposed framework, a collision warning system simulator has been developed. It evaluates the likelihood of a vehicle being in a near-collision situation using a wide variety of local and global information sources typically available in VANET environment. Experimental results for two driving scenarios mimicking near-collision situations demonstrate the capability of the proposed framework to achieve accurate situation assessment on the road. [Biography] FAKHREDDINE KARRAYis the University Research Chair Professor in Electrical and Computer Engineering and co-Director of the Center for Pattern Analysis and Machine Intelligence Center at the University of Waterloo, Canada. He received the Ing. Dip (EE), degree from ENIT, Tunisia and the PhD degree from the University of Illinois, Urbana Champaign, USA. Dr. Karray’s research interests are in the areas of intelligent systems, soft computing, sensor fusion, and context aware machines with applications to intelligent transportation systems, cognitive robotics and natural man- machine interaction. He has (co)authored over 350 technical articles, a textbook on soft computing and intelligent systems, five edited textbooks and 18 textbook chapters. He holds 16 US patents. He has supervised the work of more than 58 PhD and M.Sc students and has served in the PhD committee of more than 65 PhD candidates. He has chaired/co-chaired 14 international conferences in his area of expertise and has served as keynote/plenary speaker on numerous occasions. He has also served as the associate editor/guest editor for more than 12 journals, including the IEEE Transactions on Cybernetics, the IEEE Transactions on Neural Networks and Learning, the IEEE Transactions on Mechatronics, the IEEE Computational Intelligence Magazine. He is the Chair of the IEEE Computational Intelligence Society Chapter in Kitchener-Waterloo, Canada. |