Centre for Intelligent Systems Research

IEEE Logo  SMC Victorian Chapter

Upcoming Event

IEEE SMC Victorian Chapter - Lecture - Dr John Mashford

Date: Monday 30 March 2015
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Dr John Mashford, CSIRO

  • Title: MCV: A (semi-)hierarchical image labelling technique utilising MRF image models
  • Biography: 

    John Mashford studied Mathematics, Physics and Philosophy at Melbourne University between 1975 and 1979 where obtained a BSc.(Hons.) degree. In 1980 he worked for the engineering company Nelson English, Loxton and Andrews. Between 1981 and 1984 he studied Mathematics at the State University of New York at Stony brook concentrating on Differential Geometry and Analysis (with a 7 month break living in Paris). He commenced working for CSIRO full time in July, 1985. He completed his PhD on mathematical physics part time at Melbourne University, while working full time for CSIRO, between 1992 and 2005. He ceased working for CSIRO full time in November 2014 and is currently a consultant mathematician. He has programmed in FORTRAN, C, C++, Lisp, PROLOG and Java and is familiar with the DOS, Windows and UNIX operating systems. His CSIRO research has been in the areas of operations research, artificial intelligence and mathematical modelling concentrating specifically on computer vision. He has published more than 40 papers and is a member of IEEE and ACM. He invented and implemented a method for rail route optimisation which resulted in a multimillion dollar CSIRO spinoff company and was awarded the Australian Technology Award, and also the MCV image labelling algorithm which is currently being run on CSIRO supercomputers for remote sensing applications.

  • Abstract: 

    In this talk the MCV (Markov concurrent vision) image labeling algorithm is described. This algorithm is a (semi-) hierarchical algorithm commencing with a partition made up of single pixel regions and merging regions or subsets of regions using a Markov random field (MRF) image model. It is an example of a general approach to computer vision called concurrent vision in which the operations of image segmentation and image classification are carried out concurrently. The output of the MCV algorithm can be a simple segmentation partition or a sequence of partitions which can provide useful information to higher level vision systems. In the case of an autoregressive Gaussian MRF the evaluation of sub-images for homogeneity is computationally inexpensive and may be effected by a hardwired feed-forward neural network. The merge operation of the algorithm is massively parallelizable.

Further Event Details (77 KB)

Event Registration

For catering purposes, please register for the event here: IEEE SMC Event Registration Page

For more information on this event, please contact: Trish O'Toole
Email: trish.otool@deakin.edu.au, Phone: +61 3 5227 1352

How do I get to CISR?

Centre for Intelligent Systems Research
Building na
Deakin University
Geelong Waurn Ponds Campus
75 Pigdons Road
Waurn Ponds, Victoria 3216

Directions to CISR (757 KB)

View Larger Map

Past Events

IEEE SMC Victorian Chapter - Lecture - Associate Professor Chee-Peng Lim

Date: Monday 2 March 2015
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Associate Professor Chee-Peng Lim, Centre for Intelligent Systems Research, Deakin University

  • Title: Computational Intelligence-based Systems: Architectures, Algorithms, and Applications
  • Biography: 

    Chee-Peng Lim's research interests include design and development of computational intelligence-based systems for pattern classification, data mining, condition monitoring, medical prognosis and diagnosis, manufacturing process optimization and decision support. He collaborates closely with researchers in the international arena, whereby he received the Australia-India Senior Visiting Fellowship, 2013 (by Australian Academy of Science), Australia-Japan Emerging Research Leaders Exchange Program, 2013 (by Australian Academy of Technological Sciences and Engineering), Australia Endeavour Executive Award, 2009, Commonwealth Fellowship, 2003 (University of Cambridge, UK); Fulbright Scholarship, 2002 (University of California, Berkeley, USA). To date, he has published more than 270 technical papers in journals, conference proceedings, and books, received 7 best paper awards, edited 3 books and 12 special issues in journals, and served in the editorial board of 5 international journals.

  • Abstract: 

    In this information age, the usefulness and applicability of computerised intelligent systems in deriving knowledge enterprise is well-recognised. As an example, search and advertising tools of Google provided $111 billion to economic activities of the USA in 2013. Computational intelligence is a broad discipline that encompasses many different methodologies inspired by human and/or animal intelligence. In this lecture, the benefits of utilising computational intelligence for designing and developing computerised intelligent systems are exemplified. Different architectures and algorithms of individual and hybrid computational intelligence models, which include artificial neural networks, fuzzy systems, and evolutionary algorithms, are explained. Applications of such computational intelligence-based systems to a number of real-world problems are demonstrated.

Further Event Details (77 KB)

IEEE SMC Victorian Chapter - Lecture - Associate Professor Marcus Watson

Date: Wednesday 11 February 2015
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Associate Professor Marcus Watson, Schools of Medicine & Psychology, The University of Queensland; Executive Director, Queensland Health Clinical Skills Development Service

  • Title: Building Effective Simulation Programs: Going Beyond Education to Design Better Healthcare Delivery
  • Biography: 

    A/Prof Marcus Watson is the Executive Director of the Clinical Skills Development Service, Australia's largest healthcare educational and research simulation program distributed across Queensland. He is an Associate Professor of Medical Education in the School of Medicine and an Honorary Associate Professor in the School of Psychology at The University of Queensland. He has extensive knowledge of simulations and human factors in both healthcare and defence. He has experience as a developer and instructor working with computer based simulation, high end immersive simulation, serious games and distributed learning. Marcus is a contributor to the HWA NHET-Sim program and the Chair of the Board of Simulation Australia. Marcus instructs on a range of workshops including simulations development, serious games, online learning and human factors in healthcare. He has received national awards for innovation and the Jerome Ely Award for the Best Paper in Human Factors for 2004.

  • Abstract: 

    The use of simulations in healthcare is not new; however, changes in the way we deliver care and accumulating research into the effectiveness of simulations is increasing the application of simulations internationally. Healthcare simulations is transitioning from a focus on individual clinical skills to the application of simulations to develop clinical teams and even the redesign systems. The growth over the last five years has been dramatic yet many healthcare organisations are struggling to efficiently implement large-scale simulations programs. Examples of effective programs from the literature will be used to examine why simulations can achieve such large effects. The discussion will also cover how simulation can be used to reduce training requirements and improve patient care by using simulation to understand and test processes of care.

Further Event Details (76 KB)

IEEE SMC Victorian Chapter - Lecture - Associate Professor Neil McLachlan

Date: Monday 9 February 2015
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Associate Professor Neil McLachlan, Melbourne School of Psychological Sciences, Melbourne University

  • Title: Neuromorphic Approaches to Computing Acoustic Information
  • Biography: 

    Dr McLachlan is an Associate Professor in Psychological Sciences at The University of Melbourne and has broad professional experience in music, acoustic design, engineering, and auditory neuroscience. In 2000 he designed the World's first harmonic bells, and more recently has designed a new harmonic percussion ensemble for use in educational and a range of community contexts. To establish better design criteria for musical instrument design he has developed the first end-end neurobiological model of auditory processing. He has computationally implemented aspects of this model leading to the development of new sound segregation and recognition algorithms for hearing prosthetics and automated sensing systems.

  • Abstract: 

    During the 1890's Ivan Pavlov observed that dogs could be conditioned to salivate at the sound of a bell. The association of conditioned stimuli to behaviours has been studied in a wide range of animals for over a century, however practically no research has been undertaken on how animals learn to recognize sounds in the first place. This is important because sound recognition likely occurs early in auditory processing, and underpins most other auditory functions. Previous research has shown that conditioned reflexive responses to sound involve ponto-cerebellar pathways, and so these pathways likely underpin sound recognition more generally. High level computational models of these pathways have been used to recognize human speech, music, environmental sounds and animal calls, and to act as adaptive filters for integrating pitch and loudness information. This paper will outline a new neurocognitive account of the auditory pathways and provide examples of computational algorithms based on this model. More broadly, it will discuss the possibility that neuro-cognition based on memory processes may provide the operating systems for future generations neuromorphic computers based on memsistors. These computers will learn and adapt to natural environments just like animals, but can "inherit" (or share) their sense memories from other computers at any time.

Further Event Details (76 KB)

IEEE SMC Victorian Chapter - Lecture - Dr. John Wang

Date: Wednesday 17 December 2014
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Dr. John Wang, Senior Research Scientist, DSTO

  • Title: Assessment of Memory Cushions in Aircraft Seating for Injury Mitigation through Dynamic Impact Test
  • Biography: 

    John Wang received his B.E. ('82) and M.E. ('86) in mechanical engineering from Shanghai Polytechnic University. He taught Mechanical Engineering at Tongji University, Shanghai from 1982 to 1988, being promoted to lecturer in 1987. With the full financial support of the Australian Government John studied at the Asian Institute of Technology (AIT) from 1988 to 1991, where he received his PhD. Dr Wang then worked at AIT as a research engineer and concurrently Consultant Engineer for Thai companies. Relocating to Australia, John was a Visiting Fellow at the University of New South Wales (UNSW) in early 1992 before joining United Air Specialists Pty Ltd, as a mechanical engineer. From 1993 to 1999 John worked at UNSW initially as a post-doctoral fellow and later ('98) was promoted to senior research officer. John joined Weapons Systems Division, DSTO in 1999 as a research scientist and has since 2002 been working at Air Vehicle/Aerospace Division, DSTO as a senior research scientist. His research has covered several areas, including elastic-hydrodynamic lubrication, soil mechanics, mechanical vibration, rotor-bearing-foundation dynamics, machine design and development, application of finite element method, vehicle and occupant protection against landmines/crask impacts, and advanced composite materials and structures. John has over 150 book chapter, journal, conference and research report publications. John has been co-supervisor for PhD students (currently has two PhD students at Monash University) and external examiner for 7 PhD theses. John has been manager for DSTO and CRC-ACS research tasks/projects since 2004. John's experience also includes one year senior leadership position as short term/acting group head.

  • Abstract: 

    It has been indicated in literature that Visco-Elastic Polyurethane (VEPU) foam cushions is promising for aircraft seat applications as an effective means to reduce impact force to the occupant, however, very limited research work in this area has been reported. In addition, no any literature is available regarding full-scale drop testing where the VEPU cushions together with seat stroke energy absorbing mechanism are used. The Deference Science and Technology Organisation (DSTO) and Cooperative Research Centre for Advanced Composite Structures (CRC-ACS) with support from Crashlab, Roads and Maritime Services (RMS), New South Wales (NSW), have conducted a series of drop tests at three levels, namely large coupon material level tests, full scale tests with a FAA Hybrid III crash dummy and a rigid seat, and full scale tests with a FAA Hybrid III crash dummy and stroke seats. The coupon tests were used to compare and select candidate VEPU foam materials. The full scale tests were conducted to determine the effectiveness of the VEPU foam cushions (with different densities/stiffness) in reducing the level of force transmitted to the occupant of a seat with or without a stroke mechanism respectively, during an aircraft crash. The test methods and results of the full scale drop tests will be provided in this talk. In addition, a brief introduction will also be provided about some related work conducted at DSTO and CRC-ACS, such as computational modelling, research on temperature effect of the VEPU cushions, as well as some earlier research on land vehicle seat cushions.

Further Event Details (83 KB)

IEEE SMC Victorian Chapter - Lecture - Dr. Andrew Maher

Date: Tuesday 25 November 2014
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Dr. Andrew Maher, Leader R & D Programme, Arup's Australasian Offices

  • Title: New Technologies for Understanding Performance of the Built Environment and a Perspective on Development Through Corporate Research
  • Biography: 

    Dr Andrew Maher leads the internal research and development programme for Arup's Australasian offices. He is an architect with an interest in digital technologies whose experience has helped establish leadership in new technologies as the firm increasingly introduces digital innovation into its ways of working. He has a keen interest in research and development, innovation and commercialisation and introduces new digital services to through Arup Digital - digital.Arup.com and the innovation blog fieldsofactivity.com

    Arup in Australasia - Arup is the creative force at the heart of many of the world's most prominent projects in the built environment. From more than 90 offices in over 38 countries, over 12,000 planners, designers, engineers and consultants deliver innovative projects across the world with creativity and passion. Arup established a presence in Australasia over 50 years ago when entrusted with the structural design of the Sydney Opera House. The firm opened its first office in Sydney in 1963. There are now over 1,300 staff working from 12 offices across Australia, Singapore, Indonesia and New Zealand.

  • Abstract: 

    New technologies are being rapidly deployed for the built environment to better and more broadly understand the built environment from instrumenting buildings to measure actual environmental performance to monitoring human behaviour for life safety. Much of the innovative research for this work is undertaken in collaboration with universities.

    In this talk, various examples of new technologies will be shown and a perspective will be given on how research and development for new technology is developed within a corporate structure and how collaboration with universities is central to its success.

Further Event Details (76 KB)

IEEE SMC Victorian Chapter - Lecture - Dr. Kim Hua Tan

Date: Monday 20 October 2014
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Dr. Kim Hua Tan, Reader in Lean Operations and Supply Management, Nottingham University Business School, England

  • Title: Harvesting Big Data to Enhance Supply Chain Innovation Competence Set
  • Biography: 

    Dr. Kim Hua Tan is a Reader in Lean Operations and Supply Management at Nottingham University Business School. Prior to this, he was a researcher and teaching assistant at Centre for Strategy and Performance, University of Cambridge. Dr. Tan spent many years in industry, holding various executive positions before joining academia in 1999. His current research interests are lean management, operations strategy, big data, food supply chain risk management, and sustainable manufacturing. Dr. Tan has published a book called 'Winning Decisions: Translating Business Strategy into Action Plans,' and numerous articles in academic journals such as Decision Sciences, International Journal of Production Economics, International Journal of Innovation Management, and others.

  • Abstract: 

    Today, firms can access to big data (videos, tweets, and other unstructured sources) to extract new ideas or understanding about their products, customers, and markets. Thus, managers increasingly view data as an important driver of innovation and a significant source of value creation and competitive advantage. To get the most out of the big data (in combination with a firm's existing data), a more sophisticated way of handling, managing, analysing and interpreting data is necessary. However, there is a lack of data analytics techniques to assist firms to capture the potential of innovation afforded by data and to gain competitive advantage. This research aims to address this gap by developing and testing an analytic infrastructure based on the deduction graph technique. The proposed approach provides an analytic infrastructure for firms to incorporate their own competence sets with other firms. Case studies results indicate that the proposed data analytic approach enable firms to utilise big data to gain competitive advantage by enhancing their supply chain innovation capabilities.

Further Event Details (77 KB)

IEEE SMC Victorian Chapter - Lecture - Professor Xinghuo Yu

Date: Wednesday 1 October 2014
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Professor Xinghuo Yu, IEEE Fellow, Director, RMIT Platform Technologies Research Institute

  • Title: Discontinuous Control Systems: Past, Present and Future
  • Biography: 

    Professor Xinghuo Yu is the Founding Director of RMIT Platform Technologies Research Institute. His research interests include variable structure and nonlinear control, complex and intelligent systems and industrial applications. He has published over 500 refereed papers in technical journals, books and conference proceedings. Professor Yu has served as an Associate Editor of IEEE Transactions on Circuits and Systems - Part I, IEEE Transactions on Industrial Informatics, IEEE Transactions on Industrial Electronics and several other scholarly journals. He received a number of awards and honours for his achievements, including 2013 Dr.-Ing Eugene Mittelmann Achievement Award of IEEE Industrial Electronics Society and 2012 IEEE Industrial Electronics Magazine Best Paper Award. Professor Yu is a Fellow of the IEEE, Vice-President for Publications and an IEEE Distinguished Lecturer of IEEE Industrial Electronics Society. He is also a Fellow of the Institution of Engineers, Australia, the Institution of Engineering and Technology (UK), the Australian Computer Society and the International Energy Foundation.

  • Abstract: 

    Discontinuous control is a most effective approach to deliver fast and efficient actions to achieve desirable control objectives. However its analysis and design present some of the most difficult mathematical challenges. Various schools of thought have been developed over the last several decades to address the analysis and design issues, yet, none of them can provide a satisfactory solution across the spectrum of discontinuity.

    In this talk, we will first introduce the basics of discontinuous control systems. We will then examine the major schools of thoughts in dealing with discontinuity and the analysis and design of this class of systems, exploring inherent properties that distinguish them from the continuous control systems and outlining critical issues that hinder their developments. Future perspectives in theory and applications will be discussed.

Further Event Details (78 KB)

IEEE SMC Victorian Chapter - Lecture - Professor Dan Koditschek

Date: Wednesday 23 July 2014
Time: 9:30 am - 10:30 am
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Professor Dan Koditschek, Alfred Fitler Moore Professor, Electrical & Systems Engineering, School of Engineering & Applied Science, University of Pennsylvania

  • Title: Composition of Attractor Basins for Dexterous Robotic Tasks
  • Biography: 

    Daniel E. Koditschek is the Alfred Fitler Moore Professor of Electrical and Systems Engineering. Dr. Koditschek received his bachelor's degree in Engineering and Applied Science and his M.S. and Ph.D. degrees in Electrical Engineering in 1981 and 1983, all from Yale University. He served on the Yale Faculty in Electrical Engineering until moving to the University of Michigan a decade later. In January 2005, he moved to the University of Pennsylvania to assume the post of Chair of the Electrical and Systems Engineering Department, within the School of Engineering and Applied Science.

    Koditschek's research interests include robotics and, more generally, the application of dynamical systems theory to intelligent mechanisms. His archival journal and refereed conference publications, numbering well over 100, have appeared in a broad spectrum of venues ranging from the Transactions of the American Mathematical Society through The Journal of Experimental Biology, with a concentration in several of the IEEE journals and related transactions. Various aspects of this work have received mention in general scientific publications such as Scientific American and Science as well as in the popular and general lay press such as The New York Times and Discover Magazine. Dr. Koditschek is a member of the AMS, ACM, MAA, SIAM, SICB and Sigma Xi and is a Fellow of the IEEE and the AAAS.

    Koditschek holds secondary appointments within the School of Engineering and Applied Science in the departments of Computer and Information Science and Mechanical Engineering.

  • Abstract: 

    This talk reviews a two decade program of research in the design and implementation of modular controllers for dynamically dexterous robots. We seek to represent tasks by means of "templates:" low dimensional reference dynamics whose specified attractors encode goals and whose repelling boundaries represent obstacles or forbidden behaviors. General purpose machines typically have degrees of freedom unrelated to the needs of specific templates. Hence the most basic control module is an "anchor:" a feedback law that embeds the template as an attracting invariant submanifold in the machine's physical state space. Synthesis of more complicated behaviors from simpler constituents proceeds by sequential and parallel composition of templates. A correct synthesis is one for which the limit set of the anchored composition yields the desired composition of the template limit sets. After reviewing various instances of these ideas applied to the setting of steady state legged locomotion, the talk concludes with a preliminary look at the problem of encoding and implementing transitional tasks such as leaping across gaps and onto ledges.

Further Event Details (80 KB)

IEEE SMC Victorian Chapter - Lecture - Professor Toshio Fukuda

Date: Friday 18 July 2014
Time: 12:00 pm - 1:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Professor Toshio Fukuda, Honorary Professor (Deakin University), Beijin Institute of Technology, Nagoya University, Meijo University

  • Title: Multi-scale Robotics
  • Biography: 

    Toshio Fukuda received the B.A. degree from Waseda University, Tokyo, Japan, in 1971, and the M.S and Dr. Eng. from the University of Tokyo, Tokyo, Japan, in 1973 and 1977, respectively.

    In 1977, he joined the National Mechanical Engineering Laboratory. In 1982, he joined the Science University of Tokyo, Japan, and then joined Nagoya University, Nagoya, Japan, in 1989. He was Director of Center for Micro-Nano Mechatronics and Professor of Department of Micro-Nano Systems Engineering at Nagoya University, where he was mainly involved in the research fields of intelligent robotic and mechatronic system, cellular robotic system, and micro- and nano-robotic system. He was the Russell Springer Chaired Professor at UC Berkeley, Distinguished Professor, Seoul National University, and many other universities. Currently, He is Professor Emeritus Nagoya University, Visiting Professor Institute for Advanced Research Nagoya University, Professor Meijo University, Professor Beijin Institute of Technology.

    Dr. Fukuda is IEEE Region 10 Director (2013-2014) and served President of IEEE Robotics and Automation Society (1998-1999), Director of the IEEE Division X, Systems and Control (2001- 2002), and Editor-in-Chief of IEEE / ASME Transactions on Mechatronics (2000-2002). He was President of IEEE Nanotechnology Council (2002-2003, 2005) and President of SOFT (Japan Society for Fuzzy Theory and Intelligent Informatics) (2003-2005). He was elected as a member of Science Council of Japan (2008-). He received the IEEE Eugene Mittelmann Award (1997), IEEE Millennium Medal (2000), Humboldt Research Prize (2002), IEEE Robotics and Automation Pioneer Award (2004), IEEE Robotics and Automation Society Distinguished Service Award (2005), Award from Ministry of Education and Science in Japan (2005). IEEE Nanotechnology Council Distinguished service award (2007). Best Googol Application paper awards from IEEE Trans. Automation Science and Engineering (2007). Best papers awards from RSJ (2004) and SICE (2007), Special Funai Award from JSME (2008), 2009 George Saridis Leadership Award in Robotics and Automation (2009), IEEE Robotics and Automation Technical Field Award (2010), ROBOMECH Award 2010 (2010), The Society of Instrument and Control Engineers Technical Field Award (2010), IROS Harashima Award for Innovative Technologies (2011), Friendship Award of Liaoning Province PR China (2012), Distinguished Service Award, The Robotics Society of Japan (2010), World Automation Congress 2010 (WAC 2010) dedicated to Prof. Toshio Fukuda, Best Paper Award in 2010 International Symposium on Micro-Nano Mechatronics and Human Science (MHS2010), IEEE Fellow (1995), SICE Fellow (1995), JSME Fellow (2001), RSJ Fellow (2004), Honorary Doctor of Aalto University School of Science and Technology (2010).

  • Abstract: 

    This talk is an overview of the Multi-scale robotics, based on the Cellular Robotics System, which is the basic concept of the emergence of intelligence in a multi-scale way from Cell Level to the Organizational Level. It consists how the system can be structured from the individual to the group/society levels in analogy with the biological system. It covers a wide range of challenging topics:

    1. Individual robot level, Brachiation Robots and Multi-locomotion robots, medical robotics and simulator
    2. Cooperation and competition of the multiple robotics system
    3. Distributed autonomous robotic system
    4. Micro and nano robotics system
    5. Bio analysis and synthesis: bio-robotics system

Further Event Details (192 KB)

IEEE SMC Victorian Chapter - Tutorial - Dr Abbas Khosravi

Date: Monday 9 June 2014
Time: 12:00 pm - 1:00 pm
Location: Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia
Speaker: Dr Abbas Khosravi, Centre for Intelligent Systems Research, Deakin University

  • Title: Optimal design of type reduction algorithms for interval type-2 fuzzy logic systems
  • Biography: 

    Abbas Khosravi received the B.Sc. degree in electrical engineering from Sharif University of Technology, Tehran, Iran, in 2002, the M.Sc. degree in electrical engineering from Amirkabir University of Technology, Tehran, in 2005, and the Ph.D. degree from Deakin University, Australia, in 2010. Dr Khosravi is currently with the Centre for Intelligent Systems Research (CISR), Deakin University, Australia. He has authored/co-authored more than 80 publications in international journals and conference proceedings. His current research interests include computational intelligence and soft computing techniques and their application in various engineering problem domains. Dr Khosravi was the recipient of the Alfred Deakin Postdoctoral Research Fellowship in 2011.

  • Abstract: 

    Recent literature shows that interval type-2 fuzzy logic systems "IT2FLSs" possess an excellent approximation capability even better than traditional nonparametric methods such as neural networks "NNs". Type reduction "TR" is one of the key components of IT2FLSs with a huge impact on their performance. This research aims to comprehensively investigate and quantify effects of TR algorithms on the quality of forecasts generated by IT2FLS models. It also proposes a new nonparametric nonlinear TR algorithm that optimally generates the defuzzified model output directly from the firing strengths and consequent lower and upper values of each rule. The NN type reducer is trained through minimization of an error-based cost function using evolutionary optimization algorithms. Once the optimal NN-based type reducer is trained, IT2FLS models can be easily used in prediction and classification problems. Numerical testing using real datasets indicate IT2FLS models equipped with the new optimal TR algorithm outperform IT2FLS models using traditional TR algorithms in terms of forecast accuracy and consistency. This benefit is achieved in no cost, as the computational requirement of the proposed optimal TR algorithm is the same as traditional TR algorithms.

Further Event Details (97 KB)

IEEE SMC Victorian Chapter - Inaugural Lecture

Date: Monday 7 April 2014
Time: 5:00 pm - 7:00 pm
Location: Room na 1.418, GTP Building (Ground Floor), Centre for Intelligent Systems Research, Deakin University, Waurn Ponds, Geelong, Australia

5:00 - 5:05 pm - Opening and Welcome - Professor Saeid Nahavandi
5:05 - 5:10 pm - Anthony Gascoigne - Chair, IEEE Victorian Section
5:10 - 5:50 pm - Lecture - Professor Laslo T. Koczy - Budapest University of Technology and Economics, Hungary

  • Title: Fuzzy Signatures
  • Biography: 

    Professor and President of the University Research Council, Szechenyi Istvan University (SZE, Gyor) and Budapest University of Technology and Economics (BME) Hungary

    Laszlo Koczy received the M.Sc., M.Phil. and Ph.D. degrees from the Technical University of Budapest (BME) in 1975, 1976 and 1977, respectively; and the (postdoctoral) D.Sc. degree from the Hungarian Academy of Science, all in Electrical/Control Engineering. He spent most of his career at BME until 2001 and from 2002 at SZE. However, he has been a visiting professor at various universities abroad, namely in Australia (ANU, Murdoch and UNSW), Japan (TIT), Korea (POSTECH), Austria (J. Kepler U.), Italy (U. of Trento) and Brazil, China, Finland and Poland for summer schools. He was one of the LIFE Endowed Fuzzy Theory Chair Professors at Tokyo Institute of Technology and advisor to the Laboratory for International Fuzzy Engineering Research in Yokohama. His focus of research interest is fuzzy systems and Computational Intelligence topics (evolutionary algorithms, neural networks), as well as applications. He has published over 370 refereed papers and several textbooks on the subject. He introduced the concept of rule interpolation in sparse fuzzy models, and applied it successfully to the control of an automatic guided vehicle; further hierarchical interpolative fuzzy systems and fuzzy Hough transform. This latter provided the key technology in the winning vehicle in the 2007 Hungarian Mars Rover Competition. His research interests include applications of CI for telecommunication, transportation, vehicles and mobile robots, control, information retrieval, etc.

    Among others he had been an Associate Editor of IEEE TFS and he is an Associate Editor of Fuzzy Sets and Systems, Int. J. of Fuzzy Systems, J. of Advanced Computational Intelligence, Mathware and Soft Computing, etc.

    He was the General Chair of FUZZ-IEEE 2004 in Budapest, and a number of other conferences, co-chair, PC member, etc. at many other scientific events. He served in the International Fuzzy Systems Association as President, and is now Administrative Committee member of IEEE Computational Intelligence Society.

    At SZE he serves his second term as Dean of Engineering, he chairs the Ph.D. School Council and is one of the sponsors of the Szechenyi Alternative Fuel Engine Vehicles Competition, the National Conference of Mechanical Engineering Students, etc.

  • Abstract: 

    Fuzzy signatures (FS) are complex structured uncertain descriptors which are suitable for manipulations even when their respective actual structures are not entirely identical. This presentation will give an introduction to the definitions and basic operations in connection with FS.

    In many engineering problems there is a series of features which may be grouped into subsets with components related closer to each other, even to sub-subsets within these subsets. Such structures may be represented by either a tree graph, or an iteratively nested vector (with sub-vectors as components).

    A very special extension of the idea of FS is given by the Fuzzy Situational Maps (FSM) where the sub-trees represent matrices of two or more dimensions with more or less fixed spatial structure. Zoom in and zoom out operations combined with proper fuzzy aggregations help to increase or decrease the detail view of a given part of the area described by the FSM.

    A series of possible applications of FSM will be presented such as description of condition of residential buildings, warehouse layouts and scenarios for intelligent collaborating robots.

5:50 - 6:30 pm - Lecture - Professor Bill Moran - Defence Science Institute, University of Melbourne

  • Title: The Ubiquitous Sensor
  • Biography: 

    Professor Bill Moran, from the Department of Electrical and Electronic Engineering, has been appointed as Director of the Defence Science Institute (DSI), a joint venture between the University of Melbourne and the Defence Science and Technology Organisation (DSTO).

    Professor Moran is an expert in radar technology, coding and information theory, waveform adaptive sensing, information geometry and compressive sensing, high resolution radar for environmental monitoring, scalable robust video surveillance over constrained networks, mathematics of distributed radar, radar on a chip (ROACH), detection and tracking of targets using distributed antenna, sonar simulation modelling, rapid prototyping, and sensor networks.

    Professor Moran is a Fellow of the Australian Academy of Science (FAA), a Member of the Institute of Electrical and Electronic Engineers, and a Member of the London, Australian and American Mathematical Societies.

  • Abstract: 

    Sensors are becoming an increasingly important part of our society. Cameras, radars, IR sensors, microphones, are everywhere. If correctly used in disaster management contexts such as bushfires they would be able to assist in deployment of first responders and evacuation of residents.

    The aim of this talk is to discuss the theory of sensing, mostly in fairly general terms but with examples taken from disaster management and defence. One aspect of sensing that is being considered in the research community is adaptivity. Sensors can change in many ways: cameras can move, change focal length, change aperture. Radars can change their illumination pattern.

    How can we better use this adaptive aspect of sensors to extract the most information from a scene? What is information anyway? And how much does it cost to collect? How can we automate the adaptivity of sensing to optimize the results.

6:30 - 7:00 pm - Wrap-up and Light Refreshments

Further Event Details (124 KB)

Deakin University acknowledges the traditional land owners of present campus sites.

13th March 2015