Tutorials and Workshops
|Mehdi Bahrami||Tutorial A1: Cloud Computing for Emerging Cloud App:Cloud App-as-a-Service (CAaaS)||Cloud Lab, Univ. California at Merced, USA||Sunset I&II||9:30am-12:30pm|
|Hermann Kaindl||Tutorial A2: Interaction Design for Specifying Requirements||Vienna University of Technology, Austria||Bay View||9:30am-12:30pm|
|Tutorial A3: Big Data based Technological innovations on Intelligent Health Service in the Clouds||Iwate Prefectural University, Japan University of Granada, Spain||Royal III, IV, V||9:30am-12:30pm|
|Haibin Zhu||Tutorial B1: Adaptive Collaboration Systems||Nipissing University, Canada||Sunset I&II||2:00pm-5:00pm|
|Chuangyin Dang||Tutorial B2: Game Theory: Nash Equilibrium and its Applications||City University of Hong Kong, Hong Kong||Bay View||2:00pm-5:00pm|
|Ludo Stellingwerff||Tutorial B3: Novel Agent-Based Software Engineering||Almende BV, Rotterdam, Netherlands||Royal III, IV, V||2:00pm-5:00pm|
José del R. Millán
Jose M. Carmena
|Tutorial C: Brain-Machine Interaction: From Neural Decoding to Real-World Applications||
University of California, Berkeley, USA
Vinod A Prasad
|University College London, UK|
|Nanyang Tech. University, Singapore|
|Jet Propulsion Laboratory, USA|
|Workshop C: System Engineering: Human-Centered Intelligent Vehicles||
ENSTA-Paris Tech, France
Renault S.A.S, France
|Palm III, IV, V||9:30am-12:30pm 2:00pm-5:00pm|
|Liu Honghai||Workshop on Assistive and Rehabilitative Technology and Applications*||University of Portsmouth,||Moved to Session T3: Oct. 7 1:50PM -3:30PM Dockside|
Tutorial 1: Cloud Computing for Emerging Cloud App - Cloud App-as-a-Service (CAaaS)
Speaker: Mehdi Bahrami, University of California at Merced, USA
Abstract: This tutorial will provide an introduction to the emerging field of Cloud Computing for designing, developing, deploying and maintaining online and offline apps. It will begin with explaining the concepts behind cloud computing systems, cloud software architecture, the need for cloud computing as part of app industry to deal with new app design, network apps, app designing tools, and the motivation for migrating to cloud computing systems. It will review facts, goals and common architectures of a cloud computing system, as well as introduce general cloud services for apps developers and marketing. The tutorial will highlight major problems, challenges, costs and the role of cloud computing architecture in the field of designing apps and how an app-design industry has an opportunity to migrate to cloud computing systems with low investment. It will describe some cloud vendor services to illustrate how cloud vendors can improve an app business. Finally, the tutorial will survey some of the cutting-edge practices in the field, and present some opportunities for future development.
Speaker Bio: Mehdi Bahrami is working in the Cloud Lab at the University of California, Merced, and is a senior member of IEEE. He was a Senior Software Analyst at the Lian Processor Co. He has more than 10 years of software industry experience and more than 5 years of teaching experience in the field of computer science. He has published several technical papers in the areas of Cloud Computing Architecture, Grid Architecture, and Software Architecture. He served as an editor-in-chief, editor, and reviewer for several international computer science journals, including Springer Journals. He also served as a technical program committee member for several international IEEE computer science conferences. He has extensive experience with software engineering and developing distributed software applications across diverse platforms, such as Web-based, Windows-based, and Android-based systems.
Tutorial 2: Interaction Design for Specifying Requirements
Speaker: Hermann Kaindl, Vienna University of Technology, Austria
Abstract:This tutorial explains joint modeling of (communicative) interaction design and requirements, through discourse models and ontologies. Our discourse models are derived from results of human communication theories, cognitive science and sociology (even without employing speech or natural language). While these models were originally devised for capturing interaction design, it turned out that they can be also viewed as specifying classes of scenarios, i.e., use cases. In this sense, they can also be utilized for specifying requirements. Ontologies are used to define domain models and the domains of discourse for the interactions with software systems. User interfaces for these software systems can be generated semi-automatically from our discourse models, domain-of-discourse models and specifications of the requirements. This is especially useful when user interfaces for different devices are needed. So, requirements meet interaction design to make applications both more useful and usable.
Speaker Bio: Hermann Kaindl joined the Institute of Computer Technology at the Vienna Univ. of Technology in early 2003 as a full professor. Prior to moving to academia, he was a senior consultant with the division of program and systems engineering at Siemens AG Austria. There he has gained more than 24 years of industrial experience in software development and human-computer interaction. He has published five books and more than 170 papers in refereed journals, books and conference proceedings. He is a Senior Member of the IEEE, a Distinguished Scientist member of the ACM, a member of the AAAI, and is on the executive board of the Austrian Society for Artificial Intelligence.
Tutorial 3: Big Data based Technological innovations on Intelligent Health Service in the Clouds
Speakers: Hamido Fujita, Iwate Prefectural University, Japan
Enrique Herrera-Viedma, University of Granada, Spain
Abstract:Big Data technology is a new challenge to create human profiles, monitor social behavior, provide decision support based on social trends or discover new service providing opportunities. The objective of this workshop is to highlight new research directions in providing services granules represented in Cloud Semantics based on IoP (Internet of People) preferences. The IoP cloud will provide ordered preference on people in connection to health needs and crisis services. These two services are also presented in IoH (Internet of Health) in cloud semantics, and also Internet of Crisis (IoC) in another cloud. These collaborative clouds may provide services to users in health and crises based on semantical analysis in relation to their preferences without having users to provide direct input. The system will do these situational (different scenarios) predictions and provide specific prediction fits to handle the situations. The system will do these predictions and provide specific directions that fit with a situational scenario. Aspects that are to be discussed in this workshop are:
-Cooperative clouds, policies and securities
- Sentimental analysis prediction and subjective criteria of IoP, user preferences extracted from Social Networks
- Trust based decision making models for decision making processes and consensus processes in Social Media exploiting the preferences and opinions and data from social networks
- Structure of the cloud-based big data context and the most representative crisis evaluation decisions
- Data source clustering schemes or classification of data sources by attributes
-Virtual Doctor System in the clouds, as a service using the IoH for health provider system based on the Virtual Doctor System (developed by the workshop leaders).
Speaker Bios: Hamido Fujita is Professor at Iwate Prefectural University (IPU), Iwate, Japan, and director of Intelligent Software Systems. He is the Editor-in-Chief of Knowledge-Based Systems, an Elsevier journal of high impact factor (4.104). He received the Doctor Honoris Causa from Óbuda University in 2013, and the title of Honorary Professor from Óbuda University, Budapest, Hungary in 2011. He received the Honorary Professorship from many distinguished universities. He is an Adjunct professor to Stockholm University, Sweden, University of Technology Sydney, National Taiwan Ocean University and others. He has supervised PhD students jointly with the University of Laval, Quebec, Canada; University of Technology, Sydney, Australia; University of Paris 1 Pantheon-Sorbonne, France, University of Genoa, Italy, and others. He led a number of projects including Intelligent HCI, a project related to Mental Cloning as an intelligent user interface between human users and computers and the SCOPE project on Virtual Doctor Systems for medical applications (http://www.fujita.soft.iwate-pu.ac.jp/).
Enrique Herrera-Viedma received the B.Sc. and Ph.D. degrees in Computer Sciences, from the University of Granada (Spain) in 1993 and 1996, respectively. He is currently a Professor with the Department of Computer Science and Artificial Intelligence at the University of Granada, Vice-Dean of Research in Library and Communication Faculty, and Director of the Quality Evaluation and Information Retrieval Research Laboratory (SECABA). He is an Associate Editor of several ISI journals: IEEE Transaction on Systems, Man, and Cybernetics: Systems; Knowledge Based Systems; Applied Soft Computing, Soft Computing; Journal of Intelligent Fuzzy Systems; Fuzzy Optimization and Decision Making, and Information Science. He has published extensively in leading international journals in this field more than 110 papers in ISI journals. His H-index is 41 and he presents more than 5500 citations in Web of Science. In 2014 he has been identified by Thomson Reuters and Shangai Ranking Center as a Highly Cited Researcher (http://decsai.ugr.es/~viedma).
Tutorial 4: Adaptive Collaboration Systems
Speaker: Haibin Zhu, Nipissing University, Canada
Abstract:In this tutorial, we aim to clarify the terminology of Role Based Collaboration (RBC) and Adaptive Collaboration (AC). The presenter will answer the following questions: What do we mean by roles in collaboration? What is role-based collaboration (RBC)? Why do we need RBC? How can we support RBC? What are the emerged and potential applications of RBC? What are the emerged and potential benefits? What are the challenges and difficulties? This presentation describes RBC and its Environment-Class, Agent, Role, Team, and Object (E-CARGO) model, introduces AC within the context of solving real-world team performance problems using computer-based algorithms. Based on our previous work on the E-CARGO model, a theoretical foundation for AC using a simplified model of role-based collaboration (RBC) was proposed. Several parameters that affect team performance were defined and integrated into a theorem, which showed that dynamic role assignment facilitated better performance than static role assignment. The benefits of implementing AC were further proven by simulating a “future battlefield” of remotely-controlled robotic vehicles; in this scenario, team performance clearly benefited from shifting vehicles (or roles) using a single controller. Related research was also discussed for future studies.
Speaker Bio: Haibin Zhu is Full Professor and Coordinator of the Computer Science Program, Founding Director of the Collaborative Systems Laboratory, Nipissing University, Canada. He received the B.S. degree in computer engineering from the Institute of Engineering and Technology, China (1983), and the M.S. (1988) and Ph.D. (1997) degrees in computer science from the National University of Defense Technology (NUDT), China. He was a visiting professor and a special lecturer in the College of Computing Sciences, New Jersey Institute of Technology, USA (1999-2002) and a lecturer, an associate professor and a full professor at NUDT (1988-2000). He has published 130+ research papers, four books and two book chapters on object-oriented programming, distributed systems, collaborative systems, agent systems and computer architecture. He is a senior member of IEEE, a member of ACM, and a Life Member of the Chinese Association for Science and Technology, USA.
Tutorial 5: Game Theory: Nash Equilibrium and its Applications
Speaker: Chuangyin Dang, City University of Hong Kong
Abstract:The concept of Nash equilibrium is one of the most important and elegant ideas in game theory. Unfortunately, as pointed out in Selten (1975) and Myerson (1978), a game can have many Nash equilibria, and some of these equilibria may be inconsistent with our intuitive notions about what should be the outcome of a game. To reduce this ambiguity and eliminate some of these counterintuitive equilibria, the concept of perfect equilibrium was introduced in Selten (1975) and reviewed in Myerson (1978). The introduction of perfect equilibrium substantially reduces the set of Nash equilibria. Nevertheless, a game can still have many perfect equilibria, and some of these equilibria are undesirable. To further exclude some of these undesirable equilibria, the concept of proper equilibrium was formulated in Myerson (1978).
Among these refinements, the concept of proper equilibrium has a desired property that a proper equilibrium of the normal-form of an extensive-form game induces a sequential equilibrium (Kreps and Wilson 1982). Furthermore, as pointed out recently in Myerson and Weibull (2013), settled equilibria are proper. These results show that proper equilibrium is one of the most powerful refinements and has many applications in practices. Therefore it is indispensable for the determination of proper equilibrium in applications of game theory. Govindan and Klumpp (2002)'s result implies that a direct check on whether a strategy profile is a proper equilibrium requires, in principle, an infinite number of computations. Hansen et al (2010) shows that it is NP-hard to determine whether a given pure strategy Nash equilibrium is proper for a three-person game. These results imply that one can only get a proper equilibrium from a limit point of a sequence of epsilon-proper equilibria. Such a process inherently induces numerical instability when the number of pure strategies is large. This deficiency leads to a further refinement of Nash equilibrium, namely, a numerically more stable proper refinement. In this tutorial, a brief introduction to these refinements will be presented and path-following approaches to their determination will be discussed.
Speaker Bio: Chuangyin Dang received the PhD degree in Operations Research/Mathematical Economics from Tilburg University, The Netherlands, in 1991. He currently is Professor of Systems Engineering and Engineering Management at City University of Hong Kong. Prior to this position, Prof. Dang held faculty positions at University of California at Davis, Delft University of Technology and Auckland University, and was research fellow at Cowls Foundation for Research in Economics, Yale University. He is best known for developing the D1-triangulation of the Euclidean space and simplicial and fixed-point iterative methods for integer programming. Prof. Dang received Outstanding Research Achievements Award from Tilburg University in 1990 and was invited to give talks at Cornell University, Stanford University, University of Michigan at Ann Arbor, University of Minnesota at Twin Cities, etc. His research interests include computational optimization and applications, mathematical modelling and analysis in economics and finance, and mathematical optimization in pattern recognition and information processing. Prof. Dang has published over one hundred and thirty papers in such journals as IEEE Transactions on Automatic Control, IEEE Transactions on Computers, IEEE Transactions on Cybernetics, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Fuzzy Systems, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Neural Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, Artificial Intelligence, Computational Optimization and Applications, Mathematical Programming, Mathematics of Operations Research, SIAM Journal on Optimization, Neural Computation, Neural Networks, and Pattern Recognition.
Tutorial 6: Novel Agent-Based Software Engineering
Speaker: Ludo Stellingwerff, Almende BV, Rotterdam, The Netherlands
Abstract:This tutorial will introduce and demonstrate a novel approach to agent-based software engineering, which may lead to a wider adoption of this paradigm. The agent-based approach is known to be a valid solution for distributed software engineering; however, it has not been widely adopted in industry. During this tutorial, we will analyze the reasons for it as well as the limitations of the current agent platforms. After that, we will put forward a new paradigm to build agents based on the current web technology. With this fresh approach, agents can be easily built for a large variety of applications running on heterogeneous devices, like the cloud, portable devices, and local computers. Also, there will be an extensive presentation and a software demonstration of the web-based agent platform Eve, which is based on the approach described earlier. In the second part of the tutorial, there will be practical workshop in which the participants will be asked to collaborate to build an Eve-based working application. The tutorial will conclude with a thorough discussion about the pros and cons of these principles.
Speaker Bio: Ludo Stellingwerff is Senior Software Engineer at Almende B.V., Rotterdam, The Netherlands. He earned a Bachelor of Engineering in Aerospace at the Haarlem Institute of Technology and a Master of Science in Software Engineering at the University of Liverpool, UK. His main interest is software engineering, and he proposes a new approach to software architecture inspired by decoupled systems of technical, biological and social nature. Currently, he is working on an open-source agent platform called 'Eve' that can be used for bringing software agents to production level software applications.
Tutorial 7: Brain-Machine Interfaces (BMI): From Neural Decoding to Real-World Applications
Speakers: Ricardo Chavarriaga, EPFL, Switzerland
Tom Carlson, University College London, UK
Vinod A Prasad, Nanyang Tech. University, Singapore
Adrian Stoica, Jet Propulsion Laboratory, USA
Sessions: Morningand Afternoon
Abstract: This tutorial is part of the BMI Workshop being held at SMC2014. The tutorial will provide an introduction to brain-machine interfacing (BMI) system and discuss the current trends and outstanding challenges in the field: by the end participants will understand the fundamental techniques, including signal acquisition and processing, user intention detection, human factors, system design, robotic and sensor integration, machine learning, modeling, and shared control. Participants who are experts in Systems, Human-Machine Systems, and Cybernetics will gain some insight into how their own research can be applied in improving and developing BMI systems.
The possibility of controlling neuro-prostheses and other assistive devices directly from brain signals has gained increasing attention over the past few years. Brain-machine interfaces (BMI) are systems that translate the user's intention - coded by brain activity measures invasive and non-invasively - into a control signal without using activity of any muscles or peripheral nerves. These control signals can potentially be employed to substitute motor capabilities (e.g. brain-controlled prosthetics for amputees or patients with spinal cord injuries); to help in the restoration of such functions (e.g. as a tool for stroke rehabilitation), to enable verbal, spelling, Internet, or other types of communications for those who are disabled or otherwise unable to communicate, and other non-clinical applications such as telepresence and gaming.
This tutorial is structured in two parts: The first part will provide an introduction to the BMI field; covering different recording techniques, state-of-the-art machine learning methods for signal processing and decoding of neural activity, and finally, current applications, including rehabilitation and assistive technologies (e.g., wheelchairs, exo-skeletons, robotic prostheses, communication aids, and other assistive devices) will be reviewed. The second part of this tutorial will discuss how the next generation of BMI can be improved through the integration of context-aware system design principles for controlling complex devices, shared control, hybrid approaches including body sensor networks, machine learning, real-world modelling issues, virtual/augmented reality, haptics and teleoperation, human factors, and augmented cognition, among others. Besides the presenters, worldwide-recognized experts from SMC's different research areas will deliver brief detailed presentations on potential research avenues for enriching BMIs.
Speaker Bios: Ricardo Chavarriaga is a Senior Researcher at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland. He received an engineering degree in electronics from the Pontificia Universidad Javeriana (Cali, Colombia) in 1998, and a Ph.D. in Computational Neuroscience from the EPFL in 2005. He co-chairs the IEEE SMC technical committee in BMI systems and is in the editorial board of the journals Brain-Computer interfaces, IEEE Transactions on Human- Machine Systems and Frontiers in Neurorobotics. In the past he has organized BCI-related Tutorials at the IEEE conference on Cybernetics 2013 and the IEEE/ACM Human-Robot interaction conference 2009, as well as workshops at the International BCI conference 2013, the IEEE SMC conference 2011. His research focuses on robust brain-machine interfaces and multimodal human-machine interaction. Specifically, decoding of cortical potentials that convey information about the user's cognitive processes. In particular error recognition, anticipation of future events and decision-making. Furthermore, He investigates on how the exploitation of such processes can be integrated with shared control principles and hybrid approaches for BMI control of complex devices.
Tom Carlson is a Lecturer (~assistant prof.) in the Aspire Centre for Rehabilitation Engineering and Assistive Technology at University College London (UCL), UK. He received his MEng in Electrical and Electronic Engineering (2006) and his PhD in Intelligent Robotics (2010), both from Imperial College London, UK. He then spent 3.5 years as a scientific researcher at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland, before joining UCL. His research focuses on the user-centred design of assistive robotic technologies for people with spinal cord injuries. In particular he is interested in advanced alternative interfaces and shared control systems that strike the balance between the fast, reliable and inexhaustible task execution capabilities of automation and the complementary inventive, adaptive and interactive task execution skills of humans. Tom is currently a co-chair of the IEEE SMC Technical Committee on Shared Control, which he co-founded in 2012. Over the past four years, he has co-organised several successful workshops and tutorials at IEEE SMC, IEEE CybConf and IEEE/ACM HRI.
Vinod A Prasad received his B. Tech degree in instrumentation and control engineering from N.S.S.College of Engineering, Palakkad, University of Calicut, India in 1993 and the M. Eng and PhD degrees from School of Computer Engineering, Nanyang Technological University, Singapore in 2000 and 2004 respectively. Since 2010 he is an Associate Professor in NTU. He also served as a Visiting Associate Professor in Dept. of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada, during June – July 2013. Vinod’s research interests include digital signal processing, low power and reconfigurable DSP circuits, software defined radio, cognitive radio and brain-computer interface. He has published 171 papers in refereed international journals and conferences. Currently, Vinod is leading a research team of 2 Postdoctoral Research Fellows and 7 PhD Students in Centre for High Performance Embedded Systems (CHiPES), NTU. He is a Senior Member of IEEE, Associate Editor of Circuits, Systems, and Signal Processing Journal (Springer), Editor of International Journal of Advancements in Computing Technology (IJACT), and Technical Committee Co-Chair (Brain-Machine Interface) of IEEE Systems, Man & Cybernetics Society. He has won the Nanyang Award for Excellence in Teaching in 2009, the highest recognition conferred by NTU to individual faculty who have exhibited excellent teaching practice and enriched the learning experiences of their students through their enthusiasm, care and close rapport.
Adrian Stoicahas over twenty years of R&D experience in autonomous systems, developing novel adaptive, learning and evolvable hardware techniques and embedding them into electronics and intelligent information systems, for applications ranging from measurement equipment to space avionics to robotics. Contributed pioneering work in new fields (humanoid learning by imitation, evolvable hardware, survivable self-reconfigurable electronics for extreme environments), invented new concepts (polymorphic electronics, cognitive anti-tamper techniques) and took them to hardware demonstration. He has over 100 papers, 5 awarded patents, founded several conferences (including the NASA/ESA conference on Adaptive Hardware and Systems), roles in IEEE (Program Chair 2011 IEEE Systems Man and Cybernetics, etc), plenary speaker at more than 10 international conferences. His research interest include Autonomous systems, human-centered robots and systems, machine/robot learning, artificial/computational intelligence/cognition, human-robot collaboration, teaching/fostering robots, human-robot interaction, robot control using biological signals (EEG, EMG), social robotics, cognitive robotics, humanoids, household/service robotics, advanced electronics (secure electronics, high-performance electronics, electronics for harsh radiation/temperature environments) biometrics, adaptive and evolvable hardware and systems, anti-aging technologies, foresight and strategic R&D planning.