[Abstract] Social robotics is a field that deals with simulating social behavior on robots with the aim of making the robots cope with the interactive aspects of autonomy while they interact with humans or another embodied autonomous agents. Due to the many layers of social interaction and the complexity of the autonomous social behavior, the observed social behaviors are simulated. We aim at augmenting the social interaction behaviors with elements of brain-inspired mechanisms that cause social behavior. So far we use a combination of observed and emulated social intelligence.

Autistic children have atypical social behavior and the origin of that can be traced back to the difficulties in performing simple behaviors such as eye contact, turn taking, and imitation. In addition, at present, understanding the underlying mechanisms of intentions and emotions is getting within the reach of contemporary science.  We use a combination of methods consisting of functional brain modeling, behavioral robotics, and human centered design in social scenarios that comply to the modern therapies for autistic children such as Applied Behavioral Analysis and Pivotal Response Training. The behaviors are tested with human subjects (especially children with autism). The user group of children with autism was chosen, because they do not only benefit from the outcome of the research but also help us to generate knowledge on how social interaction is developing in typically developing and socially impaired (autistic) children. The results of the experiments with humans facilitate knowledge discovery and the obtained results are fed back as a research input for novel robot behaviors, and interaction scenarios for behavioral training. 
 [Biography] Dr. Ir. Emilia I. Barakova is affiliated with the Department of Industrial Design at the Eindhoven University of Technology, The Netherlands, and simultaneously holds a Visiting Researcher position at RIKEN Brain Science Institute in Japan. She has: Masters Degree in Electronics and Automation from Technical University of Sofia (Bulgaria) and PhD in Mathematics and Physics from Groningen University (The Netherlands, 1999).

Barakova has expertise in behavioral robotics and functional brain modeling based on behavioral data from mice, monkeys, and humans, on learning methods, and human centered interaction design. Currently she is working on human-robot social interaction, robotics for behavioral training of autistic children and  on prediction of conflicts in social groups, which includes measuring, and analyzing human behavior and interaction, use of machine learning and brain-inspired computational models to create robot interactive behaviors and human-centered design to design interactive scenarios that are based on advanced therapeutic practices.

Barakova has worked at different research institutes: the RIKEN Brain Science Institute (Japan), the GMD-Japan Research Laboratory (Japan), Groningen University (The Netherlands), the Eindhoven University of Technology (The Netherlands), Starlab (Belgium), and the Bulgarian Academy of Science. She has closely collaborated with Honda Research Institute (Asimo), Fraunhover AiS (Germany), Philips Research, Noldus, and TiViPE (The Netherlands), and ARC Cambridge (UK). She has been an interim Scientific Director of GMD Japan research laboratory, a project leader of several multidisciplinary projects, and coordinated the Robotics and Social robots educational and research team at ID department of TU/e. Barakova is an Associate editor of Journal of Integrative Neuroscience, and has organized several scientific workshops, special issues of international journals. She has organized  international conferences and has served as a program chair of IEEE and ACM conferences. Barakova is an author of over 100 scientific papers, conference proceedings, and one book.

Top

 [Abstract] We live in a world where the pressure to be more efficient has never been greater. Carbon mitigation is a key driver for this imperative, as is the need to do more with less. This talk will bring together several distinct threads of research. First, it will argue the case for leveraging formal service engineering techniques, and indeed formal computing techniques in modeling, designing, delivering and monitoring services in the most general sense. Second, it will argue that generating efficiencies from such services requires us to leverage optimization techniques, both in the design and operation of such services. Third, it will argue that piecemeal optimization is inadequate and that we must design networks of collaboratiing services to effectively maximize efficiency opportunities. These threads will be brought together in the context of the Optimizing Web project that provides the infrastructure for large, ubiquitous networks of local optimizers to collaborate to improve solutions relative to a shared (and arguably global) objective function. This has implications for our reponse to the climate change challenge (where the global objective is the minimization of the carbon footprint), but also in the context of service engineering at the bottom of the pyramid. 
[Biography] Aditya Ghose is Professor of Computer Science at the University of Wollongong and Director of its Decision Systems Lab. He holds PhD and MSc degrees in Computing Science from the University of Alberta, Canada (he also spent parts of his PhD candidature at the Beckman Institute, University of Illinois at Urbana Champaign and the University of Tokyo) and a Bachelor of Engineering degree in Computer Science and Engineering from Jadavpur University, Kolkata, India. While at the University of Alberta, he received the Jeffrey Sampson Memorial Award. His research has been funded by the Australian Research Council, the Canadian Natural Sciences and Engineering Research Council, the Japanese Institute for Advanced Information Technology (AITEC) and various Australian government agencies as well as companies such as Bluescope Steel, CSC and Pillar Administration. His research has been published in the top venues in service-oriented computing (SCC and ICSOC), software modelling (ER), software evolution (IWSSD, IWPSE) and AI (Artificial Intelligence Journal, AAAI, AAMAS and ECAI). He has been an invited speaker at the Schloss Dagstuhl Seminar Series in Germany and the Banff International Research Station in Canada. He has also been a keynote speaker at several conferences, and program/general chair of several others. He is a senior technical advisor to several companies in the areas of constraint programming and business process management, both in Australia and Canada. He reviews for well-regarded journals such as Artificial Intelligence, the IBM Systems Journal and the Journal of Autonomous Agents and Multi-Agent Systems, serves as assessor (Ozreader) for the Australian Research Council and as an external reviewer for the Natural Sciences and Engineering Research Council (NSERC) of Canada and the Science Foundation of Ireland. Professor Ghose is a Research Leader in the Australian Cooperative Research Centre for Smart Services, Co-Director of the Centre for Oncology Informatics at the Illawarra Health and Medical Research Institute, Co-Leader of the University of Wollongong Carbon-Centric Computing Initiative and Co-Convenor of the Australian Computer Society NSW SIG on Green ICT. He is also Vice-President of CORE, Australia's apex body for computing academics.

Top

 [Abstract] In recent years the development of a multitude of environments for social interaction has provided unprecedented opportunities for mass participation in social activities on a global scale. Participation in social action can take many forms from well-structured dialogues such as those taking place in scientific conferences to spontaneous crowd reactions similar to those occurring in sports or mass entertainment venues. Our research focuses on the creation of methods for expression, rendering and analysis of collective reactions in social activities. Collective in this context refers to a number of reactions with similar content, referring to the same situation and posted by a significant number of people at approximately the same point in time. We examine the types of such reactions and propose a number of rendering methods that take into account their magnitude, persistence and the aesthetics of the environment they appear in. We also describe analysis tools for tracking the emergence and evolution of such phenomena and discovering their causes. Finally, we propose methods by which the results of this analysis can be used in the creation of richer and more engaging social interaction experiences. 
[Biography] Professor Nikitas M. Sgouros holds a PhD in Computer Science from Northwestern University, USA (1994) a M.Sc. with distinction in Artificial Intelligence from the University of Edinburgh, UK (1990) and a Diploma in EECS from the National Technical University of Athens, Greece (1988). Currently, he is Professor in the Department of Digital Systems at the University of Piraeus, Greece. His main research interests include multimedia systems, artificial intelligence and entertainment computing. Dr. Sgouros has participated in a number of national and EU research projects. He is the author of more than 50 publications in scientific journals and conferences.

Top

 [Abstract] In this work, we are exploring spatial and social dynamics and clashes in social simulations involving partner selection. We are considering three different social settings: (a) a modified Axelrod cultural simulation model extended with a Moore neighborhood, heterogeneous sets of cultural features per agent and a number of psychologically realistic, basic and more advanced, conceptual models of cultural affinity perception and imitation, (b) a proto-imitation model where agents imitate unconditionally those they happen to interact with because perceived external signals are replicated impulsively without associating with objects of reference, and (c) a model of social noisy IPD interaction with an additional attraction mechanism that makes agents unconditionally cooperative toward attractive opponents. In all these models, a simple mechanism of partner selection has been found to modify the social environment by allowing different types of social structures to emerge, for example fast built cultural homogeneous groups in the case of cultural simulation or groups or interacting cooperative agents that are attracted by one another in the case of IPD with attraction. We are identifying a number of cognitive factors that are used to model partner selection, namely memory depth, learning speed and openness, and how they relate to both the type of the social environment at hand (all-to-all, networked ot grid-based) and the phenomena obtained. We are finally discussing how these factors may be studied and taken into account when designing complex sociotechnical systems, such as social networking collaborative environments with human participants, so as to accomodate the diversity of the social and cultural background of participants. 
[Biography] Elpida Tzafestas is an Associate Professor of Artificial Intelligence in the Department of Philosophy and History of Science, University of Athens, Greece. She finished her Electrical and Computer Engineering degree from  NTU, Athens, M.Sc. and Ph.D. on Artificial Intelligence (Univ. Paris VI, France). She has been a senior researcher in the Institute of Communication and Computer Systems (NTU, Athens) and has taught a number of undergraduate courses on computer science and graduate courses on intelligent, complex and biological systems. She has been the principal investigator in numerous national and european R&D projects and has authored over eighty articles in journals, books and conference proceedings, at least half of them as a single author. She serves on several editorial boards and is frequent reviewer for journals, conferences and research grants. Her research interests lie on the intersection of biological, complex and cognitive systems and their application to intelligent human-computer interaction, logistics and sustainable development.

Top

 [Abstract] Different components of machine intelligence are explained. The role of rough sets in uncertainty handling and granular computing is described. The significance of its integration with other soft computing tools and the relevance of rough-fuzzy computing, as a stronger paradigm for uncertainty handling, are explained. Different applications of rough granules, significance of f-granulation and certain important issues in their implementations are stated. Generalized rough sets using the concept of fuzziness in granules and sets are defined both for equivalence and tolerance relations. These are followed by definitions of various entropy measures. Different tasks such as case generation, class-dependent rough-fuzzy granulation for classification, rough-fuzzy clustering and defining various image ambiguity measures for mining are then addressed in this regard, explaining the nature and characteristics of granules used therein.
While the method of case generation with variable reduced dimension is useful for mining data sets with large dimension and size, class dependent granulation coupled with neighborhood rough sets for feature selection is efficient in modeling overlapping classes. Superiority of rough-fuzzy clustering is illustrated for brain MRI segmentation problem. Image ambiguity measures, which take into account both the fuzziness in boundary regions, and the rough resemblance among nearby gray levels and nearby pixels, are useful for various image analysis operations. Merits of generalization in rough sets, as well as the incorporation of the concept of rough granulation on the top of fuzziness in gray level are extensively demonstrated for image segmentation problem.
The talk concludes with stating the future directions of research such as in bioinformatics and web intelligence, and the challenging issues. 
[Biography] Sankar K. Pal (www.isical.ac.in/~sankar) is a Distinguished Scientist of the Indian Statistical Institute and a former Director. He is also a J.C. Bose Fellow of the Govt. of India. He founded the Machine Intelligence Unit and the Center for Soft Computing Research: A National Facility in the Institute in Calcutta. He received a Ph.D. in Radio Physics and Electronics from the University of Calcutta in 1979, and another Ph.D. in Electrical Engineering along with DIC from Imperial College, University of London in 1982. He joined his Institute in 1975 as a CSIR Senior Research Fellow where he later became a Full Professor in 1987, Distinguished Scientist in 1998 and the Director for the term 2005-10.
He worked at the University of California, Berkeley and the University of Maryland, College Park in 1986-87; the NASA Johnson Space Center, Houston, Texas in 1990-92 & 1994; and in US Naval Research Laboratory, Washington DC in 2004. Since 1997 he has been serving as a Distinguished Visitor of IEEE Computer Society (USA) for the Asia-Pacific Region, and held several visiting positions in Italy, Poland, Hong Kong and Australian universities.
Prof. Pal is a Fellow of the IEEE, USA, the Academy of Sciences for the Developing World (TWAS), Italy, International Association for Pattern recognition, USA, International Association of Fuzzy Systems, USA, and all the four National Academies for Science/Engineering in India. He is a co-author of seventeen books and more than four hundred research publications in the areas of Pattern Recognition and Machine Learning, Image Processing, Data Mining and Web Intelligence, Soft Computing, Neural Nets, Genetic Algorithms, Fuzzy Sets, Rough Sets and Bioinformatics.
He has received the 1990 S.S. Bhatnagar Prize (which is the most coveted award for a scientist in India), and many prestigious awards in India and abroad including the 1999 G.D. Birla Award, 1998 Om Bhasin Award, 1993 Jawaharlal Nehru Fellowship, 2000 Khwarizmi International Award from the Islamic Republic of Iran, 2000-2001 FICCI Award, 1993 Vikram Sarabhai Research Award, 1993 NASA Tech Brief Award (USA), 1994 IEEE Trans. Neural Networks Outstanding Paper Award (USA), 1995 NASA Patent Application Award (USA), 1997 IETE-R.L. Wadhwa Gold Medal, the 2001 INSA-S.H. Zaheer Medal, 2005-06 Indian Science Congress-P.C. Mahalanobis Birth Centenary Award (Gold Medal) for Lifetime Achievement, 2007 J.C. Bose Fellowship of the Government of India and 2008 Vigyan Ratna Award from Science & Culture Organization, West Bengal.
Prof. Pal is/ was an Associate Editor of IEEE Trans. Pattern Analysis and Machine Intelligence (2002-06), IEEE Trans. Neural Networks [1994-98 & 2003-06], Neurocomputing (1995-2005), Pattern Recognition Letters (1993-2011), Int. J. Pattern Recognition & Artificial Intelligence, Applied Intelligence, Information Sciences, Fuzzy Sets and Systems, Fundamenta Informaticae, LNCS Trans. On Rough Sets, Int. J. Computational Intelligence and Applications, IET Image Processing, J. Intelligent Information Systems, and Proc. INSA-A; Editor-in-Chief, Int. J. Signal Processing, Image Processing and Pattern Recognition; a Book Series Editor, Frontiers in Artificial Intelligence and Applications, IOS Press, and Statistical Science and Interdisciplinary Research, World Scientific; a Member, Executive Advisory Editorial Board, IEEE Trans. Fuzzy Systems, Int. Journal on Image and Graphics, Int. J. Computational Science & Engineering, and Int. J. Approximate Reasoning; and Guest Editor, IEEE Computer, and Theoretical Computer Science - C.

Top

 [Abstract] One of the main chalenges for the use of intelligent techniques to solve real problems is the selection of the most suited technique. Metalearning allows the use of learning algorithms for the recommendation of the techniques with the best potential to provide a good model.
In this talk I will discuss how metalearning can support the development of intelligent systems by recommending the most promising intelligent techniques. Real problems will illustrate the usefulness of using metalearning. 
[Biography] Prof. André C. Ponce de Leon F. de Carvalho is a Full Professor in the Department of Computer Science, University of S?o Paulo, Brazil, where he was head of Department from 2008 to 2010. He received his B.Sc. and M.Sc. degrees in Computer Science from the Universidade Federal de Pernambuco, Brazil. He received his Ph.D. degree in Electronic Engineering from the University of Kent, UK. He has published around 80 Journal and 200 Conference refereed papers. He has been involved in the organization of several conferences and journal special issues. His main interests are Machine Learning, Data Mining and Hybrid Intelligent Systems. He is in the editorial board of several journals and was a member of the Brazilian Computing Society, SBC, Council. He was until July 2011 the editor of the SBC/Elsevier textbook series.

Top