From Data to Information Granules: A Data Science Perspective
Department of Electrical & Computer Engineering
University of Alberta, Edmonton Canada
Systems Research Institute, Polish Academy of Sciences
Abstract: To capture the essence of data, facilitate building their essential descriptors and reveal key relationships (associations), we advocate a need for transforming data into more abstract constructs - information granules. In this setting, information granules are regarded as conceptually sound knowledge tidbits over which various models could be developed.
The paradigm shift implied by the engagement of information granules becomes manifested in several tangible ways including (i) a stronger dependence on data when building structure-free and versatile models spanned over selected numeric or granular representatives of experimental data, (ii) emergence of models at various levels of abstraction being promoted by the specificity/generality of information granules, and (iii) building a collection of individual local models and supporting their efficient aggregation and consensus building.
A framework of Granular Computing along with a diversity of its formal settings offers a critically needed conceptual and algorithmic environment. A suitable perspective built with the aid of information granules is advantageous in realizing a suitable level of abstraction. It also becomes instrumental when forming sound and pragmatic problem-oriented and user-oriented tradeoffs among precision of results, their easiness of interpretation, value, and stability.
The functional scheme advocated in this talk is outlined as follows: data -> numeric prototypes -> granular prototypes -> granular models. Numeric prototypes are formed through invoking clustering algorithms, which quite commonly gives rise to a collection of the representatives. Two ways of generalization of prototypes are considered: (i) symbolic and (ii) granular. In the symbolic generalization, one moves away from the numeric values of the prototypes and regards them as sequences of integer indexes (labels). Along this line, developed are concepts of (symbolic) stability and (symbolic) resemblance of data structures. The second generalization motivates the buildup of granular prototypes, which arise as a direct consequence for a more comprehensive representation of the data. This entails that information granules (including their level of abstraction), have to be prudently formed to achieve the required quality of the granular model. Subsequently two modes of aggregation of models (sources of knowledge) such as passive and active aggregation are also discussed.
Biography: Witold Pedrycz (IEEE Fellow, 1998) is Professor and Canada Research Chair (CRC) in Computational Intelligence in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. In 2009 Dr. Pedrycz was elected a foreign member of the Polish Academy of Sciences. In 2012 he was elected a Fellow of the Royal Society of Canada. Witold Pedrycz has been a member of numerous program committees of IEEE conferences in the area of fuzzy sets and neurocomputing. In 2007 he received a prestigious Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society. He is a recipient of the IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, and a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society.
His main research directions involve Computational Intelligence, fuzzy modeling and Granular Computing, knowledge discovery and data science, fuzzy control, pattern recognition, knowledge-based neural networks, relational computing, and Software Engineering. He has published numerous papers in this area. He is also an author of 17 research monographs and edited volumes covering various aspects of Computational Intelligence, data mining, and Software Engineering.
Dr. Pedrycz is vigorously involved in editorial activities. He is an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Int. J. of Granular Computing (Springer). He serves on an Advisory Board of IEEE Transactions on Fuzzy Systems and is a member of a number of editorial boards of international journals.
Professor, Tier I Canada Research Chair in Wireless Communication Networks
Weihua Zhuang has been with the Department of Electrical and Computer Engineering, University of Waterloo, Canada, since 1993, where she is a Professor and a Tier I Canada Research Chair in Wireless Communication Networks.
Professor Zhuang’s research interests include wireless communications, wireless networking, and smart grid. Her current research activities focus on distributed network control and resource allocation, heterogeneous wireless and wireline interworking, information and communication systems for smart grid. Her extensive research works have been published in the first-rate IEEE journals and conference proceedings. She is a co-recipient of several best paper awards from IEEE conferences.
Professor Zhuang was the Editor-in-Chief of IEEE Transactions on Vehicular Technology (2007-2013), Technical Program Chair/Co-Chair of IEEE VTC Fall 2017 and Fall 2016, and the Technical Program Symposia Chair of the IEEE Globecom 2011. She is a Fellow of the IEEE, the Royal Society of Canada, the Canadian Academy of Engineering, and the Engineering Institute of Canada. She is an elected member in the Board of Governors and VP Publications of the IEEE Vehicular Technology Society.
AI and Robotics: Scenario Intelligence
Max Qing Hu Meng
The Chinese University of Hong Kong, China
Abstract: Robotics and artificial intelligence are attracting more and more public
attentions and research efforts lately. Recent revolutionary development
and drastic progress in robotic technology and
artificial intelligence in terms of both hardware capability and
software power have made it possible for researchers to redefine what
robotics and artificial intelligence can achieve with their joint force
in accomplishing complicated human tasks, exploring new applications,
and expanding envelops of possibilities. We will use our own research
case studies to initiate discussions on how the
artificial intelligence shall be combined with or integrated in robotics
to tackle tasks that could not be accomplished to our satisfaction.
Personal thoughts and outlook on future research efforts and potentials
in robotics and artificial intelligence will be outlined to conclude the
Biography: Max Q.-H. Meng received his Ph.D. degree in Electrical and Computer
Engineering from the University of Victoria, Canada, in 1992. He joined
the Chinese University of Hong Kong in 2001 and is currently Professor
and Chairman of Department of Electronic Engineering. He was with the
Department of Electrical and Computer Engineering at the University of
Alberta in Canada, serving as the Director of the Advanced Robotics and
Teleoperation Lab and holding the positions of Assistant Professor
(1994), Associate Professor (1998), and Professor (2000), respectively.
He is affiliated with the State Key Laboratory of Robotics and Systems
at Harbin Institute of Technology as a Distinguished Chair Professor via
the One Thousand Talent Program and the Honorary Dean of the School of
Control Science and Engineering at Shandong University, in China. His
research interests include robotics, perception, intelligent robots and
agents, and medical robotics and devices. He has published some 600
journal and conference papers and led more than 50 funded research
projects to completion as PI. He has served as an editor of several
journals and General and Program Chair of many conferences including
General Chair of IROS 2005 and General Chair of ICRA 2021 to be held in
Xi’an, China. He is an elected member of the Administrative Committee
(AdCom) of the IEEE Robotics and Automation Society. He is a recipient
of the IEEE Millennium Medal, a Fellow of IEEE, a Fellow of HKIE, and a
Fellow of the Canadian Academy of Engineering.
Deep Learning for Big Data Applications - Challenges and Future Directions
Regents’ Professor and Chair
Department of Computer Science
Georgia State University, Atlanta, Georgia, USA
Abstract: Due to improvements in mathematical formulas and increasingly powerful computers, we can now model many more layers of virtual neurons (deep neural networks or deep learning) than ever before. Deep learning is now producing many remarkable recent successes in computer vision, automatic speech recognition, natural language processing, audio recognition, and medical imaging processing. Although various deep learning architectures and novel algorithms have been applied to many big data applications, extending deep learning into more complicated applications such as bioinformatics or medical images will require more conceptual and software breakthroughs, not to mention many more advances in processing power. In this talk, I will outline the challenges and problems in deep learning research. They include design of new architectures, handling high dimensional data, encoding schemes, mathematical proofs, optimization of hyperparameters, logic and reasoning, result explanation and hardware support for deep learning. Some solutions and preliminary results in these areas will be presented.
Biography: Yi Pan is currently a Regents’ Professor and Chair of Computer Science at Georgia State University, USA. He has served as an Associate Dean and Chair of Biology Department during 2013-2017 and Chair of Computer Science during 2006-2013. Dr. Pan received his B.Eng. and M.Eng. degrees in computer engineering from Tsinghua University, China, in 1982 and 1984, respectively, and his Ph.D. degree in computer science from the University of Pittsburgh, USA, in 1991. His profile has been featured as a distinguished alumnus in both Tsinghua Alumni Newsletter and University of Pittsburgh CS Alumni Newsletter. Dr. Pan's research interests include parallel and cloud computing, wireless networks, and bioinformatics. Dr. Pan has published more than 250 journal papers with over 80 papers published in various IEEE journals. In addition, he has published over 150 papers in refereed conferences. He has also co-authored/co-edited 43 books. His work has been cited more than 8000 times. Dr. Pan has served as an editor-in-chief or editorial board member for 15 journals including 7 IEEE Transactions. He is the recipient of many awards including IEEE Transactions Best Paper Award, several other conference and journal best paper awards, 4 IBM Faculty Awards, 2 JSPS Senior Invitation Fellowships, IEEE BIBE Outstanding Achievement Award, NSF Research Opportunity Award, and AFOSR Summer Faculty Research Fellowship. He has organized many international conferences and delivered keynote speeches at over 60 international conferences around the world.
Department of Information and Computer Science
Faculty of Science and Technology
Abstract: With rapid aging society in developed countries particularly Japan, social costs for nursing care and medical expenses are also rising. Meanwhile, the size of the average family has continued to shrink, which results in the increase of elderly people living alone. Smart healthcare is expected to support the aging society where people can live healthy and peacefully, while reducing the costs for support dramatically. To realize such a society, smart technologies are necessary. Smart sensor is one of the smart technologies where it is expected to collect information about people and environments while keeping privacy. For instance, monitoring a person living alone is an important problem in which the use of cameras is not normally permitted or preferred. In this talk I will introduce smart healthcare and smart sensors that realize it. I will also introduce some of our developed smart sensors based on wireless communications technologies. I will present some ideas how to securely share personal health data and cnclude.
Biography: Tomoaki Ohtsuki (Otsuki) is currently a Professor at Keio university, Japan. He received the B.E., M.E., and Ph. D. degrees in Electrical Engineering from Keio University, Yokohama, Japan in 1990, 1992, and 1994, respectively. From 1995 to 2005 he was with Science University of Tokyo. In 2005 he joined Keio University. He is engaged in research on wireless communications, optical communications, signal processing, and information theory. Dr. Ohtsuki is a recipient of the 1997 Inoue Research Award for Young Scientist, the 1997 Hiroshi Ando Memorial Young Engineering Award, Ericsson Young Scientist Award 2000, 2002 Funai Information and Science Award for Young Scientist, IEEE the 1st Asia-Pacific Young Researcher Award 2001, the 5th International Communication Foundation (ICF) Research Award, 2011 IEEE SPCE Outstanding Service Award, the 27th TELECOM System Technology Award, ETRI Journal’s 2012 Best Reviewer Award, and 9th International Conference on Communications and Networking in China 2014 (CHINACOM ’14) Best Paper Award.
He has published more than 165 journal papers and 380 international conference papers.
He served a Chair of IEEE Communications Society, Signal Processing for Communications and Electronics Technical Committee. He served a technical editor of the IEEE Wireless Communications Magazine and an editor of Elsevier Physical Communications. He is now serving an Area Editor of the IEEE Transactions on Vehicular Technology and an editor of the IEEE Communications Surveys and Tutorials. He has served general-co chair and symposium co-chair of many conferences, including IEEE GLOBECOM 2008, SPC, IEEE ICC2011, CTS, IEEE GCOM2012, SPC, IEEE SPAWC, and IEEE APWCS. He gave tutorials and keynote speech at many international conferences including IEEE VTC, IEEE PIMRC, and so on. He was a Vice President of Communications Society of the IEICE, Japan and is the elected President of Communications Society of the IEICE, Japan. He is a senior member of the IEEE and a fellow of the IEICE.