Plenary Speakers (In alphabetical order)
|
A. Murat Tekalp |
||
|
Janusz Kacprzyk |
Slim Bechikh |
|
|
|
||
|
|
|
|
|
|
Ah-Hwee Tan PhD & Professor Associate Editor of the IEEE Transactions on Neural
Networks and Learning Systems and the IEEE Transactions on Systems, Man, and
Cybernetics: Systems Singapore Management University, Singapore City,
Singapore. |
|
|
A.Murat Tekalp PhD & Professor Member of Turkish Academy of Sciences, Member of Academia
Europaea, IEEE Fellow, Lifetime Achievement Award
of IEEE Turkey Section Ko¸c University,
Istanbul, Turkey. |
|
|
Andries Engelbrecht PhD & Professor Associate Editor of, IEEE Transactions on Evolutionary
Computation Stellenbosch University, Stellenbosch, South Africa. |
|
|
Boris
Mirkin PhD & Professor Member of Academia Europaea,
Member of the UK EPSRC Computing Peer Review College, Member of the British
Classification Society Higher School of Economics, Moscow, RF and
Birkbeck, University of
London, UK.
|
|
|
Chin-Teng
Lin PhD & Professor IEEE Fellow, IFSA Fellow, Editor in Chief, IEEE
Transactions on Fuzzy Systems University of Technology Sydney, NSW, Australia. |
|
|
C.L.Philip Chen PhD & Professor Member of the European Academy of Sciences and Arts,
Foreign Member of Academia Europaea, IEEE Fellow,
AAAS Fellow, Editor in Chief, IEEE Transactions on Cybernetics South China University of Technology, Shenzhen, China. |
|
|
Derong Liu PhD & Professor Foreign member of the European Academy of Sciences, IEEE
Fellow, Editor in Chief, Artificial Intelligence Review Guangdong University of Technology, Guangzhou, China. |
|
|
De-Shuang
Huang PhD & Professor IEEE Fellow, IAPR Fellow, Editorial board of, IEEE/ACM
Transactions on Computational Biology & Bioinformatics Tongji University, Shanghai, China. |
|
|
El-Sayed M. El-Alfy PhD & Professor IEEE Senior Member, Associate Editor of, IEEE
Transactions on Neural Networks and Learning Systems King Fahd
University of Petroleum and Minerals, Saudi Arabia. |
|
|
Georgios
N. Yannakakis PhD & Professor Editor in Chief, IEEE Transactions on Games, Associate
Editor of, IEEE Transactions on Evolutionary Computation, Dean of the School
of Digital Games, University of Malta University of Malta, Msida,
Malta. |
|
|
Jacek
Ma¨½dziuk PhD & Professor Member of the Information Committee of the Polish Academy
of Sciences, General Co-Chair of the 2021 IEEE Congress on
Evolutionary Computation, AE of IEEE
Transactions on Neural Networks and Learning Systems and AI in
Games Warsaw University of Technology, Warsaw, Poland. |
|
|
James
M. Keller PhD & Professor IEEE Life Fellow, IFSA Fellow, President-Elect of CIS,
receives the 2021 Frank Rosenblatt Award from the IEEE University of Missouri, Michigan, U.S. |
|
|
Janusz Kacprzyk PhD &
Professor Institute of
Polish Academy of Sciences, Warsaw, Poland. |
|
|
Jinde Cao PhD & Professor Member of Academia Europaea,
Foreign Member of the Russian Academy of Natural Sciences, Foreign Member of
the Russian Academy of Engineering, Member of the African Academy of
Sciences, Member of the Pakistan Academy of Sciences, IEEE Fellow Southeast University, Nanjing, China. |
|
|
Jun
Wang PhD & Professor Foreign Member of Academia Europaea,
IEEE Fellow, IAPR Fellow, Editor-in-Chief of, IEEE Transactions on
Cybernetics City University of Hong Kong, Hong Kong, China. |
|
|
Kay
Chen Tan PhD & Professor IEEE Fellow, Editor-in-Chief of IEEE Transactions on
Evolutionary Computation Hong Kong Polytechnic University, Hong
Kong, China. |
|
|
Leszek
Rutkowski PhD & Professor Member of the Polish Academy of Sciences, IEEE Fellow,
Editor-in-chief, Journal of Artificial Intelligence and Soft Computing
Research University of Technology, Częstochowa,
Poland. |
|
|
Marco
Dorigo PhD & Professor Member of Academia Europaea, Inventor
of the ant colony optimization metaheuristic, IEEE Fellow, AAAI Fellow, ECAI
Fellow, Editor-in-Chief of, journal ¡°Swarm Intelligence¡± University Libre De Bruxelles,
Iridis, Belgium. |
|
|
Nikhil
R. Pal PhD & Professor Member of Indian Academy of Sciences, Member of Indian
Academy of Engineering, IEEE Fellow Indian Institute of Statistics, Kolkata, India. |
|
|
Pedro
Larranaga PhD & Professor Member of the Academia Europaea,
EurAI Fellow, Fellow of the Asia-Pacific Artificial
Intelligence Association Universidad Polit¨¦cnica de
Madrid, Madrid, Spain. |
|
|
Radu-Emil
Precup PhD & Professor Corresponding Member of the Romanian Academy, Editor-in-Chief,
International Journal of Artificial Intelligence, Editorial board of IEEE
Transactions on Fuzzy Systems, IEEE Transactions on Cybernetics, Information
Sciences (Elsevier), Engineering Applications of Artificial Intelligence Politehnica University of Timişoara, Romania. |
|
|
Sergey
Ablameyko PhD & Professor Member of Belarus Academy of Sciences, Member of Academia
Europaea, IAPR Fellow, AAIA Fellow and
Vice-President Belarusian State University, Minsk, Republic of Belarus. |
|
|
Slim
Bechikh PhD & Associate Professor Associate
Editors, IEEE Transactions on Evolutionary Computation, Swarm and
Evolutionary Computation
University
of Carthage, Tunisia.
|
|
|
Tingwen Huang PhD & Professor Member of Academia Europaea,
IEEE Fellow, AAIA Fellow Texas A&M University at Qatar, College Station,
Texas, USA. |
|
|
Tufan Kumbasar PhD & Associate Professor Area Editor-in-Chief, International Journal of
Approximate Reasoning, Associate Editor of, IEEE Transaction on Fuzzy Systems Istanbul Technical University, Maslak-Istanbul,
Turkey. |
|
|
Witold
Pedrycz PhD & Professor Member of the Royal Society of Canada, Foreign Member of
the Polish Academy of Sciences, IEEE Life Fellow, Editor in Chief,
Information Sciences, Co-editor-in-Chief of Int. J. of Granular Computing University of Alberta, Edmonton, Canada. |
|
|
Xin
Yao PhD & Professor IEEE Fellow, Royal Society Wolfson Research Merit Award,
IEEE Computational Intelligence Society Evolutionary Computation Pioneer
Award University of Birmingham, Birmingham, UK. |
|
|
Yaochu Jin PhD & Professor Member of Academia Europaea,
IEEE Fellow, Editor-in-Chief of IEEE Transaction on Cognitive and Development
Systems, Complex & Intelligent Systems Bielefeld University,
North Rhine Westphalia, Germany. |
|
|
Zengguang Hou PhD & Professor IEEE Fellow, editorial board of "IEEE Transactions on
Cybernetics", "Neural Networks" Institute of Automation, Chinese Academy of Sciences,
Beijing, China. |
Cognitive
Computing: A New Wave of Computational Intelligence?
Ah-Hwee Tan, PhD & Professor.
Associate Editor
of the IEEE Transactions on Neural Networks and Learning Systems and the IEEE
Transactions on Systems, Man, and Cybernetics: Systems
Singapore Management University, Singapore City, Singapore.
|
|
Abstract:
Although
recent development in machine learning techniques, in particular deep
learning, has raised much expectation in Artificial Intelligence (AI),
data-driven learning-based AI systems are typically designed to solve
specific problems by learning from a massive amount of training data. Human
cognition, on the other hand, involves a complex interplay of many high level functions, notably self-awareness, memory,
reasoning, learning, and problem solving. In this talk, we shall review a
family of biologically-inspired self-organizing neural network models,
collectively known as fusion Adaptive Resonance Theory (fusion ART). By
extending the Adaptive Resonance Theory (ART) into a multi-channel network
architecture, fusion ART unifies a number of important neural models
developed over the past decades, including Adaptive Resonance Theory (ART)
networks for unsupervised learning, Adaptive Resonance Associative Map (ARAM)
for supervised learning, and Fusion Architecture for Learning and Cognition
(FALCON) for reinforcement learning. Following the notion of embodied
cognition, fusion ART, encompassing a set of universal neural coding and
adaptation principles, can be used as a building block for cognitive
computation and intelligent behaviours, notably
real-time reinforcement learning, reasoning, and decision making. In this
talk, case studies will be presented, illustrating how such cognitive systems
may be manifested as Non-Player Characters (NPC) in virtual game environment
and Computer Generated Forces (CGF) in combat
simulation. |
Bio-Sketch: Dr
Ah-Hwee Tan received Ph.D. in Cognitive and Neural
Systems from Boston University, Master of Science and Bachelor of Science
(First Class Honors) in Computer and Information Science from the National
University of Singapore. He is currently Professor of Computer Science and
Associate Dean (Research) at the School of Computing and Information Systems
(SCIS), Singapore Management University (SMU). Before joining SMU, he was Professor of Computer
Science at the School of Computer Science and Engineering (SCSE), Nanyang
Technological University, where he last served as the Associate Chair
(Research) of the school. Prior to NTU, he was a Senior Member of Research
Staff at the A*STAR Institute for Infocomm
Research(12R), spearheading the Text Mining and Intelligent Agents research programmes. His current research interests include
cognitive and neural systems, brain-inspired intelligent agents, machine
learning, and text mining. Dr. Tan has published over 200 technical papers in
major international journals and conferences of his fields, in addition to six
edited books and proceedings. He holds two US patents, five Singapore patents,
and has spearheaded several A*STAR projects in commercializing a suite of
knowledge management and text mining software. He has served as Associate
Editor/Editorial Board Member of several journals, including IEEE Transaction
on Neural Networks and Learning, IEEE Transactions on SMC Systems, and IEEE
Access. He is a Senior Member of IEEE, Member of Web Intelligence (WI)
Technical Committee and Web Intelligence (WI) Conference Steering Committee,
Vice Chair of IEEE CIS Task Force on Towards Human-Like Intelligence, and
General Co-Chair of 2022 IEEE Symposium Series on Computational Intelligence
(IEEE SSCI 2022).
Deep Learning for Image and Video
Restoration/Super-Resolution
A. Murat Tekalp, PhD & Professor
Member of Turkish
Academy of Sciences, Member of Academia Europaea,
IEEE Fellow, Lifetime Achievement Award of IEEE Turkey Section
Koç University,
Istanbul, Turkey.
|
|
Abstract: Deep learning
has made a significant impact not only on computer vision and natural
language processing but also on classical signal processing problems such as
image/video restoration/SR and compression. Recent advances in neural
architectures led to significant improvements in the performance of learned
image/video restoration and SR. We can consider learned image
restoration and SR as learning either a mapping from the space of degraded
images to ideal images based on the universal approximation theorem, or a
generative model that captures the probability distribution of ideal images.
An important benefit of data-driven deep learning approach is that
neural models can be optimized for any differentiable loss function,
including visual perceptual loss functions, leading to perceptual video
restoration and SR, which cannot be easily handled by traditional model-based
approaches. I will discuss loss functions and evaluation criteria for
image/video restoration and SR, including fidelity and perceptual criteria,
and the relation between them, where we briefly review the perception vs.
fidelity (distortion) trade-off. We then discuss practical problems in
applying supervised training to real-life restoration and SR, including
overfitting image priors and overfitting the degradation model and some
possible ways to deal with these problems. |
Bio-Sketch: A. Murat
Tekalp received Ph.D. degree in Electrical, Computer,
and Systems Engineering from Rensselaer Polytechnic Institute (RPI), Troy, New
York, in 1984, He has been with Eastman Kodak Company, Rochester, New York,
from 1984 to 1987, and with the University of Rochester, Rochester, New York,
from 1987 to 2005, where he was promoted to Distinguished University Professor.
He is currently Professor at Koç University,
Istanbul, Turkey. He served as Dean of Engineering between 2010-2013. His
research interests are in digital image and video processing, including video
compression and streaming, video networking, and image/video processing using
deep learning. He is a Fellow of IEEE and a member of Academia Europaea. He served as an Associate Editor for IEEE Trans.
on Signal Processing (1990-1992) and IEEE Trans. on Image Processing
(1994-1996). He chaired the IEEE Signal Processing Society Technical Committee
on Image and Multidimensional Signal Processing (Jan. 1996 - Dec.
1997). He was the Editor-in-Chief of the EURASIP journal Signal
Processing: Image Communication published by Elsevier between 1999-2010. He was
appointed as the General Chair of IEEE Int. Conf. on Image Processing (ICIP) at
Rochester, NY in 2002, and as Technical Program Co-Chair for ICASSP 2000,
EUSIPCO 2005, and ICIP 2020. He was on the Editorial Board of the
IEEE Signal Processing Magazine (2007-2010) and the Proceedings of the IEEE
(2014-2020). He is now serving in the Editorial Board of Wiley-IEEE Press
(since 2018). He served in the ERC Advanced Grants Evaluation
Panel (2009-2015). Dr. Tekalp has authored the
Prentice Hall book Digital Video Processing (1995), a completely rewritten
second edition of which is published in 2015.
Forecasting
Non-Stationary Time Series without Recurrent Connections
Andries Engelbrecht, PhD &
Professor
Associate Editor
of the IEEE Transactions on Evolutionary Computation
Stellenbosch University,
Stellenbosch, South Africa.
|
|
Abstract: Artificial neural networks (NNs) are widely used in
modeling and forecasting time series. Since most practical time series are
non-stationary, NN forecasters are often implemented using recurrent/delayed
connections to handle the temporal component of the time varying sequence.
These recurrent/delayed connections increase the number of weights required
to be optimized during training of the NN. Particle swarm optimization (PSO)
has become an established method for training NNs, and was shown in several
studies to outperform the classical backpropagation training algorithm. The
original PSO was, however, designed for static environments. In dealing with
non-stationary data, modified versions of PSOs for optimization in dynamic
environments are used. These dynamic PSOs have been successfully used to
train NNs on classification problems under non-stationary environments. This
talk formulates training of a NN forecaster as dynamic optimization problem
to investigate if recurrent/delayed connections are necessary in a NN time
series forecaster when a dynamic PSO is used as the training algorithm. Eight
forecasting problems are used to show that FNNs trained with the dynamic PSO
significantly outperform various recurrent NNs. These findings highlight that
recurrent/delayed connections are not necessary in NNs used for time series
forecasting (for the time series considered in this talk) as long as a
dynamic PSO algorithm is used as the training method. |
Bio-Sketch: Andries Engelbrecht received the
Masters and PhD degrees in Computer Science from the University of
Stellenbosch, South Africa, in 1994 and 1999 respectively. He is currently
appointed as the Voigt Chair in Data Science in the Department of Industrial
Engineering, with a joint appointment as Professor in the Computer Science
Division, Stellenbosch University. Prior to 2019, he was appointed in the
Department of Computer Science, University of Pretoria (1998-2018), where he
served as the head of the department (2008¨C2017), South African Research Chair
in Artificial Intelligence (2007¨C2018), and Director of the Institute for Big
Data and Data Science (2017¨C2018). His research interests include swarm
intelligence, evolutionary computation, artificial neural networks, artificial
immune systems, machine learning, data analytics, and the application of these
Artificial Intelligence paradigms to data mining, games, bioinformatics,
finance, and difficult optimization problems. He is author of two books,
¡°Computational Intelligence: An Introduction¡± and ¡°Fundamentals of
Computational Swarm Intelligence¡±.
Modeling conceptual generalization over taxonomies
Boris Mirkin,
PhD & Professor
Member of Academia
Europaea, Member of the UK EPSRC Computing Peer
Review College, Member of the British Classification Society
Higher School of Economics, Moscow, RF and
University of London,UK.
|
|
Abstract: Deep learning successfully generalizes
features of records and images. Here is an effort on the opposite side, in
mental generalizations. We define and find a most specific generalization of
a fuzzy set of topics assigned to leaves of the rooted tree of a domain
taxonomy. This generalization lifts the thematic set to a¡°head subject¡±in the
higher ranks of the taxonomy to ¡°tightly¡± cover the set, possibly bringing in
some errors, both ¡°gaps¡± and ¡°offshoots¡±. We developed algorithms for both
maximum parsimony and maximum likelihood criteria. Our approach involves two
more automated analysis techniques: a fuzzy clustering method, FADDIS, using
both additive and spectral properties, and a purely structural string-to-text
relevance measure based on suffix trees annotated by symbol frequencies. We
apply this in two domains: (a) extracting research tendencies from
collections of research papers in Data Science; (b) extending sizes of internet advert
targeted audiences. (Joint work with S. Nascimento,T. Fenner, D. Frolov,
and Z. Ayrapetyan.) |
Bio-Sketch: Boris Mirkin
holds a PhD in Computer Science (Mathematics) and DSc in Systems Analysis
(Technology) degrees from Russian Universities. He was one of the leaders in
developing clustering and data analysis research in Russia and the USSR.
In 1991-2010, he travelled through long-term visiting
appointments in France, Germany, USA, and a teaching appointment as Professor
of Computer Science, Birkbeck University of London, UK (2000-2010).
He develops methods for clustering and interpretation
of complex data within the ¡°data recovery¡± perspective. Currently these
approaches are being extended to automation of text analysis problems including
the development and use of hierarchical ontologies. He published a hundred of
refereed papers and a dozen of monographs.
Brain Computer Interface in Human-Autonomy
Teaming
Chin-Teng
Lin, PhD &
Professor
IEEE Fellow, IFSA
Fellow, Editor in Chief, IEEE Transactions on Fuzzy Systems
University of
Technology Sydney, NSW, Australia.
|
|
Abstract: BCI is widely considered a ¡®disruptive
technology¡¯ for the next-generation human-computer interface in wearable
computers and devices. In particular, there are incredible potential
real-life applications of BCI in augmenting human performance for people in
health and aged care. Despite
this, there are limitations. Human cognitive functions, such as action
planning, intention, preference, perception, attention, situational
awareness, and decision-making, although omnipresent in our daily lives, are
complex and hard to emulate. Yet, by studying the brain and behaviour at work, a BCI plays an incredibly important
role natural cognition. Discover the
latest thinking in the realm of the Brain-Computer Interface in this lecture.
Listen the current status of BCI and discusses its three major obstacles: the
shortage of wearable EEG devices, the various forms of noise contamination
that hinder BCI performance, and the lack of suitable adaptive cognitive
modelling. This talk will introduce the fundamental physiological changes of
human cognitive functions in the interaction with autonomous machines
(autonomy) and explain how to combine the bio-findings and AI techniques to
develop monitoring and feedback systems to enhance the cooperation of human
and autonomy. |
Bio-Sketch: Chin-Teng Lin received the B.S. degree from the National Chiao-Tung University (NCTU), Taiwan in 1986, and the
Master and Ph.D. degree in electrical engineering from Purdue University, West
Lafayette, Indiana, U.S.A. in 1989 and 1992, respectively. He is currently a
Distinguished Professor, Co-Director of Centre for AI, and Director of CIBCI
Lab, FEIT, UTS. He is also invited as the International Faculty of the
University of California at San Diego (UCSD) from 2012 and Honorary
Professorship of University of Nottingham from 2014.
Prof. Lin¡¯s research focuses
on machine-intelligent systems and brain computer interface, including
algorithm development and system design. He has published over 380 journal
papers (H-Index 76 based on Google Scholar), and is the co-author of Neural
Fuzzy Systems (Prentice-Hall) and author of Neural Fuzzy Control Systems with
Structure and Parameter Learning (World Scientific). Dr. Lin served as Editor-in-Chief of
IEEE Transactions on Fuzzy Systems from 2011 to 2016, and has served on the
Board of Governors of IEEE Circuits and Systems Society, IEEE Systems, Man, and
Cybernetics Society, and IEEE Computational Intelligence Society. Dr. Lin is an IEEE Fellow, and received
the IEEE Fuzzy Pioneer Award in 2017.
C. L. Philip Chen, PhD &
Professor
Member of the
European Academy of Sciences and Arts, Foreign Member of Academia Europaea, IEEE Fellow, AAAS Fellow, Editor in Chief, IEEE
Transactions on Cybernetics
South China
University of Technology, Shenzhen, China.
|
|
Abstract: Learning in neural networks suffers from the fixed structure of the network with a given number of layers and neurons when gather information for training. When the learning is unsatisfied, a new structure is re-designed and the process is repeated. In this talk, a dynamic neural network structure via Stacked Broad Learning Systems (BLS) will be discussed. The BLS has been proved to be effective and efficient lately. The proposed dynamic model is a novel incremental stacking of BLS. This invariant inherits the efficiency and effectiveness of BLS that the structure and weights of lower layers of BLS are fixed when the new blocks are added. The modified incremental stacking algorithm only computes the connection weights within the BLS block while the connecting weights of the lower stacks remains fixed, making the learning process very efficient. Experimental results on UCI datasets, MNIST dataset, NORB dataset, CIFAR-10 dataset, SVHN dataset, and CIFAR-100 dataset indicate that the proposed method outperforms the other state-of-the-art methods on both accuracy and training speed, such as Deep Residual Networks. In addition,
taking the advantages of BLS that can accumulate and reuse the learned
knowledge, applications of BLS, Federated Broad Learning, in an open
environment will be discussed. Federated Broad Learning supports learning
from streaming data continuously, so it can adapt to the environment changes
and provide better real-time performance. The broad learning enabled systems
have been rigorously established in theory and tested in both simulation and
experimental studies. |
Bio-Sketch: C. L. Philip Chen (F¡¯07) is the Chair Professor and Dean
of the College of Computer Science and Engineering, South China University of
Technology and was a Chair Professor of the Faculty of Science and Technology,
University of Macau, where he was the former Dean (2010-2017), after he left a
professorship position in the USA for 23 years. He is a Fellow of IEEE, AAAS,
IAPR, CAA, and HKIE; a member of Academia Europaea
(AE), European Academy of Sciences and Arts (EASA). He received IEEE Norbert
Wiener Award in 2018 for his contribution in systems and cybernetics, and
machine learnings; and IEEE Joseph G. Wohl Career Award for his contributions
in SMCS and IEEE in 2021. He was a recipient of the 2016 Outstanding Electrical
and Computer Engineers Award from his alma mater, Purdue University. He
received IEEE Transactions on Neural Networks and Learning Systems best
transactions paper award two times for his papers in 2014 and 2018, Franklin
Taylor best conference paper award in IEEE Int¡¯l Conf. on SMC 2019. He is a
highly cited researcher by Clarivate Analytics from 2018 to 2021 continuously.
Currently, he is the
Editor-in-Chief of the IEEE Transactions on Cybernetics after he completed his
term as the Editor-in-Chief of the IEEE Transactions on Systems, Man, and
Cybernetics: Systems (2014-2019). He was the IEEE Systems, Man, and Cybernetics
Society President from 2012 to 2013, an Associate Editor of the IEEE
Transactions on AI, IEEE Trans on SMC: Systems, and IEEE Transactions on Fuzzy
Systems, an Associate Editor of China Sciences: Information Sciences. He
received Macau FDCT Natural Science Award three times and a First-rank
Guangdong Guangdong Province Scientific and
Technology Advancement Award in 2019. His current research interests include
cybernetics, computational intelligence, and systems.
AI and Machine Learning for Optimal Control of
Complex Nonlinear Systems
Derong Liu, PhD &
Professor
Foreign member of
the European Academy of Sciences, IEEE Fellow, Editor in Chief, Artificial
Intelligence Review
Guangdong
University of Technology, Guangzhou, China.
|
|
Abstract: Researchers have
been searching for novel control methods to handle the complexity of modern
industrial processes. Artificial intelligence and especially machine learning
approaches might provide a solution for the next generation of control
methodologies that can handle the level of complexities in many modern
industrial processes. It has been shown by many researchers reinforcement
learning can do a very good job approximating optimal control actions and
provide a nearly optimal solution for the control of complex nonlinear
systems. It requires a combination of function approximation structures such
as neural networks and optimal control techniques such as dynamic
programming. Theoretical development has been on a fast-track in the past ten
years. On the other hand, parallel control, cloud control, as well as
agent-based control have been studied as alternatives for handling complex
nonlinear systems. This lecture will review the development of these
methodologies to summarize the inherent relationship among these
developments. |
Bio-Sketch: Derong Liu received
the PhD degree in electrical engineering from the University of Notre Dame,
USA, in 1994. He became a Full Professor of Electrical and Computer Engineering
and of Computer Science at the University of Illinois at Chicago in 2006. He
was selected for the ¡°100 Talents Program¡± by the Chinese Academy of Sciences
in 2008, and he served as the Associate Director of The State Key Laboratory of
Management and Control for Complex Systems at the Institute of Automation, from
2010 to 2016. He has published 19 books. He is the Editor-in-Chief of
Artificial Intelligence Review (Springer). He was the Editor-in-Chief of the
IEEE Transactions on Neural Networks and Learning Systems from 2010 to 2105. He
is a Fellow of the IEEE, a Fellow of the International Neural Network Society,
a Fellow of the International Association of Pattern Recognition, and a Member
of Academia Europaea (The Academy of Europe).
Deep Neural Networks Based Motifs Mining in
Biological Binding Sequences
De-Shuang Huang,
PhD & Professor
IEEE Fellow, IAPR
Fellow, Editorial board of, IEEE/ACM Transactions on Computational Biology
& Bioinformatics
Tongji University,
Shanghai, China.
|
|
Abstract: Transcription
factor/Translation factor (TF) play a central role in gene regulation.
Knowing the binding specificities of TFs is essential for developing models
of the regulatory processes in biological systems and for deciphering the
mechanism of gene expression. In this talk, I will first present the
fundamental issue for motif prediction of biological sequences, then
systematically present motif prediction of biological sequences in combination
with the popular emerging technology ¡°Deep Neural Networks¡±. Firstly, several
classical models for deep neural network and the research status of
biological sequence motif prediction will be briefly introduced, and the
existing shortcomings of deep-learning based motif prediction is discussed,
some motif prediction methods including high-order convolutional neural
network architecture, weakly-supervised convolutional neural network
architecture, deep-learning based sequence + shape framework and bidirectional
recurrent neural network for DNA motif prediction are briefly overviewed.
Secondly, some latest results are importantly presented. Finally, some new
research problems in this aspect will be pointed out and over-reviewed. |
Bio-Sketch: De-Shuang
Huang is a Professor in Department of Computer Science and Director of
Institute of Machine Learning and Systems Biology at Tongji University, China.
He is currently the Fellow of the International Association of Pattern
Recognition (IAPR Fellow), Fellow of the IEEE (IEEE Fellow) and Senior Member
of the INNS, Bioinformatics and Bioengineering Technical Committee Member of
IEEE CIS, Neural Networks Technical Committee Member of IEEE CIS, the member of
the INNS, Co-Chair of the Big Data Analytics section within INNS, and
associated editors of IEEE/ACM Transactions on Computational Biology &
Bioinformatics, and Neural Networks, etc. He founded the International
Conference on Intelligent Computing (ICIC) in 2005. ICIC has since been
successfully held annually with him serving as General or Steering Committee
Chair. He also served as the 2015 International Joint Conference on Neural
Networks (IJCNN 2015) General Chair, July 12-17, 2015, Killarney, Ireland, the
2014 11th IEEE Computational Intelligence in Bioinformatics and Computational
Biology Conference (IEEE-CIBCBC) Program Committee Chair, May 21-24, 2014,
Honolulu, USA. His main research interest includes neural networks, pattern
recognition and bioinformatics.
Machine Learning Powered
Applications in IoT: Opportunities and Challenges
El-Sayed M. El-Alfy, PhD & Professor
IEEE Senior
Member, Associate Editor of, IEEE Transactions on Neural Networks and Learning
Systems
King Fahd University of Petroleum and Minerals,
Saudi Arabia.
|
|
Abstract: Recent
years have witnessed a rapid development and evolution of the
Internet-of-Things (IoT) due to modern advancements in computing and
communication hardware and software technologies. The amalgamation of machine
learning with IoT has enabled smart and cost-effective applications
penetrating many facets of our daily life activities by automatically making
insights and valuable inferences of the massive amounts of data produced by
people and machines at the network edge. The global sensor market is
estimated to steadily increase reaching over 350 billion USD by 2027 with
ubiquitous deployment in cyber-physical systems in many domains such as home
appliances, transportation, healthcare, energy and utilities, manufacturing,
agriculture, defense and cybersecurity. In this talk, we will provide a
concise overview of the IoT architecture and the evolution of sensing
technologies. Moreover, we will discuss the potential benefits of machine
learning in IoT applications with demonstration of some use cases. |
Bio-Sketch: EL-SAYED M. EL-ALFY is currently a
professor and affiliated researcher the intelligent secure systems research
center, King Fahd University of Petroleum and Minerals. He has more than 25
years of experience in industry and academia, involving research, teaching,
supervision, curriculum design, program assessment, and quality assurance in
higher education. He is an approved ABET/CSAB Program Evaluator (PEV), NCAAA
reviewer, and consultant for several universities and research agents in
various countries. He is an active researcher with interests in fields related
to machine learning and nature-inspired computing and their applications to
intelligent systems and cybersecurity analytics. His work has been
internationally recognized and received a number of awards. He has published
numerously in peer-reviewed journals and conferences, edited a number of books
published by reputable international publishers, attended and contributed in
the organization of many world-class conferences, and supervised master and Ph.D.
students. Dr. El-Alfy is a senior member of IEEE and was also a member of
ACM, IEEE Computational Intelligence Society, IEEE Computer Society, IEEE
Communication Society, and IEEE Vehicular Technology Society. He has served as
a Guest Editor for a number of special journal issues, and in the editorial
board of a number of international journals, including IEEE/CAA Journal of Automatica Sinica, IEEE
Transactions on Neural Networks and Learning Systems, International Journal of
Trust Management in Computing and Communications, and Journal of Emerging
Technologies in Web Intelligence (JETWI).
AI and Games:
The Virtuous Cycle
Georgios N. Yannakakis, PhD &
Professor
Editor in Chief, IEEE
Transactions on Games, Associate Editor of, IEEE Transactions on Evolutionary
Computation
University of
Malta, Msida, Malta.
|
|
Abstract: Ever since the birth of the idea of artificial
intelligence (AI), games have been helping AI research to advance. Games not
only pose interesting and complex problems for AI to solve, they also offer a
rich canvas for creativity and expression. This rare domain where science
meets art and interaction offers unique properties for the study of AI and is
the key driver of technical progress and AI breakthroughs including deep
learning and artificial general intelligence. It is not only AI that advances
through games, however; AI has been helping games to advance across several
fronts: in the way we play them, in the way we understand their inner
functionalities, in the way we design them, and in the way
we understand play, interaction and creativity. As games get increasingly
richer and more complex through creative AI processes, AI advances further
and in turn, it advances the environments it is trained in a continuous
co-(r)evolutionary virtuous loop. Video games are arguably the most important
domain to develop AI for, while AI is arguably the most important
technological leap forward for games. |
Bio-Sketch: Georgios N. Yannakakis
is a Professor and Director of the Institute of Digital Games, University of
Malta and co-founder of modl.ai. He
does research at the crossroads of artificial intelligence, computational
creativity, affective computing, game technology, and human-computer
interaction and he has published over 260 journal and conference papers in the
aforementioned fields (h-index 57). His research has been supported by numerous
national and European grants and has appeared in Science Magazine and New
Scientist among other venues. He has been involved in a number of journal
editorial boards; he is the upcoming Editor in Chief of the IEEE Transactions
on Games and an Associate Editor of the IEEE Transactions on Evolutionary
Computation. Prof. Yannakakis has been the General
Chair of key conferences in the area of game artificial intelligence (IEEE CIG
2010) and games research (FDG 2013, FDG 2020). He is the co-author of the
Artificial Intelligence and Games textbook and the co-organizer of the
Artificial Intelligence and Games summer school series.
The many
faces of the Vehicle Routing Problem. Problem formulations, solution methods,
challenges
Jacek Ma¨½dziuk, PhD &
Professor
Member of the
Information Committee of the Polish Academy of Sciences, General
Co-Chair of the 2021 IEEE Congress on Evolutionary Computation, Chair of the
annual IEEE SSCI Symposium on Computational Intelligence for Human-like
Intelligence, Associate Editor of, IEEE Transactions on Neural Networks and Learning
Systems and the IEEE Transactions on Computational Intelligence and AI in Games.
Warsaw University of Technology,
Warsaw, Poland.
|
|
Abstract: The
Vehicle Routing Problem belongs to the most widely researched problems in the
domain of Operations Research, mainly due to its practical relevance and
combinatorial complexity. The importance of the VRP stems from its direct
application to everyday business routines of distribution / service-providing
companies. Due to a huge variety of practical implementations of the problem,
the VRP literature covers a broad range of possible extensions to the
classical problem formulation. The list of newly proposed or currently
enjoying popularity VRP formulations includes: last mile and same day
delivery, crowd shipping, bike sharing systems, post-disaster response plans,
local routing in large production or cargo plants, autonomous delivery, UAV
delivery, Green VRP, Waste Collection VRP or Rich VRP. Simultaneously, an
adequate increase of interest in the application of traditional Computational
Intelligence methods (e.g. genetic, memetic, ant colony or particle swarm
optimization, simulated annealing, or their various hybrid versions) can be
observed in the VRP domain. At the same time, approaches proven efficient in
other optimization areas (e.g. methods based on Monte Carlo simulations or
algorithms rooted in game theory) have lately entered the VRP field and
become a viable alternative to more traditional techniques. This talk
will start with presentation of the baseline versions of the problem along
with adequate population-based solutions, followed by an overview of new
problem formulations and recently-proposed solving methods. |
Bio-Sketch: Jacek Ma¨½dziuk, Ph.D., D.Sc. (Senior Member IEEE) received the
M.Sc. (Honors) and Ph.D. degrees in applied mathematics from the Warsaw
University of Technology, Warsaw, Poland, in 1989 and 1993, resp. and the D.Sc.
degree in computer science from the Systems Research Institute, Polish Academy
of Sciences, Warsaw, in 2000. He is currently Professor with the Faculty of
Mathematics and Information Science, Warsaw University of Technology, where he
is also the Head of the Division of Artificial Intelligence and Computational
Methods and the Head of the Doctoral Program in computer science. He has
authored three books (including Knowledge-free and Learning-based Methods in
Intelligent Game Playing, Springer) and 160+ research papers. His research
interests include application of Computational Intelligence and Artificial
Intelligence to games, dynamic and bilevel optimization problems, human machine
co-learning and cooperation in problem solving, and development of
general-purpose human-like learning and problem-solving methods which involve
intuition, creativity and multitasking. Prof. Ma¨½dziuk
was a recipient of the Fulbright Senior Research Award (UC Berkeley and ICSI
Berkeley, USA) and the Robert Schuman Foundation Fellowship (CNRS, Besaçon, France). Recently he has been a visiting professor
at the School of Computer Science and Engineering, Nanyang Technological
University, Singapore (2015-2017), General Co-Chair of the 2021 IEEE Congress
on Evolutionary Computation (CEC¡¯21), Krakow, Poland, and Chair of the annual
IEEE SSCI Symposium on Computational Intelligence for Human-like Intelligence
2013-2021. He is the Founding Chair of the IEEE ETTC Task Force on Toward
Human-like Intelligence and serves/served as an Associate Editor for the IEEE
Transactions on Neural Networks and Learning Systems and the IEEE Transactions
on Computational Intelligence and AI in Games.
Streaming Clustering and Predictive Health
Alerts
James M. Keller,
PhD & Professor
IEEE Life Fellow, IFSA
Fellow, President-Elect of CIS, receives the 2021 Frank Rosenblatt
Award from the IEEE
University of
Missouri, Michigan, U.S.
|
|
Abstract:
As one who has been involved in research and applications of
clustering for many years, I¡¯ve come to view the clustering enterprise
through three basic questions. 1. Do you
believe there are any clusters in your data? 2. If so, can
you come up with a technique to find the natural grouping of your data? 3. Are the
clusters you found good groupings of the data? These questions have fueled many advances to both feature
vector analytics and relational data analytics. Question1 probably draws the
least attention since us clustering folk want to get about our business. However, for example, some nice
visualization techniques have been advanced to assist with this assertion. A
side benefit of not skipping this aspect of the problem is that the methods
to provide an idea of whether the data has natural clusters also give hints
about the big question of how many clusters to search for. There are
hundreds, perhaps thousands, of answers to question 2, and always room for
more. Question 3 looks at the issue of cluster validity, usually optimizing
the number of clusters to provide compact and well separated groups of data.
With the explosion of ubiquitous continuous sensing (something Lotfi Zadeh predicted as one of the pillars of
Recognition Technology in the late 1990s), on-line streaming clustering is
attracting more and more attention. I was drawn into this world mainly due to
our desire to continuously monitor the activities, and health conditions, of
older adults in a large interdisciplinary eldercare research group. Roughly,
the requirements are that the streaming clustering algorithm recognize and
adapt clusters as the data evolves, that anomalies are detected, and that new
clusters are automatically formed as incoming data dictate. A practical
advantage of a streaming model is that data trends can be examined as they
occur, and alerts could be generated as feature vectors representing activity
move¡°toward¡±cluster boundaries. The purpose of this talk is to examine
my thoughts on streaming clustering in general, and a new early warning
approach of health changes in eldercare monitoring, based on the MU streaming
clustering algorithm. |
Bio-Sketch: James
M. Keller received the Ph.D. in Mathematics in 1978. He is now the Curators¡¯
Distinguished Professor Emeritus in the Electrical Engineering and Computer
Science Department at the University of Missouri. Jim is an Honorary Professor
at the University of Nottingham. His research interests center on computational
intelligence: fuzzy set theory and fuzzy logic, neural networks, and
evolutionary computation with a focus on problems in computer vision, pattern
recognition, and information fusion including bioinformatics, spatial reasoning
in robotics, geospatial intelligence, sensor and information analysis in
technology for eldercare, and landmine detection. His industrial and government funding
sources include the Electronics and Space Corporation, Union Electric,
Geo-Centers, National Science Foundation, the Administration on Aging, The
National Institutes of Health, NASA/JSC, the Air Force Office of Scientific
Research, the Army Research Office, the Office of Naval Research, the National
Geospatial Intelligence Agency, the U.S. Army Engineer Research and
Development Center, the Leonard Wood Institute, and the Army Night Vision and
Electronic Sensors Directorate.
Professor Keller has coauthored over 500 technical publications.
Jim is a Life Fellow of the Institute of
Electrical and Electronics Engineers (IEEE), a Fellow of the International
Fuzzy Systems Association (IFSA), and a past President of the North American
Fuzzy Information Processing Society (NAFIPS). He received the 2007 Fuzzy Systems Pioneer
Award and the 2010 Meritorious Service Award from the IEEE Computational
Intelligence Society (CIS). Jim won
the 2021 IEEE Frank Rosenblatt Technical Field Award. He has been a distinguished lecturer for
the IEEE CIS and the ACM. Jim
finished a full six years term as Editor-in-Chief of the IEEE Transactions on
Fuzzy Systems, followed by being the Vice President for Publications of the
IEEE Computational Intelligence Society from 2005-2008, then as an elected CIS Adcom member, and finished another term as VP Pubs
(2017-2020). He is President-Elect
of CIS in 2021 with his term as President in 2022 - 2023. He was the IEEE TAB Transactions Chair
as a member of the IEEE Periodicals Committee, and was a member of the IEEE
Publication Review and Advisory Committee from 2010 to 2017. Among many
conference duties over the years, Jim was the general chair of the 1991 NAFIPS
Workshop, the 2003 IEEE International Conference on Fuzzy Systems, and
co-general chair of the 2019 IEEE International Conference on Fuzzy Systems.
Swarm Intelligence Network and Mathematics
Jinde Cao, PhD &
Professor
Member of Academia
Europaea, Foreign Member of the Russian Academy of
Natural Sciences, Foreign Member of the Russian Academy of Engineering, Member
of the African Academy of Sciences,
Member of the
Pakistan Academy of Sciences, IEEE Fellow
Southeast
University, Nanjing, China.
|
|
Abstract:
This report mainly introduces the related background of Swarm
Intelligence Network, the
main work progress at home and abroad, and future prospects and reflections. |
Bio-Sketch: Jinde Cao, chief
professor of Southeast University, winner of the National Innovation Award, and
enjoys the special government allowance of the State Council. He was
successively elected as a member of the European Academy of Sciences, a member
of the Russian Academy of Engineering, a member of the Russian Academy of
Natural Sciences, a member of the African Academy of Sciences, a member of the
European Academy of Sciences and Arts, Member of the Pakistan Academy of
Sciences, Member of the International Academy of Systems and Control Sciences, and
IEEE Fellow.
He is a Chief Professor of Southeast
University, Dean of the School of Mathematics, Director of the Department of
Science, Director of the Key Laboratory of Network Group Intelligence of
Jiangsu Province, Member of the Mathematics Professional Teaching Committee of
the Ministry of Education, Standing Director of the Chinese Society of
Industrial and Applied Mathematics, Director of the Jiangsu Society of
Industrial and Applied Mathematics Chairman, Chairman of Jiangsu University
Mathematical Union, etc. The winner of the National Innovation Competition
Award enjoys a special government allowance from the State Council. He was
successively elected as a member of the European Academy of Sciences, a member
of the Russian Academy of Engineering, a member of the Russian Academy of
Natural Sciences, a member of the European Academy of Sciences and Arts, a
member of the African Academy of Sciences, a member of the Pakistan Academy of
Sciences, a member of the International Academy of Systems and Control
Sciences, and an IEEE Fellow. He has long been engaged in the research of
complex networks and complex systems, neural dynamics and optimization, and
engineering stability. He has presided over 1 national key research and
development plan project, 9 national natural science fund projects (including 1
key project), and doctoral fund of the Ministry of Education 3 projects, the
project results are included in the 2009 annual report of the National Natural
Science Foundation of China as a tour of the results of the National Natural
Science Foundation of China.
Advances in Collaborative
Neurodynamic Optimization
Jun Wang, PhD
& Professor
Foreign Member of
Academia Europaea, IEEE Fellow, IAPR Fellow, Editor-in-Chief
of IEEE Transactions on Cybernetics
City University of
Hong Kong, Hong Kong, China.
|
|
Abstract:
The past three decades witnessed the birth and growth of neurodynamic
optimization which has emerged as a potentially powerful problem-solving tool
for constrained optimization due to its inherent nature of biological
plausibility and parallel and distributed information processing. Despite the
success, almost all existing neurodynamic approaches work well only for
optimization problems with generalized convex functions. Effective
neurodynamic approaches to optimization problems with nonconvex functions and
discrete variables are rarely available. In this talk, collaborative neurodynamic
optimization approaches will be presented. In the collaborative
neurodynamic optimization framework, multiple
neurodynamic optimization models with diversified initial states are employed
for scatter local search in parallel and a meta-heuristic rule (such as PSO)
is used to reposition neuronal states upon their local convergence to escape
local minima and move toward global optimal solutions. The efficacy of the
proposed approaches will be substantiated with experimental results for,
nonnegative matrix factorization, supervised learning, vehicle-task
assignment, and portfolio selection, etc. |
Bio-Sketch: Jun Wang is the Chair Professor Computational Intelligence in the Department
of Computer Science and School of Data Science at City University of Hong Kong.
Prior to this position, he held various academic positions at Dalian University
of Technology, Case Western Reserve University, University of North Dakota, and
the Chinese University of Hong Kong. He also held various short-term visiting
positions at USAF Armstrong Laboratory, RIKEN Brain Science Institute, Dalian
University of Technology, Huazhong University of Science and Technology, and
Shanghai Jiao Tong University (Changjiang Chair
Professor). He received a B.S. degree in electrical engineering and an M.S.
degree from Dalian University of Technology and his Ph.D. degree from Case
Western Reserve University. His current research interests include neural
networks and their applications. He published over 270 journal papers, 15 book
chapters, 11 edited books, and numerous conference papers in these areas. He
was the Editor-in-Chief of the IEEE Transactions on Cybernetics (2014-2019) and
served as an Associate Editor of the IEEE Transactions on Neural Networks, IEEE
Transactions on Cybernetics and its predecessor, and IEEE Transactions on
Systems, Man, and Cybernetics: Part C, as a member of the editorial board of
Neural Networks, editorial advisory board of International Journal of Neural
Systems. He was an organizer of many international conferences such as the
General Chair of the 13th/25th International Conference on Neural Information
Processing (2006/2018), the 2008 IEEE World Congress on Computational
Intelligence, and a Program Chair of the 2012 IEEE International Conference on
Systems, Man, and Cybernetics. He is an IEEE Life Fellow, IAPR Fellow, CAAI
Fellow, and a foreign member of Academia Europaea
(The Academy of Europe). He was a Distinguished Lecturer of the IEEE
Computational Intelligence Society (CIS) and the IEEE Systems, Man and
Cybernetics Society (SMCS). In addition, he served in many professional
organizations such as Asia Pacific Neural Network Assembly (APNNA) as President
(2006), IEEE Fellow Committee, IEEE CIS Awards and Fellow Committees, IEEE SMCS
Board of Governors and Fellow Committee. He is a recipient of the APNNA
Outstanding Achievement Award, IEEE CIS Neural Networks Pioneer Award, CAAI Wu
Wenjun AI Science and Technology Achievement Award, and IEEE SMCS Norbert
Wiener Award and Outstanding Contribution Award, among other distinctions.
Advances in Evolutionary Transfer Optimization
Kay Chen Tan,
PhD & Professor
IEEE Fellow,
Editor-in-Chief of IEEE Transactions on Evolutionary Computation
Hong Kong Polytechnic University,
Hong Kong, China.
|
|
Abstract: It is known
that the processes of learning and the transfer of what has been learned are
central to humans in problem-solving. However, the study of optimization
methodology which learns from problem solved and transfer what have been learned
to help problem-solving on unseen problems, has been underexplored in the
context of evolutionary computation. This talk will touch upon the topic of
the evolutionary transfer optimization (ETO), which focuses on knowledge
learning and transfer across problems for enhanced evolutionary optimization
performance. I will first present an overview of existing ETO approaches for
problem solving in evolutionary computation. I will then introduce some of
our recent work on ETO. It will end with a discussion on future ETO research
directions, covering various topics ranging from theoretical analysis to
real-world applications. |
Bio-Sketch: Kay Chen Tan is
currently a Chair Professor (Computational Intelligence) of the Department of
Computing, The Hong Kong Polytechnic University. He has co-authored 7 books and
published over 200 peer-reviewed journal articles. Prof. Tan is currently the
Vice-President (Publications) of IEEE Computational Intelligence Society, USA.
He was the Editor-in-Chief of IEEE Transactions on Evolutionary Computation
from 2015-2020 (IF: 11.554) and IEEE Computational Intelligence Magazine from
2010-2013 (IF: 11.356). Prof. Tan is an IEEE Fellow, an IEEE Distinguished
Lecturer Program (DLP) speaker since 2012, and an Honorary Professor at
University of Nottingham in UK. He is also the Chief Co-Editor of Springer Book
Series on Machine Lear-ning: Foundations,
Methodologies, and Applications since 2020.
Challenging problems in stream data mining
Leszek Rutkowski,
PhD & Professor
Member of the
Polish Academy of Sciences, IEEE Fellow, Editor-in-chief, Journal of Artificial
Intelligence and Soft Computing Research
University of
Technology, Częstochowa, Poland.
|
|
Abstract: This lecture presents a
collection of original methods and algorithms for stream data mining. Unlike
the vast majority of previous approaches, which are largely based on
heuristics, it highlights methods and algorithms that are mathematically
justified. First, the basic concepts of stream data mining are outlined with
a special emphasis put on concept drift ¨C the phenomenon describing the
time-varying nature of streaming data. Next, it describes how to adapt
static decision trees to accommodate data streams; in this regard, new
splitting criteria are developed to guarantee that they are asymptotically
equivalent to the classical batch tree. Moreover, new decision trees are
designed, leading to the original concept of hybrid trees. In turn,
nonparametric techniques based on Parzen kernels
and orthogonal series are employed to address concept drift in the problem of
non-stationary regressions and classification in a time-varying environment.
Lastly, an extremely challenging problem that involves designing ensembles
and automatically choosing their sizes is described and solved. The material
presented in the lecture is based on the recent book: Leszek Rutkowski,
Maciej Jaworski, Piotr Duda, ¡°Stream Data Mining:
Algorithms and Their Probabilistic Properties¡±, Studies in Big Data, Springer
2020. |
Bio-Sketch: Professor Leszek
Rutkowski (IEEE Fellow and Academician - Polish Academy of Sciences) received
the M.Sc. degree in cybernetics, the Ph.D. and D.Sc. degrees in automatic
control/learning systems from the Wrocław University
of Technology, Wrocław, Poland, in 1977, 1980, and
1986, respectively, and the honoris causa degree from the AGH University of
Science and Technology, Cracow, Poland, in 2014. He has been with the
Czestochowa University of Technology, Czestochowa, Poland, since 1980, and
with the Academy of Social Sciences, Poland, since 2010; in both places he
currently holds the position of a Full Professor. From 1987 to 1990, he held a
visiting position with the School of Electrical and Computer Engineering, Oklahoma
State University, Stillwater, OK, USA. In 2004, he was elected as a member of
the Polish Academy of Sciences, Warsaw, Poland. He has authored/co-authored
over 300 publications and 8 books. Professor Leszek Rutkowski was a recipient
of the IEEE Transaction on Neural Networks Outstanding Paper Award and, as the
Chairman of the Chapter, the Outstanding Chapter Award from the IEEE
Computational Intelligence Society. He was awarded by the IEEE Fellow
Membership Grade for contributions to neurocomputing and flexible fuzzy systems
in 2004. In 2015 Professor Leszek Rutkowski received a degree honoris causa
from the prestigious AGH University of Science and Technology in Cracow ¡°in
recognition of outstanding scientific achievements in the field of artificial
intelligence in particular neuro-fuzzy systems¡±. Professor Leszek Rutkowski is
the Founding Chair of the Polish Chapter of the IEEE Computational Intelligence
Society, and in 2019 was re-elected as the President of the Polish Neural
Network Society. His current research interests include stream data mining,
neural networks, deep learning, multiagent systems, fuzzy modeling, and
pattern classification. He is editor-in-chief of the Journal of Artificial
Intelligence and Soft Computing Research, and he is on the editorial board of
the IEEE Transactions on Cybernetics, International Journal of Neural Systems,
International Journal of Applied Mathematics and Computer Science, and
Knowledge and Information Systems. He is a widely cited and internationally
recognized scholar with H index equal to 53, 43, and 42, in Google Scholar, Web
of Science, and Scopus databases, respectively.
Towards
robust and secure robot swarms
Marco Dorigo, PhD
& Professor
Member of Academia
Europaea, Inventor of the ant colony optimization metaheuristic, IEEE Fellow, AAAI
Fellow, ECAI Fellow, Editor-in-Chief of the journal ¡°Swarm Intelligence¡±
University Libre
De Bruxelles, Iridis, Belgium.
|
|
Abstract: In the talk, I will present an approach named
mergeable nervous system for robot swarms and show how it can be used to
design and implement swarms of robots that are easier to control and that can
self-repair. I will also discuss some recent results of research aimed
to improve security in robot swarms via the use of Merkle trees and of the
blockchain. |
Bio-Sketch: Marco Dorigo received the Laurea,
Master of Technology, degree in industrial technologies engineering in 1986,
and the Ph.D. degree in electronic
engineering in 1992 from the Politecnico di Milano,
Milan, Italy, and the title of Agr'eg'e de l¡¯Enseignement Sup'erieur, from ULB, in 1995. From 1992 to 1993, he was a Research Fellow at the
International Computer Science Institute,
Berkeley, CA. In 1993, he was a NATO-CNR Fellow,
and from 1994 to 1996, a Marie Curie Fellow. Since 1996, he has been a tenured Researcher of the FNRS, the Belgian
National Funds for Scientific Research,
and co-director of IRIDIA, the artificial intelligence
laboratory of the ULB. He is the inventor of the ant colony optimization metaheuristic. His current
research interests include swarm
intelligence, swarm robotics, and metaheuristics for discrete optimization. He is the Editor-in-Chief of
Swarm Intelligence, and an Associate
Editor or member of the Editorial Boards of many journals on computational intelligence and adaptive systems.
Dr. Dorigo is a Fellow of the AAAI, EurAI, and IEEE. He was awarded the Italian Prize for Artificial Intelligence in 1996, the
Marie Curie Excellence Award in 2003, the
Dr. A. De Leeuw-Damry-Bourlart
award in applied sciences in 2005, the Cajastur International Prize for Soft Computing in 2007,
an ERC Advanced Grant in 2010, the IEEE Frank
Rosenblatt Award in 2015, and the IEEE
Evolutionary Computation Pioneer Award, awarded in 2016.
Driver¡¯s Cognitive States:
Monitoring Them and Revealing Associated Information Flow in
the Brain
Nikhil R. Pal,
PhD & Professor
Member of Indian
Academy of Sciences, Member of Indian Academy of Engineering, IEEE Fellow
Indian Institute
of Statistics, Kolkata, India.
|
|
Abstract:
Every
year, in every country drowsy driving kills many people. Therefore, it is
very important to assess the vigilance levels (cognitive states) of a driver
when he/she is driving so that if the driver falls drowsy or gets distracted
by some other reason, such as by a mobile phone call, he/she can be given an
alert signal. In this talk I
consider two important issues related to drowsy driving, when EEG is used as
our source of information. 1.
We discuss the design of an unsupervised system for
detection of drowsiness in drivers in a subject and session independent
manner and at the same time using just one EEG channel so that the driver¡¯s
comfort is not affected. The system does not need any pre-trained model.
Every time any driver starts driving a fresh model of normal (alert) state of
the driver is generated and a significant deviation from the model is viewed
as a distraction. 2.
We also analyse the changes
in information flow between different brain regions when the vigilance level
of a subject changes from alert to drowsy. For this we use transfer entropy
as the vehicle. It indicates how the brain struggles, possibly by recruiting
more neurons, to maintain the activity level when the cognitive state changes
from alert to drowsy. It reveals some interesting findings that may help to
understand the cortico-cortical communication during drowsy driving. |
Bio-Sketch: Nikhil R. Pal (Fellow, IEEE)
received the B.Sc. degree in physics and Master of Business Management degree
from the University of Calcutta, Calcutta, India, and the Master of Technology
and Ph.D. degrees from the Indian Statistical Institute, Calcutta, India. He is
a Professor of Electronics and Communication Sciences Unit and the Head of the
Centre for Artificial Intelligence and Machine Learning, Indian Statistical
Institute, Kolkata, India. His current research interest includes brain
science, computational intelligence, machine learning, and data mining.
Prof. Pal was a recipient of
the 2015 IEEE Computational Intelligence Society (CIS) Fuzzy Systems Pioneer
Award. He has given many plenary/keynote speeches in different premier
international conferences in the area of computational intelligence. He was the
Editor-in-Chief of the IEEE TRANSACTIONS ON FUZZY SYSTEMS from January 2005 to
December 2010. He served/has been serving on the Editorial/Advisory
Board/Steering Committee of several journals, including the International
Journal of Approximate Reasoning, Applied Soft Computing, International Journal
of Neural Systems, Fuzzy Sets and Systems, IEEE TRANSACTIONS ON FUZZY SYSTEMS,
and the IEEE TRANSACTIONS ON CYBERNETICS. He has served as the general chair,
the program chair, and the co-program chair of several conferences. He was a
Distinguished Lecturer of the IEEE CIS from 2010 to 2012 and from 2016 to 2018,
and a member of the Administrative Committee of the IEEE CIS from 2010 to 2012.
He served as the Vice-President for Publications of the IEEE CIS from 2013 to
2016 as well as the President of the IEEE CIS from 2018 to 2019. He is a Fellow
of the National Academy of Sciences, India, Indian National Academy of
Engineering, Indian National Science Academy, International Fuzzy Systems
Association, and The World Academy of Sciences.
Bayesian Networks for Interpretable Machine Learning and Optimization
Pedro Larrañaga, PhD & Professor
Member of the
Academia Europaea, EurAI
Fellow, Fellow of the Asia-Pacific Artificial Intelligence Association
Universidad Polit¨¦cnica de Madrid, Madrid, Spain.
|
|
Abstract: Artificial
intelligence is being increasingly used for high-stakes applications, and it
is becoming more and more important that the models used to be interpretable.
Bayesian networks offer a paradigm for interpretable artificial intelligence
that is based on probability theory. This talk discusses techniques and
algorithms that have been developed in the field of Bayesian networks to
facilitate the interpretation of machine learning models as well as the
heuristic optimization process. With regard to machine learning models,
several approaches will be shown that allow understanding the process of
structural learning of a Bayesian network from data, to later discuss about
the visualization options of said models and finally introduce methods to
interpret different types of reasoning (diagnostic, intercausal, predictive,
abductive, counterfactual, ...) that Bayesian networks are capable of
providing. The heuristic optimization process that an evolutionary algorithm
follows will be interpreted from the so-called estimation of distribution
algorithms in which the crossover and mutation operators used in the genetic
algorithms are replaced in each generation by the learning and simulation of
a Bayesian network. |
Bio-Sketch: Pedro Larrañaga
is Full Professor in Computer Science and Artificial Intelligence at the
Universidad Polit¨¦cnica de Madrid. He received the
MSc degree in Mathematics (Statistics) from the University of Valladolid and
the PhD degree in Computer Science from the University of the Basque Country
(Excellence Award). His research interests are primarily in the areas of
probabilistic graphical models, metaheuristics for optimization, machine
learning classification models, and real applications, like biomedicine,
bioinformatics, neuroscience, industry 4.0 and sports. He has published more than
200 papers in high impact factor journals and has supervised more than 30 PhD
theses. He is fellow of the European Association for Artificial Intelligence
since 2012 and fellow of the Academia Europaea and of
the Asia-Pacific Artificial Intelligence Association since 2018 and 2021
respectively. He has been awarded the 2013 Spanish National Prize in Computer
Science, the prize of the Spanish Association for Artificial Intelligence in 2018
and the Amity Research Award in Machine Learning in New Delhi, in 2020.
Evolving Fuzzy Models and Applications
Radu-Emil Precup, PhD & Professor
Corresponding Member of the Romanian Academy, Editor-in-Chief,
International Journal of Artificial Intelligence, Editorial board of IEEE
Transactions on Fuzzy Systems, IEEE Transactions on Cybernetics
Politehnica University of
Timisoara, Timisoara, Romania
|
|
Abstract: As
shown in the classical papers on evolving fuzzy systems (EFSs), evolving
Takagi-Sugeno or Takagi-Sugeno-Kang
fuzzy models are characterized by continuous online rule base learning. These
fuzzy models are developed in terms of the application of online
identification algorithms. The online identification algorithms continuously
evolve the parameters of the fuzzy models, which are built online by adding
new or removing old local models. This process is referred to as the adding
mechanism. According to the recent classification of online identification
algorithms (Dovžan, Logar
and Škrjanc, 2015), three categories of online
identification algorithms are considered, (1), (2) and (3): (1) adaptive
algorithms ¨C they start with the initial Takagi-Sugeno-Kang
fuzzy model structure given by other algorithms or by user experience, the
number of space partitions/clusters does not change over time, and these
algorithms adapt just the parameters of the membership functions and the
local models; (2) incremental algorithms ¨C they implement only adding
mechanisms; (3) evolving algorithms ¨C these algorithm implement, besides the
adding mechanism, also the removing and a part of them the merging and the
splitting mechanisms. These specific features ensure a large area of
applications. This speech highlights a part of the results obtained by the
Process Control group of the Politehnica University
of Timisoara, Romania. The presentation is focused on representative
applications, implemented in our labs, with real-validated by experimental
results. The results pointed out here include different lab equipment as
pendulum-crane systems, twin rotor aerodynamic systems, magnetic levitation
systems, anti-lock braking systems, and shape memory alloy systems. The scope
of the development of these models is the model-based and data-driven
model-free design and tuning of fuzzy controllers by the Process Control
Group. |
Keywords¡ªapplications, evolving fuzzy models, lab equipment,
Takagi-Sugeno-Kang fuzzy models
Bio-Sketch: Radu-Emil Precup (M IEEE '03 - SM IEEE '07) was born in Lugoj,
Romania, in 1963. He received the Dipl.Ing. (Hons.)
degree in automation and computers from the "Traian
Vuia" Polytechnic Institute of Timisoara,
Timisoara, Romania, in 1987, the Diploma in mathematics from the West
University of Timisoara, Timisoara, in 1993, and the Ph.D. degree in automatic
systems from the "Politehnica" University
of Timisoara, Timisoara, in 1996.
From 1987 to
1991, he was with Infoservice S.A., Timisoara. He is
currently with the Politehnica University of
Timisoara, Romania, where he became a Professor in the Department of Automation
and Applied Informatics, in 2000, and he is currently a Doctoral Supervisor of
automation and systems engineering. He is also an Adjunct Professor within the
School of Engineering, Edith Cowan University, Joondalup, WA, Australia, and a
Member of the Doctoral School of Applied Informatics with the Óbuda University (previously named Budapest Tech
Polytechnical Institution), Budapest, Hungary. He is currently the Director of
the Automatic Systems Engineering Research Centre with the Politehnica
University of Timisoara, Romania. From 1999 to 2009, he held research and
teaching positions with the Universit¨¦ de Savoie, Chamb¨¦ry and Annecy,
France, Budapest Tech Polytechnical Institution, Budapest, Hungary, Vienna
University of Technology, Vienna, Austria, and Budapest University of
Technology and Economics, Budapest, Hungary. He has been an Editor-in-Chief of
the International Journal of Artificial Intelligence since 2008 and he is also
on the editorial board of several other prestigious journals including IEEE
Transactions on Fuzzy Systems, IEEE Transactions on Cybernetics, Information
Sciences (Elsevier), Engineering Applications of Artificial Intelligence
(Elsevier), Applied Soft Computing (Elsevier), Expert Systems with Applications
(Elsevier), Evolving Systems (Springer), Healthcare Analytics (Elsevier),
Communications in Transportation Research (Elsevier) and Cogent Engineering
(Taylor & Francis).
He is the
author or coauthor of more than 300 papers published in various scientific
journals, refereed conference proceedings, and contributions to books. His
research interests include mainly development and analysis of new control
structures and algorithms (conventional control, fuzzy control, data-based
control, sliding mode control, neuro-fuzzy control, etc.), theory and
applications of soft computing, computer-aided design of control systems,
modeling, optimization (including nature-inspired algorithms), and applications
to mechatronic systems (including automotive systems and mobile robots),
embedded systems, control of power plants, servo systems, electrical driving
systems.
Prof. Precup is a corresponding member of The Romanian Academy, a
Doctor Honoris Causa of the Óbuda University,
Budapest, Hungary, a Doctor Honoris Causa of the Sz¨¦chenyi
Istv¨¢n University, Győr,
Hungary, a member of the Subcommittee on Computational Intelligence as part of
the Technical Committee (TC) on Control, Robotics and Mechatronics in the Institute
of Electrical and Electronics Engineers (IEEE) Industrial Electronics Society,
the Task Force on Autonomous Learning Systems within the Neural Networks TC of
the IEEE Computational Intelligence Society, the TCs on Computational
Cybernetics and Cyber-Medical Systems of the IEEE Systems, Man, and Cybernetics
Society, the Task Force on Adaptive and Evolving Fuzzy Systems within the Fuzzy
Systems Technical Committee of the IEEE Computational Intelligence Society, the
International Federation of Automatic Control (IFAC) Technical Committee on
Computational Intelligence in Control (previously named Cognition and Control),
the Working Group WG 12.9 on Computational Intelligence of the Technical
Committee TC12 on Artificial Intelligence of the International Federation for
Information Processing (IFIP), the European Society for Fuzzy Logic and
Technology (EUSFLAT), the Hungarian Fuzzy Association, and the Romanian Society
of Control Engineering and Technical Informatics.
He was the
recipient of the Elsevier Scopus Award for Excellence in Global Contribution
(2017), the "Tudor Tănăsescu" Prize from
the Romanian Academy for data-driven controller tuning techniques (2020), the
"Grigore Moisil"
Prize from the Romanian Academy, two times, in 2005 and 2016, for his contribution
on fuzzy control and the optimization of fuzzy systems, the Spiru
Haret Award from the National Grand Lodge of Romania
in partnership with the Romanian Academy in 2016 for education, environment and
IT, the Excellency Diploma of the International Conference on Automation,
Quality & Testing, Robotics AQTR 2004 (THETA 14, Cluj-Napoca, Romania), two
Best Paper Awards in the Intelligent Control Area of the 2008 Conference on
Human System Interaction HSI 2008, Krakow (Poland), the Best Paper Award of
16th Online World Conference on Soft Computing in Industrial Applications WSC16
(Loughborough University, UK) in 2011, the Certificate of Appreciation for the
Best Paper in the Session TT07 1 Control Theory of 39th Annual Conference of
the IEEE Industrial Electronics Society IECON 2013 (Vienna, Austria), a Best
Paper Nomination at 12th International Conference on Informatics in Control,
Automation and Robotics ICINCO 2015 (Colmar, France), a Best Paper Award at 7th
International Conference on Information Technology and Quantitative Management
ITQM 2019 (Granada, Spain), a Best Paper Award at 8th International Conference
on Information Technology and Quantitative Management ITQM 2020 & 2021 (Chengu, China), and was listed as one of the top 10
researchers in Artificial Intelligence and Automation (according to IIoT World as of July 2017).
Dynamic objects motion analysis in video by using
optical flow and neural networks
Sergey V. Ablameyko, PhD & Professor
Member of Belarus
Academy of Sciences, Member of Academia Europaea, IAPR
Fellow, AAIA Fellow and Vice-President
Belarusian State
University, Minsk, Republic of Belarus.
|
|
Abstract:
One of the important tasks in situation monitoring in video sequences
is tracking of dynamic objects. Dynamic objects are physical bodies, devices,
or set of interconnected bodies or devices such as moving cyclone, moving
group of people, a growing cell or aggregation of cells, etc. Such an object
has an internal structure consisting of interacting dynamic elements. Dynamic
objects combine movement of objects as a whole with the movement of internal
structures, their aggregation, dispersion, direct of chaotic movement of
internal structures. The presentation will be devoted to dynamic objects
motion analysis in video by using optical flow and neural networks. First, we
determine the main types of motion which make it possible to separate the key
moments of the object motion and describe the stages of their movement and
their interaction with each other. We use basic optical flow to form integral
optical flow and use it to separate background and foreground and obtain
intensive motion regions. Based on information extracted from integral optical
flow, we introduce notion of motion maps and show how it can be used for
object motion analysis. In motion maps, we analyze pixel motions
statistically for each frame to obtain quantity of pixels moving toward or away
from each pixel and their comprehensive motion at each pixel. We then define
and compute regional motion indicators to describe motions at region-level.
These indicators are further used for analysis of dynamic object behavior.
Motion maps allow to determine the moment at which the state starts to change
and we classify the main types of motion in the objects¡¯ population: directed
motion, aggregation (motion towards each other), dispersion (motion in
different directions with respect to the common center), division (formation
of several new objects in the place where the old one was), and apoptosis
(object destruction). |
It was used to
analyze objects¡¯ motion by using the integral optical flow. Several tasks have
been solved.
The first
application is analysis of biomedical images. Analysis of stem cell behavior in
microscopic video. Important part of living cell monitoring is the
investigation of dynamical properties of cells, cell conglomerates and cellular
interactions including detection of spatiotemporal localization of mitosis
events. We show cell monitoring algorithm that analyze behavior of the cells¡¯
population as a system of dynamical objects by using a concept of the integral
optical flow. The presented results are used for monitoring and quantitative
analysis of the development of cell cultures, estimating the dynamic changes
taking place in them, and determining the population¡¯s heterogeneity and
viability.
A method for determining the
characteristics of blood flow in the vessels of eye conjunctiva, such as linear
and volumetric blood speed, and topological characteristics of vascular net was
developed. To solve the problem of vessels network segmentation, we use a fully
connected convolutional neural network. The peculiarity of its organization is
that the usual convolution network is supplemented with layers in which the
union operators are replaced by operators of increasing discretization, which
leads to an increase in the resolution of the output image. Combining features
with higher resolution from a narrowing area with an expanding output area
allows to train convolutional layers to form a more accurate result at the
output. We show the efficiency of our method in real eye vessels scenes.
Second, a method
for monitoring dynamic wound changes in video sequence based on integral optical
flow will be shown. Dynamic characteristics of wound tissue changing are
introduced and calculated. We show the efficiency of our method in real wound
scenes.
The second
application is people and crowd behavior in video. We developed a new method to
identify and track crowd motion in videos based on integral optical flow.
During this process, three factors, quantity, intensity and direction of moving
pixels, are to be considered. Based on integral optical flow, we can then
define and construct four motion maps to together describe pixel motions at
each position, i.e. statistical analysis of quantity and motion direction of
pixels moving toward or away from each position. After that, we introduce
regional motion indicators to analyze motion at region-level which is
appropriate for group people motion analysis. At last, we use threshold
segmentation to identify crowd motion. The method is based on crowd geometric
structure formed by crowd motion in certain time period.
We also applied
our approach to analyze cars movement in video and detect flow extreme
situations in real-world videos. We defined and calculated parameters of moving
car flow including direction, speed, density, and intensity without detecting
and counting cars.
In presentation,
many real videos with object motion analysis will be shown.
Bio-Sketch: Sergey
Ablameyko (born in 1956, DipMath
in 1978, PhD in 1984, DSc in 1990, Prof in 1992). He was a General Director of the United
Institute of Informatics Problems of the National Academy of Sciences of
Belarus (2002-2008), Rector (President) of the Belarusian State University
(2008-2017) and now he is a Professor of BSU.
He has more than
650 publications including 25 authored/co-authored books (one published by
Springer (UK), one - by SPIE (USA), one ¨C by Exit (Poland) and 25 edited books
(two published by IOS Press in NATO Science Series). In his academic career he
was a visiting scientist in Italy, Japan, Sweden, Finland, England, Germany,
UK, Greece, Spain, Australia, New Zealand, China. He was a chair/co-chair,
member of Program Committees of numerous (more than 100) International conferences
held worldwide.
He is in Editorial
Board of Pattern Recognition and Image Analysis, Non-linear Phenomena in
Complex Systems and many other international journals. His scientific interests
are: Image analysis, pattern recognition, digital geometry, graphics
recognition, knowledge-based systems, geographical information systems, medical
imaging.
He is IEE Fellow
(UK) (1995), IEEE Senior Member (USA) (1995), Academician of International
Academy of Information Processes and Technologies (1995), Academician of
Belarusian Academy of Engineering (1995), Fellow of International Association
for Pattern Recognition (1998), Academician of the National Academy of Sciences
of Belarus (2009), Academician of Spanish Royal Academy of Doctors (2009),
Academician of European Academy of Economy and Enterprise Management (2010),
Academician of Academia Europea (2011), Honorary
professor of Grodno State University, Belarus (2012), Academician of Russian
Space Academy (2012), Honorary professor of Dalian University of Technology,
China (2013), Honorary professor of Moscow State University, Russia (2014),
Honorary professor of Binh Duong University, Vietnam
(2014), Academician of Russian Academy of Natural Sciences (2015), Academician
of Spanish Royal Academy of Economics and Finance (2016), Honorary professor of
Belgrade Alfa BK University, Serbia (2016).
For his activity
he was awarded by State Prize of Belarus (highest national scientific award),
Friendship Award of Russian Federation (2009), Friendship Award of Zhejiang Province
of China (2018) and many other national and international awards.
Efficient
Computational Approaches and Applications to Some Optimization Problems in
Smart Grid
Tingwen Huang, PhD &
Professor
Member of Academia
Europaea, IEEE Fellow, AAIA Fellow
Texas A&M
University at Qatar, College Station, Texas, USA.
|
|
Abstract:
In a smart grid
context, first we will look at the trading optimization problem among
Microgrids which benefit all sides. A multi-leaders and multi-followers Stackelberg game model is proposed for energy trading
problem in a multi-energy microgrid system. Then, we consider the
optimization problem in energy wholesale market when incorporating renewable
energy sources, and a two-stage Stackelberg-Cournot stochastic game model is established.
The risk measurement technique, conditional value at risk (CVaR), is harnessed to estimate the overbidding risk.
Third, we will consider the Plug-In Electric Vehicles (PEVs) Charging: Feeder
Overload Control problem. The last optimization problem is to consider
minimizing the total cost of the generators when they generating electricity
satisfying the demand. |
Bio-Sketch: Tingwen Huang
received his B.S. from Southwest Normal University, M.S. from Sichuan
University and Ph.D. from Texas A&M University. Now, he is a professor at
Texas A&M University at Qatar, Qatar. His research focuses on dynamics of
nonlinear systems including neural networks, complex networks and multi-agent
and their applications to smart grids and other areas. He has published some
papers in these areas.
He is
very actively involving in professional service. He serves/served as President
(2020) for Asia Pacific Neural Network Society, as an action editor or
associate editor for several international journals.
He is a
Member of the European Academy of Sciences and Arts, an Academician of the
International Academy for Systems and Cybernetic Sciences, a Fellow of IEEE and
AAIA (Asia-Pacific Artificial Intelligence Association), a Changjiang
Chair Professor.
Why and How to fuse Deep Learning and
Fuzzy Logic Systems?
Tufan Kumbasar, PhD & Associate Professor
Area Editor-in-Chief, International
Journal of Approximate Reasoning, Associate Editor of, IEEE
Transaction on Fuzzy Systems
Istanbul Technical
University, Maslak-Istanbul, Turkey.
|
|
Abstract:
It has been shown in various
studies that Interval Type-2 (IT2) Fuzzy Sets (FSs) and Fuzzy Logic Systems
(FLSs) can bring significant performance improvement in control, regression,
and classification problems when compared to its Type-1 (T1) counterparts.
However, the performance of FLSs depends on the number (and shape) of the
MFs, the dimension size of the inputs and outputs, and the volume of data.
The increasing number/ size of these factors naturally results in the issues,
which are the curse of dimensionality and the increasing training complexity
of FLSs since they have many learnable parameters. On the other hand, Deep
Learning (DL) stands up as the jewel of machine learning when tackling these
issues, especially from the representation power of deep neural networks.
This talk will introduce the basic concepts of FLSs alongside DL by means of
various case studies. I will explain how and why DL methods should be
integrated into or combined with FLSs to enhance the learning performance of
models. The talk will showcase various successful fusing applications of
IT2-FLS and DL integration studies. |
Bio-Sketch: Tufan Kumbasar
received B.Sc., M.Sc., and Ph.D. degrees in Control and Automation Engineering
from Istanbul Technical University. He is currently an Associate Professor in
the Control and Automation Engineering Department and the director of
Artificial Intelligence and Intelligent Systems (AI2S) Laboratory, Faculty of
Electrical and Electronics Engineering, Istanbul Technical University.
He has currently authored more than 100 papers in
international conferences, journals, and books. His major research interests
are in computational intelligence, notably type-2 fuzzy logic, fuzzy control,
neural networks, evolutionary algorithms, and intelligent systems. He is also
interested in robotics, machine learning, intelligent control, and their
real-world applications. He has served as a Publication Co-Chair, Panel Session
Co-Chair, Special Session Co-Chair, PC, IPC, and TPC in various international
and national conferences. Dr. Kumbasar is an
Associate Editor for the IEEE Transactions on Fuzzy Systems and an Area Editor
for the International Journal of Approximate Reasoning.
Dr. Kumbasar received the
Best Paper Awards from the IEEE International Conference on Fuzzy Systems in
2015 and the 6th International Conference on Control Engineering &
Information Technology in 2018. He was the recipient of the ODTÜ Mustafa N. Parlar Research and Education Foundation Research Incentive
Award in 2020.
Witold Pedrycz, PhD &
Professor
Member of the
Royal Society of Canada, Foreign Member of the Polish Academy of Sciences, IEEE
Life Fellow, Editor in Chief, Information Sciences, Co-editor-in-Chief of Int.
J. of Granular Computing
University of Alberta, Edmonton, Canada
|
|
Abstract:
With enormous amounts of data
come opportunities of building models of real-world systems that are
instrumental in realizing a plethora of control, prediction, and
classification tasks. The interpretability facet of ensuing models becomes
highly relevant in light of designing autonomous systems and all those
constructs supporting human-centric decision-making environments. To
transform data to tangible and actionable pieces of knowledge and formulate a
problem at hand at a suitable level of abstraction, a convenient way to
proceed is to position the problem in the environment of Granular
Computing. We advocate that a systematic way of capturing
knowledge residing within acquired data and encapsulating such knowledge in
the form of interpretable models is supported by a suitable level of
abstraction at which the data are to be represented. An abstraction mechanism
is conveniently realized in the form of information granules. Information
granules and Granular Computing deliver an operational and flexible setting in
which granular models are built and analyzed. A formal characterization of
information granules is introduced where they are concisely described as
triple (G, I, R) capturing their underlying geometry in the data space (G),
information content (I), and representation capabilities given the underlying
experimental evidence (R). |
A suite of design methods transforming data into
information granules being articulated in various formal settings (e.g.,
intervals, fuzzy sets, rough sets) is analyzed and an array of generalizations
is discussed (including collaborative ways of building granules in the presence
of some auxiliary domain knowledge). Equally important is an evaluation of the
quality of information granules sought as an abstraction mechanism of data with
the help of a reconstruction criterion (degranulation).
In the sequel, it is shown how information granules
regarded as functional modules are efficiently used in the construction of a
vast array of interpretable models, especially rule-based architectures. It is
discussed how learning mechanisms are carried out in a unified setting of
knowledge-based learning completed in the presence of data and information
granules.
Bio-Sketch: Witold Pedrycz (IEEE Life
Fellow) 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. Dr. Pedrycz is a foreign member of the Polish Academy of
Sciences and a Fellow of the Royal Society of Canada. He is a recipient
of several awards including Norbert Wiener award from the IEEE Systems,
Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre
for Soft Computing, a Killam Prize, a Fuzzy Pioneer Award from the IEEE
Computational Intelligence Society, and 2019 Meritorious Service Award from the
IEEE Systems Man and Cybernetics Society.
His main research directions involve Computational
Intelligence, Granular Computing, knowledge discovery, data science, and
knowledge-based neural networks among others.
Dr. Pedrycz is 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 Co-editor-in-Chief of Int. J. of Granular Computing (Springer)
and J. of Data Information and Management (Springer).
Ensemble
Approaches to Class Imbalance Learning
Xin Yao, PhD & Professor
IEEE Fellow, Royal
Society Wolfson Research Merit Award, IEEE Computational Intelligence Society
Evolutionary Computation Pioneer Award
University of Birmingham, Birmingham, UK.
|
|
Abstract:
Many real-world classification problems have highly imbalanced and
skew data distributions. In fault diagnosis and condition monitoring for
example, there are ample data for the normal class, yet data for faults are
always very limited and costly to obtain. It is often a challenge to increase
the performance of a classifier on minority classes without sacrificing the
performance on majority classes. This talk discusses some of the techniques
and algorithms that have been developed for class imbalance learning,
especially through ensemble learning. First, the motivations behind ensemble
learning are introduced and the importance of diversity highlighted. Second,
some of the challenges of multi-class imbalance learning and potential
solutions are presented. What might have worked well for the binary case do
not work for multiple classes anymore, especially when the number of classes
increases. Third, online class imbalance learning will be discussed, which
can be seen as a combination of online learning and class imbalance learning.
Online class imbalance learning poses new research challenges that still have
not been well understood, let alone solved, especially for imbalanced data
streams with concept drift. Fourth, the natural fit of multi-objective
learning to class imbalance learning is pointed out. The relationship between
multi-objective learning and ensemble learning will be discussed. Finally,
future research directions will be given. |
Bio-Sketch: Yao Xin is a Chair Professor of Computer
Science at the Southern University of Science and Technology, Shenzhen, China,
and a part-time Professor of Computer Science at the University of Birmingham,
UK. His major research interests include evolutionary computation, ensemble
learning and search-based software engineering. He is an IEEE fellow, a former
(2014-15) President of IEEE Computational Intelligence Society (CIS) and a
former (2003-08) Editor-in-Chief of IEEE Transactions on Evolutionary
Computation. His work won the 2001 IEEE Donald G. Fink Prize Paper Award, 2010,
2016 and 2017 IEEE Transactions on Evolutionary Computation Outstanding Paper
Awards, 2010 BT Gordon Radley Award for Best Author of Innovation (Finalist),
2011 IEEE Transactions on Neural Networks Outstanding Paper Award, and many
other best paper awards at conferences. He received a Royal Society Wolfson
Research Merit Award in 2012, the IEEE CIS Evolutionary Computation Pioneer
Award in 2013, and the 2020 IEEE Frank Rosenblatt Award.
Privacy-Preserving Data-Driven
Evolutionary Optimization
Yaochu Jin, PhD &
Professor
Member of Academia
Europaea, IEEE Fellow, Editor-in-Chief of IEEE
Transaction on Cognitive and Development Systems, Complex & Intelligent
Systems
Bielefeld University,
North Rhine Westphalia, Germany.
|
|
Abstract:
Privacy
preservation is a key concern in data-driven machine learning and
decision-making. This talk begins with an introduction to privacy-preserving
machine learning and data-driven evolutionary optimization. Then, we present
one single-objective and one multi-objective data-driven evolutionary
algorithms that can perform optimization based on data distributed on
multiple devices, without requiring to collect and store the data on a single
server. Empirical results show that the federated data-driven evolutionary
algorithms perform comparably well with centralized data-driven algorithms,
while being able to preserve the data privacy. |
Bio-Sketch: He is an Alexander von Humboldt Professor
for Artificial Intelligence endowed by the Germany Federal Minister of
Education and Research, Chair of Nature Inspired Computing and Engineering,
Faculty of Technology, Bielefeld University, Germany. He is also a Distinguished
Chair, Professor in Computational Intelligence, Department of Computer Science,
University of Surrey, Guildford, U.K. He was a ¡°Finland Distinguished
Professor¡± of University of Jyväskylä, Finland, ¡°Changjiang Distinguished Visiting Professor¡±, Northeastern
University, China, and ¡°Distinguished Visiting Scholar¡±, University of
Technology Sydney, Australia. His main research interests include evolutionary
optimization, evolutionary learning, trustworthy machine learning, and
evolutionary developmental systems.
Prof Jin
is presently the Editor-in-Chief of the IEEE TRANSACTIONS ON COGNITIVE AND
DEVELOPMENTAL SYSTEMS and the Editor-in-Chief of Complex & Intelligent
Systems. He was an IEEE Distinguished Lecturer in 2013-2015 and 2017-2019, the
Vice President for Technical Activities of the IEEE Computational Intelligence
Society (2015-2016). He is the recipient of the 2018 and 2021 IEEE Transactions
on Evolutionary Computation Outstanding Paper Award, and the 2015, 2017, and
2020 IEEE Computational Intelligence Magazine Outstanding Paper Award. He was
named by the Web of Science as ¡°a Highly Cited Researcher¡± consecutively from
2019 to 2021. He is a Member of Academia Europaea and
Fellow of IEEE.
Human¨CComputer
Interaction of robots
Zengguang Hou, PhD & Professor
IEEE Fellow, editorial board of "IEEE
Transactions on Cybernetics", "Neural Networks"
Institute of
Automation, Chinese Academy of Sciences, Beijing, China.
|
|
Abstract:
Intelligent
robots are entering our living and working spaces, but their popularization
and application are also facing many challenges. Besides, high-efficiency,
reliable, and safe human-computer interaction and control are an important
challenge that hinders their development. The report combines the
acquisition and processing of multi-modal biological signals and the active
and passive control applications of rehabilitation robots, expounds the
challenges in related fields, as well as the thinking and prospects for
future development. |
Bio-Sketch: Prof. Hou is a researcher and doctoral supervisor at the Institute of Automation of the Chinese Academy of Sciences, and concurrently serves as the deputy director of the State Key Laboratory of Management and Control of Complex Systems. He is an IEEE Fellow, a receiver of National Funds for Distinguished Young youths and the Participants of the National Special Support Plan for High-level Talents. He is currently the vice chairman of the Chinese Society of Automation, the vice chairman of the International Society of Asia-Pacific Neural Networks, the director of the International Society of Neural Networks, and the editorial board of "IEEE Transactions on Cybernetics", "Neural Networks" and other journals.