|
Prof.
Hojjat Adeli
|
Prof. Andrzej Skowron
|
Prof. Ruay-Shiung Chang
|
|
|
|
|
|
|

|
Prof. Hojjat Adeli
Abba
G. Liechtenstein Professor
The Ohio State University, USA
|
Chaos-Wavelet-Neural Network Models for Automated
EEG-Based Diagnosis of Neurological Disorders |
The author has been advancing a multi-paradigm integrated approach
for solution of complicated and intractable dynamic pattern recognition
problems. The focus of this keynote lecture is data mining and knowledge
discovery from time-series signals obtained from complex phenomena.
Novel wavelet-chaos-neural network models are presented for signal processing
of brain waves as recorded by electroencephalographs for automated electroencephalogram
(EEG)-based diagnosis of neurological disorders such as epilepsy and
the Alzheimer’s disease (AD). Through extensive parametric studies
and information reuse and integration certain combinations of parameters
from the EEG sub-bands were discovered to be effective markers for seizure
detection and epilepsy diagnosis. The model can distinguish among healthy,
interictal, and ictal EEGs with a high accuracy of 96%, substantially
better than practicing neurologists. Other algorithms for diagnosis
of the AD and Attention Deficit Hyperactivity Disorder (ADHD) will also
be discussed briefly.
|
About
Prof. Hojjat Adeli |
Hojjat Adeli received his Ph.D. from Stanford University in 1976 at the
age of 26 after receiving his B.S.-M.S. degrees from the University of
Tehran in 1973. He has authored over 430 research and scientific publications
in various fields of computer science, engineering, applied mathematics,
and medicine including 14 books such as Machine Learning - Neural Networks,
Genetic Algorithms, and Fuzzy Systems, Wiley, 1995; Neurocomputing for
Design Automation, CRC Press, 1998; Wavelets in Intelligent Transportation
Systems, Wiley, 2005; and Intelligent Infrastructure – Neural Networks,
Wavelets, and Chaos Theory for Intelligent Transportation Systems and
Smart Structures, CRC Press, 2009. His most recent book is Automated EEG-based
Diagnosis of Neurological Disorders - Inventing the Future of Neurology,
CRC Press, 2010. He is the Founder and Editor-in-Chief of Computer-Aided
Civil and Infrastructure Engineering, now in 25th year of publication
and Integrated Computer-Aided Engineering, now in 17th year of publication,
and the Editor-in-Chief of International Journal of Neural Systems. He
is the quadruple winner of the OSU College of Engineering Lumley Award
for outstanding research accomplishments. In 1998 he received the Distinguished
Scholar Award from OSU, the university’s highest research award,
“in recognition of extraordinary accomplishment in research and
scholarship”. In 2005, he was elected Honorary/Distinguished Member,
ASCE: "for wide-ranging, exceptional, and pioneering contributions
to computing in civil engineering and extraordinary leadership in advancing
the use of computing and information technologies in many engineering
disciplines throughout the world.” In 2007, he received the OSU
College of Engineering Peter L. and Clara M. Scott Award for Excellence
in Engineering Education as well as the Charles E. MacQuigg Outstanding
Teaching Award. He is a Fellow of the American Association for the Advancement
of Science. |

|
Prof.
Andrzej Skowron
University of Warsaw, Poland |
Introduction to Perception-based Computing |
We discuss Perception-based Computing (PbC) in the
Wisdom Technology (Wistech) framework. The intuitive nature of wisdom
in Wistech can be expressed by the so called wisdom equation metaphorically
described by
wisdom = knowledge + adaptive_ judgment + interactions
Interactive Rough-Granular Computing (IRGC) is used as the basic methodology
for PbC. Key issue in Granular Computing (GC) is information granulation
(IG). IG is used for modeling of human way of data compression and plays
a key role in problem solving by human. Due to limited abilities of
human organs, human perception is usually imprecise (e.g., boundary
between decision classes are vague, values of attributes are granular).
Hence, in IRGC the rough set approach in combination with the other
soft computing approaches for dealing with imprecise knowledge are used.
Computations in IRGC are performed on different kinds of objects, called
information granules (such as sensory granules, decision rules or sets
of decision rules, classifiers for vague concepts, agents or coalitions
of agents). These computations are progressing through interactions
between granules. In the discussed approach, methods for modeling of
interactions among granules and interactive computations are of great
importance. Some granules (e.g., agents) have ability to perceive objects.
Perception by such granules is understood here as a process resulting
in activation of some parts (e.g., complex concepts) of these granules.
This activation is caused by interactions of sensory parts of the granules
with distributed environments and other parts of these granules (e.g.,
granules stored in knowledge networks representing behavioral patterns
of observed objects or different components of activated complex granules).
The activated parts are used, e.g., for triggering of actions or plans.
We discuss how granules such as complex vague concepts can be approximated
using domain ontology approximation. This illustrates how the activation
of complex granules can be realized, i.e., how, in the discussed model,
the perception results are computed. Some applications of the discussed
approach in real-life projects such as medical decision support, identification
o complex behavioral patterns on the road or sunspot classification
are reported. |
About
Prof. Andrzej Skowron |
Andrzej Skowron received the Ph. D. and D. Sci. (habilitation) from
the University of Warsaw in Poland. In 1991 he received the Scientific
Title of Professor. He is Full Professor in the Faculty of Mathematics,
Computer Science and Mechanics at Warsaw University. Andrzej Skowron
is the (co)author of more than 350 scientific publications. His areas
of expertise include reasoning with incomplete information, approximate
reasoning, soft computing methods and applications, rough sets, rough
mereology, granular computing, synthesis and analysis of complex objects,
intelligent agents, knowledge discovery and data mining, decision support
systems, adaptive and autonomous systems. He was the supervisor of more
than 20 PhD Thesis. He was also involved in several national and international
research and commercial projects related to, e.g., data mining (fraud
detection, web mining), control of unmanned vehicles, medical decision
support systems and approximate reasoning in distributed environments.
In the period 1995-2009 he was the Editor-in-Chief of Fundamenta Informaticae
journal. He is the co-editor-in-chief of the LNCS Transactions on Rough
Sets journal published by Springer. He is on Editorial Boards of many
others journals including Knowledge Discovery and Data Mining. Andrzej
Skowron was the President of the International Rough Set Society from
1996 to 2000. He served or is currently serving on the program committees
of more than 100 international conferences and workshops, as program
or steering committee member, program chair or co-chair. He has delivered
numerous invited talks at international conferences including a plenary
talk at the 16-th IFIP World Computer Congress (Beijing, 2000). Throughout
his career Andrzej Skowron received many awards for his achievements.
|
|
Prof.
Ruay-Shiung Chang
Professor, Department of Computer Science
and Information Engineering,
National Dong Hwa University |
Social
Networks: Research and Applications |
On September 5, 2010, an opinion article in the Washington
Post titled "Facebook and social media offer the potential of peace"
appeared. The peace refers to the situation in Mideast. When young generations
socialize between themselves using Facebook, MySpace, and/or Tweeter,
war is less likely and peace may be possible.
Social media or social networks are changing the world, from how people
make friends to how information is disseminated. More than 500 million
people use Facebook alone. Of those, 70 percent are outside the United
States. MySpace has 122 million monthly active users, and Twitter reports
145 million registered users. With their many users and vast amount
of data produced each moment, social networks offer many research challenges
in computer science.
For example, different from conventional data types, social media data
are multi-model in nature, including content such as images, audio,
videos, discussion topics, tags, annotations, hyperlinks, profiles,
timestamps, click-throughs, etc. How to make meanings out of these data
determines if intelligent applications can be devised.
The omnipresence of Internet makes social networks popular and easily
accessible. Will social networks in turn affect the future network architecture?
With the advancement of handheld mobile devices, social networks on
the move are becoming common. Will mobile and pervasive social networks
be any different?
Then there are trust, security, and privacy issues. As you can see,
the list of related problems can go on and on and on. In this talk,
we will identify some key issues in social network research and present
some applications of social networks.
|
About
Prof. Ruay-Shiung Chang |
Ruay-Shiung
Chang received his B.S.E.E. degree from National Taiwan University in
1980 and his Ph.D. degree in Computer Science from National Tsing Hua
University in 1988. He is now a professor in the Department of Computer
Science and Information Engineering, National Dong Hwa University. His
research interests include Internet, wireless networks, RFID and grid
computing. He has published more than 70 peer-reviewed journal papers
and numerous international conference papers. He is an editor for International
Journal of Internet Protocol Technology, Journal of Internet Technology,
and Journal of Convergence Information Technology. Dr. Chang is a member
of ACM, a senior member of IEEE, and a founding member of Taiwan Institute
of Information and Computing Machinery. Dr. Chang also served on the advisory
council for the Public Interest Registry (www.pir.org)
from 2004/5 to 2007/4.
|

|
..,
..
|
.. |
..
|
About
.. |
.. |

|
..,
..
|
.. |
..
|
About
.. |
.. |

|
..,
..
|
.. |
..
|
About
.. |
.. |

|
..,
..
|
.. |
..
|
About
.. |
.. |
|