Conference tutorials
All tutorials are free to registered
conference attendees of all conferences
held at WOLDCOMP'07. Those who are
interested in attending one or more of
the tutorials are to sign up on site at
the conference registration desk in Las
Vegas.
DMIN'07 Tutorials:
Data Mining in Time Series
and Multimedia Databases
Dr.
Eamonn Keogh
Associate Professor
Computer Science & Engineering Department
University of California - Riverside, USA
Date/Time: Wednesday, June 27,
2007 / 6:00pm - 9:00 pm
Location: Ballroom 1
A CD-ROM with tutorial slides,
datasets and materials for teaching data mining will be provided in the
tutorial session.
Abstract: Time series and
multimedia data are ubiquitous; large volumes of such data are routinely
created in scientific, industrial, entertainment, medical and biological
domains. Examples include gene expression data, electrocardiograms,
electroencephalograms, gait analysis, stock market quotes, space
telemetry, microarrays, CAT Scans etc. Because such data is
intrinsically real valued, most of the work on data mining of text has
little utility for such datasets.
A decade ago, a seminal paper by
Faloutsos, Ranganathan, Manolopoulos appeared in SIGMOD. The paper, Fast
Subsequence Matching in Time-Series Databases, has spawned at least a
thousand references and extensions in the database/ data mining and
information retrieval communities. This tutorial will summarize the
decade of progress in multimedia/time series information retrieval since
this influential paper appeared.
Intended audience:
Data mining (and Information
Retrieval/Database) researchers. Both researchers in general and
those working on specific time series/multimedia database problems will
find the tutorial informative. The tutorial ends with a discussion of
the top ten problems to work on in the area, graduate students looking
for an interesting problem in a hot area will be well served.
Data mining educators (and Information Retrieval/Database).
Many professors who teach data mining/information
retrieval/databases/machine learning courses use his slides. Such
individuals will received his comprehensive (and modifiable) slides and
observe his presentation of them. They will be able to base 10 to 20
hours of graduate instruction on the tutorial.
Data mining (and Information Retrieval/Database) application
developers. They will learn the latest techniques/representations
for indexing and mining time series/ multimedia data and examples of how
the techniques fit into real-life applications.
Biography of the presenter: Dr.
Keoghs research interests are in Data Mining, Machine Learning and
Information Retrieval. He has published more than 80 papers in these
areas.
Several of his papers have won best
paper
awards. In addition he has won several teaching awards. He is the
recipient of a 5-year NSF Career Award for Efficient Discovery of
Previously Unknown Patterns and Relationships in Massive Time Series
Databases and a grant from Aerospace Corp to develop a time series
visualization tool for monitoring space launch telemetry.
Dr Keogh has given well received tutorials on time series, machine
learning and data mining all over the world, and his papers have been
referenced well over a 2,000 times.
Please see
www.cs.ucr.edu/~eamonn/tutorials.html for addition information about
his tutorials.
"Awesome tutorial!! It's just
wonderful... playful AND deep! I couldn't stop looking at it, even
though I've got other things to do....but it was a well spent hour!"
(Ben Shneiderman, Founding Director of the Human-Computer Interaction
Laboratory, University of Maryland at College Park.)
Introduction to Uncertainty and Fuzzy Logic with Data
Mining Applications
Ashu M. G. Solo
Principal/R&D Engineer,
Maverick Technologies America Inc.
Wilmington, Delaware, USA
Date/Time: Monday, June 25, 2007 /
5:20pm - 6:00pm
Location: Ballroom 1
For material (slides etc.) please
contact Ashu M. G. Solo via email
amgsolo [ a t ] mavericktechnologies [ d o t ] us
Abstract:
WHY DO
WE NEED FUZZY LOGIC?
Recent technological advances have made it possible to develop computers
that are extremely fast and efficient for numerical computations.
However, these computers lack the abilities of humans and animals in
processing cognitive information acquired by natural sensors. For
example, the human brain routinely performs tasks like recognizing a
face in an unfamiliar crowd in 100-200 ms whereas a computer can take
days to accomplish a task of lesser complexity. The use of fuzzy logic
can emulate the desirable computing aspects found in humans and
animals. Engineers and scientists have had many remarkable
accomplishments such as putting people on the moon and returning them
safely to Earth, sending spacecraft to the far reaches of the solar
system, sending rovers to explore the surface of Mars, exploring the
oceans depths, designing computers that can perform billions of
computations per second, developing the nuclear bomb, mapping the human
genome, and constructing a scanning tunneling microscope that can move
individual atoms. But alongside many outstanding achievements using
unintelligent systems, there have been many abysmal failures that
include modeling the behavior of economic, political, social, physical,
and biological systems. Engineers have been unable to develop
technology that can decipher sloppy handwriting, recognize oral speech
as well as a human can, translate between languages as well as a human
interpreter, drive a car in heavy traffic as well as a human can, walk
with the agility of a human or animal, replace the combat infantry
soldier, determine the veracity of a statement by a human subject with
an acceptable degree of accuracy, replace judges and juries, summarize a
complicated document, and explain poetry or song lyrics. These
remaining challenges and many more can benefit from fuzzy logic.
WHAT IS
FUZZY LOGIC?
Certainty and precision have much too often become an absolute standard
in design, decision making, and control problems. The excess of
precision and certainty in engineering and scientific research and
development is often providing unrealizable solutions. Fuzzy logic,
based on the notion of relative graded membership, can deal with
information arising from computational perception and cognition that is
uncertain, imprecise, vague, partially true, or without sharp
boundaries. Fuzzy logic allows for the inclusion of vague human
assessments in computing problems. Also, it provides an effective means
for conflict resolution of multiple criteria and better assessment of
options. New computing methods based on fuzzy logic can lead to greater
adaptability, tractability, robustness, and a lower cost solution in the
development of intelligent systems for decision making, identification,
recognition, optimization, and control.
WHAT
ARE SOME APPLICATIONS OF FUZZY LOGIC?
Fuzzy logic has been used in numerous applications such as data mining,
facial pattern recognition, washing machines, vacuum cleaners, antiskid
braking systems, transmission systems, control of subway systems and
unmanned helicopters, intelligent communication networks,
knowledge-based systems for multiobjective optimization of power
systems, weather forecasting systems, models for new product pricing or
project risk assessment, medical diagnosis and treatment plans, and
stock trading.
Objective:
The objective of this tutorial is to provide a clear and rapid
introduction to key aspects of fuzzy logic including uncertainty, fuzzy
sets, linguistic variables, fuzzy rule bases, computational theory of
perceptions, computing with words, and fuzzy math. This tutorial seeks
to introduce fuzzy logic concepts mainly through examples of
applications in data mining and linguistic evaluations.
Intended audience:
This
tutorial is for anybody who wishes to learn the theory and applications
of fuzzy logic, and will be extremely useful for many people involved in
research and development including computer scientists, engineers
(computer, electrical, mechanical, civil, chemical, aerospace,
agricultural, biomedical, environmental, geological, industrial,
mechatronics), mathematicians, social scientists (economics, management,
political science, psychology), natural scientists (biology, chemistry,
earth science, physics), business analysts, public policy analysts,
jurists, medical researchers, etc.
Biography of the presenter:
Ashu
M. G. Solo is an electrical and computer engineer, mathematician,
writer, and entrepreneur. His primary research interests are in new
branches of math, intelligent systems, public policy, and the
application of intelligent systems in control systems, computer
architecture, power systems, optimization, pattern recognition, decision
making, and public policy. Solo has about 50 publications in these and
other fields. He co-developed some of the best published methods for
maintaining power flow in and multiobjective optimization of radial
power distribution system operations. Solo has served on 52
international program committees for 50 research conferences and 2
research multiconferences. He is the principal of Maverick Technologies
America Inc. Solo previously served honorably as an infantry officer
and platoon commander understudy in the Cdn. Army Reserve.
A complete &
current list of WORLDCOMP Tutorials can be found
here.
|
