Big Data Analytics for Machine Learning and
Cognition and Practical tools for analysing ECG signals in Biomedical Data
By
Tariq S Durrani
University of Strathclyde Glasgow
Scotland, UK
ABSTRACT
At CSPS-15
I had made a presentation on Big Data- Instrumentation and Signal Processing-
where I covered an introduction to Big Data, its properties, and likely
illustrations, as well as an indication of some of the tools available to
analyse large scale signal processing data.
This
presentation will address two complementary aspects of Big Data analytics -
issues related to machine learning, cognition techniques for Big Data handling;
and will also pursue practical aspects of software environments such as Hadoop
for specific applications.
Initial
discussion will explore machine learning and cognition concepts and present
four propositions - Recognition engines, data mining, neural networks, support
vector machines for data separation.
This will
be followed by presentation of issues related to analysing practical data and
the effect of the Hadoop environment for handling real data representing ECG
signals, the objective of the latter analysis is related to detecting
significant characteristics of ECG recordings to determine any abnormalities in
the heart beats of the patients. The ECG signals are taken from the well-known
public database, namely MIT-BIH Arrhythmia Database, to assess the proposed
subject identification processes.
BIOGRAPHY
Professor Tariq S Durrani received his MSc and PhD
degrees in 1967 and 1970 respectively, from the University of Southampton,
UK. After postdoctoral research at
Southampton, he joined the University of Strathclyde, Glasgow, as a Lecturer in
1976, and was appointed Professor of Signal Processing in 1982. Currently he is a Research
Professor in the Department.
For the past twenty-five years, he has worked on
and supervised some 60 projects sponsored by the UK Research Councils,
government and industry, the US Navy, and the EU, amongst others. He has supervised over 40 PhD
students, and is the author/co-author of more than 350 papers and six books.
His research interests are in the areas of Communications Signal/ Image
Processing, Technology Management and Higher Education Management.
He has held visiting appointments at Princeton,
University of Southern California, Stirling University and UESTC, Chengdu.
He is active in professional circles. He was the
2006-2007 President of the IEEE Engineering Management Society, and was a Past
President of the IEEE Signal Processing Society. From 2010-2011 he was IEEE
Director and (global) Vice President Educational Activities for the IEEE.
He is a Fellow of the Royal Society of Edinburgh,
the Royal Academy of Engineering, the IEEE, the IET and The Word Academy of
Sciences. He was awarded the OBE in December 2002 for services to higher
education and electronics research.
Keynote II:
Uncertainty Theory: A Branch of Mathematics for
Modeling Belief Degrees
By
Department of Mathematical Sciences
Tsinghua University
Beijing 100084, China
http://orsc.edu.cn/liu
ABSTRACT
When no
samples are available to estimate a probability distribution, we have to invite
some domain experts to evaluate the belief degree that each event will occur.
Perhaps some people think that the belief degree is subjective probability or
fuzzy concept. However, it is usually inappropriate because both probability
theory and fuzzy set theory may lead to counterintuitive results in this case.
In order to rationally deal with belief degrees, uncertainty theory was founded
in 2007 and subsequently studied by many researchers. Nowadays, uncertainty
theory has become a branch of mathematics for modeling belief degrees.
This talk
will introduce some fundamental concepts of uncertainty theory and discuss why
uncertainty theory is useful. This presentation is based on the speaker’s book
Uncertainty Theory published by Springer-Verlag, Berlin (http://orsc.edu.cn/liu/ut.pdf).
BIOGRAPHY
Baoding Liu received his B.S. degree in 1986 from
Nankai University, and his M.S. degree in 1989 and Ph.D. degree in 1993 from
Chinese Academy of Sciences. He joined Tsinghua University as Associate
Professor in 1996, and was appointed Professor of Mathematics in 1998. Dr.
Liu's research led to the development of uncertainty theory that is a branch of
mathematics for modeling belief degrees. (http://orsc.edu.cn/liu)
Keynote III:
Capacity-Approaching Low-Density Parity-Check
Codes: Recent Developments and Applications
By
Shu Lin
Department of Electrical and Computer
Engineering
University of California, Davis,
Davis, California 95616, USA
ABSTRACT
Channel
coding is an important element in every communication or data storage system.
The objective of channel coding is to provide reliable information transmission
and storage. Over the last 6 decades, various types of codes and methods for
correcting transmission errors over a wide spectrum of communication and
storage channels have been constructed and devised.
The
ever-growing needs for cheaper, faster, and more reliable communication and
storage systems have forced many researchers to seek means to attain the
ultimate limits, known as the channel capacities, on reliable information
transmission and storage. Low-density parity-check (LDPC) codes are currently
the most promising coding technique to achieve (or close to) the Shannon limits
(or channel capacities) for a wide range of channels. Discovered by Gallager in
1962, these codes were rediscovered in the late 1990's. Ever since their
rediscovery, a great deal of research effort has been expended in design,
construction, encoding, decoding algorithms and complexity, structure,
performance analysis, generalizations and applications of these remarkable
codes.
Many LDPC
codes have been adopted as the standard codes for various current and next
generations of communication systems, such as wireless, optical, satellite,
space, digital video broadcast (DVB), multi-media broadcast (MMB), 400G
Ethernet, NASA's LANDSAT, IRIS, TDRSS and other space missions. Applications to
high-density data storage systems, such as flash memories, are now being
seriously considered. In fact, they are appearing in some recent data storage
products. This rapid dominance of LDPC codes in applications is due to their
capacity-approaching performance which can be achieved with practically
implementable iterative decoding algorithms. However, there are still many
things unknown about these codes. Further study is needed. The most urgent need
are methods to design and construct efficient decodable codes that can achieve very
low error rates for very high speed communications and very high density data
storage.
This
presentation gives an overview of LDPC codes and their recent developments,
applications and future research directions.
BIOGRAPHY
Professor Shu Lin received the B.S.E.E. degree from
the National Taiwan University, Taipei, Taiwan, Republic of China, in 1959, and
the M.S. and Ph.D. degrees in electrical engineering from Rice University,
Houston, TX,in 1964 and 1965, respectively. In 1965, he joined the Faculty of
the University of Hawaii, Honolulu, as an Assistant Professor of Electrical
Engineering. He became an Associate Professor in 1969 and a Professor in 1973.
In 1986, he joined Texas A&M University, College Station, as the Irma
Runyon Chair Professor of Electrical Engineering. In 1987, he returned to the
University of Hawaii. From 1978 to 1979, he was a Visiting Scientist at the IBM
Thomas J.Watson Research Center, Yorktown Heights, NY, where he worked on error
control protocols for data communication systems. He spent the academic year of
1996-1997 as a Visiting Chair Professor at the Technical University of Munich,
Munich, Germany. Since 2000 to 2011, he was an Honorary Professor of Lancaster
University, United Kingdom.
He retired from University of Hawaii in 1999 and he
is currently an Adjunct Professor at University of California, Davis. He has
published at least 400 technical papers in prestigious refereed technical
journals and international conference proceedings. He is the author of the
book; An Introduction to Error-Correcting Codes (Englewood Cliff, NJ:
Prentice-Hall, 1970) (translated in Chinese). He also co-authored (with D. J.
Costello) the book(with William E.Ryan); Error Control Coding: Fundamentals and
Applications (Upper Saddle River, NJ: Prentice-Hall, 1st edition, 1982,
2ndedition, 2004) (translated into Chinese), the book (with T. Kasami,
T.Fujiwara, and M. Fossorier);Trellises and Trellis-Based Decoding Algorithms,
(Boston, MA: Kluwer Academic,1998), and the book; Channel Codes: Classical and
Modern (Cambridge University Press 2009) (under translation into Chinese). His
current research areas include algebraic coding theory, coded modulation, error
control systems, satellite communications and coding for storage systems. He
has served as the Principle Investigator on 43 research grants supported by US
National Science Foundation, NASA and private communications companies.
Dr. Lin is a Member of the IEEE (Institute of
Electrical and Electronic Engineering) Information Theory Society and the
Communication Society. He served as the Associate Editor for Algebraic Coding
Theory for the IEEE TRANSACTIONS ON INFORMATION THEORY from 1976 to 1978 (first
Chinese American ever served this position) , as the Program Co-Chairman of the
IEEE International Symposium of Information Theory held in Kobe, Japan, in
June1988, a Co-Chairman of the 1988 IEEE Information Theory Workshop held in
Beijing(the first IEEE Information Theory Conference ever held in China), and a
Co-Chairman of the 2007 IEEE Information Theory Workshop held in Chengdu,
China. He was the President of the IEEE Information Theory Society in 1991 (the
first and only Chinese American ever held this position).
Dr. Lin was elected to IEEE Fellow in 1980 and Life
Fellow in 2000. In 1996, he was a recipient of the Alexander von Humboldt
Research Prize for U.S. Senior Scientists and a recipient of the IEEE
Third-Millennium Medal, 2000. In 2007, he was a recipient of The Communications
Society Stephen O. Rice Prize in the Field of Communications Theory.