|
INDEXED BY
 
CONFERENCE TO BE HELD IN
Seoul, South Korea
SPONSORED BY
SUPPORTED BY
|
KEYNOTE
SPEAKERS OF ICBET 2023
Prof. Tae-Seong Kim
Kyung Hee University, Republic of Korea
Tae-Seong Kim received the B.S. degree in
Biomedical Engineering from the University of Southern
California (USC) in 1991, M.S. degrees in Biomedical and
Electrical Engineering from USC in 1993 and 1998
respectively, and Ph.D. in Biomedical Engineering from USC
in 1999. After his postdoctoral work in Cognitive Sciences
at the University of California at Irvine in 2000, he joined
the Alfred E. Mann Institute for Biomedical Engineering and
Dept. of Biomedical Engineering at USC as Research Scientist
and Research Assistant Professor. In 2004, he moved to Kyung
Hee University in Republic of Korea where he is currently
Professor in the Department of Biomedical Engineering. His
research interests have spanned various areas of biomedical
imaging, bioelectromagnetism, neural engineering, and
assistive lifecare technologies. Dr. Kim has been developing
novel methodologies in the fields of signal and image
processing, machine learning, pattern classification, and
artificial intelligence. Lately Dr. Kim has started novel
projects in the developments of smart robotics and machine
vision with deep learning methodologies. Dr. Kim has
published more than 380 papers and twelve international book
chapters. He holds ten international and domestic patents
and has received numerous best paper awards.
Speech Title: "Deep Learning for
Human Activity Recognition"
Abstract: Human activity recognition
(HAR) is a rapidly growing and challenging research field
that involves identifying and recognizing the specific
actions and movements of humans based on multi-modal sensor
data. It is an important study topic since it contributes to
many important applications such as intelligent lifecare and
surveillance systems, human computer/robot interfaces,
intelligent healthcare systems etc. Recently deep learning
methodologies are being utilized for HAR as they can learn
features directly from raw data and significantly improve
the performance of HAR. In this talk, I will present the
latest works on multi-modal sensor based HAR using various
deep learning models along with their applications in the
areas of smart homes, healthcare, and robotics.
Prof. Tatsuya Akutsu
Kyoto University, Japan
Tatsuya Akutsu received B.Eng. and M.Eng.
in Aeronautics and D.Eng. in Information Engineering from
University of Tokyo, in 1984, 1986 and 1989, respectively.
From 1989 to 1994, he was with Mechanical Engineering
Laboratory. From 1994 to 1996, he was an Associate Professor
in the Department of Computer Science at Gunma University.
From 1996 to 2001, he was an Associate Professor in Human
Genome Center, Institute of Medical Science, University of
Tokyo. Since 2001, he has been a Professor in Bioinformatics
Center, Institute for Chemical Research, Kyoto University.
He is a fellow of Information Processing Society of Japan
(IPSJ), and was an editor-in-chief of IPSJ Transactions on
Bioinformatics for 2006-2009. His research interests include
bioinformatics, complex networks, and dicrete algorithms.
Speech Title: "Graph Theoretic Approaches
to Analysis of Biological Networks"
Abstract: For deeper understanding of
biological systems, it is crucial to analyze biological
networks, which include gene regulatory networks,
protein-protein interaction networks, and metabolic
networks. To this end, we have been applying such graph
theoretic concepts as minimum dominating sets, feedback
vertex sets, and dense subgraphs. Furthermore, we have
extended these concepts to better extract useful information
from biological networks. We have been applying these
concepts to various biological problems, which include
inference of cancer-related genes, analysis of aging genes,
analysis of mouse brain neural networks, identification of
protein hot spots, and comparison of metabolic networks in
cancer and normal cells. In this talk, we briefly introduce
these graph theoretic concepts and explain their extensions
and applications.
INVITED
SPEAKERS OF ICBET 2023
Assoc. Prof. Md. Altaf-Ul-Amin
Nara Institute of Science and Technology, Japan
Md. Altaf-Ul-Amin received B.Sc. degree
in Electrical and Electronic Engineering from Bangladesh
University of Engineering and Technology (BUET), Dhaka,
M.Sc. degree in Electrical, Electronic and Systems
Engineering from Universiti Kebangsaan Malaysia (UKM) and
PhD degree from Nara Institute of Science and Technology
(NAIST), Japan. He received the best student paper award in
the IEEE 10th Asian Test Symposium. Also, he received two
other best paper awards as a co-author of journal articles.
He previously worked in several universities in Bangladesh,
Malaysia and Japan. Currently he is working as an associate
professor in Computational Systems Biology Lab of NAIST. He
is conducting research on Network Biology, Systems Biology,
Cheminformatics and Biological Databases. He published
around 90 peer reviewed papers in international journals and
conference proceedings. Current google scholar citation
index of his publications is more than 7500.
Speech Title: "Learning Vector
Quantized Representation for Cancer Subtypes Identification
Incorporating Omics Data"
Abstract: Defining and separating cancer
subtypes is essential for facilitating personalized therapy
modality and prognosis of patients. The definition of
subtypes has been constantly recalibrated due to our
deepened understanding. During this recalibration,
researchers often rely on the clustering of cancer omics
data to provide an intuitive visual reference that could
reveal the intrinsic characteristics of subtypes. However,
while existing studies have shown promising results, they
suffer from issues associated with omics data: sample
scarcity and high dimensionality. As such, existing methods
often impose unrealistic assumptions to extract useful
features from the data while avoiding overfitting spurious
correlations. In this talk, we discuss the effectiveness of
a recent strong generative model, Vector Quantized
Variational AutoEncoder (VQ-VAE), to tackle the data issues
and extract informative latent features that are crucial to
the quality of subsequent clustering by retaining only
information relevant to reconstructing the input. VQ-VAE
does not impose strict assumptions; hence, its latent
features are better representations of the input, capable of
yielding superior clustering performance with any main
stream clustering method.
|
