iconip - university of rhode island
TRANSCRIPT
ICONIP 2012
Table of Content
Welcome Message------------------------------------------------------------------------------------------ 1
ICONIP 2012 Organization-------------------------------------------------------------------------------- 2
Sponsors and Organizer------------------------------------------------------------------------------------ 5
Keynote Speeches----------------------------------------------------------------------------------------- 9
Plenary Speeches------------------------------------------------------------------------------------------ 12
Invited Speeches------------------------------------------------------------------------------------------- 19
Panelists----------------------------------------------------------------------------------------------------- 27
Technical Program----------------------------------------------------------------------------------------- 30
Conference Venue Floor Map---------------------------------------------------------------------------- 59
City Center Area Map------------------------------------------------------------------------------------- 59
Travel Sites in Qatar--------------------------------------------------------------------------------------- 60
ICONIP 2012
Welcome to ICONIP 2012
On behalf of the Organizing Committee and Program Committee, it is our pleasure to welcome
you to 19th International Conference on Neural Information Processing (ICONIP 2012). ICONIP
is the annual conference of the Asia Pacific Neural Network Assembly (APNNA) and this series
of conferences has been held annually since 1994, becoming the premier international
conferences in the areas of neural networks.
ICONIP 2012 will be held in Doha, Qatar. It will be the first Arab country to host ICONIP
meeting since its inception in 1994. We strongly believe that this conference will advance Qatar's
culture of research and development.
Small in size, Qatar is enormous in value. It has achieved within decades what other countries
have taken centuries to accomplish. It highly values education, especial higher education. It aims
to become one of the world's strongest knowledge societies. Its citizens embrace the future with
unswerving optimism and enviable potential. Hospitable, generous, and kind, Qataris make guests
feel at home.
Scholars from more than 60 countries submitted about 700 papers for ICONIP 2012. Based on
rigorous peer reviews process, about 400 high-quality papers were selected for publication in the
prestigious series of Lecture Notes in Computer Science. In addition to the contributed papers, the
ICONIP 2012 technical program includes about 30 keynote, plenary and invited speeches and two
panels.
Our conference would not have been successful without the generous patronage of our sponsors.
We are most grateful to our Platinum Sponsor: United Development Company PSC (UDC), Gold
Sponsors: Qatar Petrochemical Company, ExxonMobil and Qatar Petroleum and organizer: Texas
A&M University at Qatar. We also would like to express our sincere thanks to Asia Pacific
Neural Network Assembly, IEEE Computational Intelligence Society, International Neural
Network Society, European Neural Network Society and Japanese Neural Network Society,
Springer for technical sponsorship.
Thank you to the members of the Advisory Committee, the APNNA Governing Board and Past
Presidents for their guidance, Special Sessions Chairs and IWDMC 2012 organizers, Publication
Committee and Publicity Chairs, for all their great efforts. Special mention should be made of the
members of the Program Committee and all reviewers for their professional review of the papers.
We would like to express our thanks to Wenwen Shen for her tremendous efforts in maintaining
the conference website, the publication team including Gang Bao, Huanqiong Chen, Ling Chen,
Dai Yu, Xing He, Junjian Huang, Chaobei Li, Huaqing Li, Cheng Lian, Jiangtao Qi, Wenwen
Shen, Huiwei Wang, Xin Wang, Shiping Wen, Ailong Wu, Jian Xiao, Wei Yao and Wei Zhang
for spending much time to check the accepted papers, and the logistics team including Brady
Creel, Hala El-Dakak, Alia Fakhr, Xing He, Rob Hinton, Huaqing Li, Geeta Megchiani, Carol
Nader, Susan Rozario, Huiwei Wang and Shiping Wen.
We wish you a fruitful conference and a wonderful time in the State of Qatar!
Mark Weichold, Honorary Conference Chair
Tingwen Huang, General Chair
Andrew Leung, Chuandong Li and Zhigang Zeng, Program Chairs
Rudolph Lorentz and Khalid Qaraqe, Organizing Chairs
1
ICONIP 2012
Honorary Conference Chair Mark Weichold, Texas A&M University at Qatar, Qatar
General Chair Tingwen Huang, Texas A&M University at Qatar, Qatar
Advisory Committee
Honorary Chair
Shun-ichi Amari, RIKEN Brain Science Institute, Japan
Members
Majid Ahmadi, University of Windsor, Canada
Sabri Arik, Istanbul University, Turkey
Salim Bouzerdoum, University of Wollongong, Australia
Jinde Cao, Southeast University, China
Jonathan H. Chan, King Mongkut's University of Technology, Thailand
Guanrong Chen, City University of Hong Kong, Hong Kong
Tianping Chen, Fudan University, China
Kenji Doya, Okinawa Institute of Science and Technology, Japan
Wlodzislaw Duch, Nicolaus Copernicus University, Poland
Ford Lumban Gaol, Bina Nusantara University, Indonesia
Tom Gedeon, Australian National University, Australia
Stephen Grossberg, Boston University, USA
Haibo He, University of Rhode Island, USA
Akira Hirose, University of Tokyo, Japan
Nikola Kasabov, Auckland University of Technology, New Zealand
Irwin King, The Chinese University of Hong Kong, Hong Kong
James Kwow, Hong Kong University of Science and Technology, Hong Kong
Soo-Young Lee, Advanced Institute of Science and Technology, Korea
Xiaofeng Liao, Chongqing University, China
Chee Peng Lim, Universiti Sains Malaysia, Malaysia
Derong Liu, University of Illinois at Chicago, USA
Bao-Liang Lu, Shanghai Jiao Tong University, China
John MacIntyre, University of Sunderland, England
Erkki Oja, Helsinki University of Technology, Finland
Nikhil R. Pal, Indian Statistical Institute, India
Marios M. Polycarpou, University of Cyprus, Cyprus
Leszek Rutkowski, Czestochowa University of Technology, Poland
Noboru Ohnishi, Nagoya University, Japan
Ron Sun, Rensselaer Polytechnic Institute, USA
Ko Sakai, University of Tsukuba, Japan
Shiro Usui, RIKEN, Japan
Xin Yao,University of Birmingham, UK
DeLiang Wang, Ohio State University, USA
Jun Wang, Chinese University of Hong Kong, Hong Kong
Li-Po Wang, Nanyang Technological University, Singapore
Rubin Wang, East China University of Science and Technology, China
Zidong Wang, Brunel University, UK
Huaguang Zhang, Northeastern University, China
2
ICONIP 2012
Organizing Committee
Chairs
Rudolph Lorentz, Texas A&M University at Qatar, Qatar
Khalid Qaraqe, Texas A&M University at Qatar, Qatar
Members
Hassan Bazzi, Texas A&M University at Qatar, Qatar
Hala El-Dakak, Texas A&M University at Qatar, Qatar
Mohamed Elgindi, Texas A&M University at Qatar, Qatar
Jihad Mohamad Jaam, Qatar University, Qatar
Samia Jones, Texas A&M University at Qatar, Qatar
Uvais Ahmed Qidwai, Qatar University, Qatar
Paul Schumacher, Texas A&M University at Qatar, Qatar
Program Chairs
Andrew Leung, City University of Hong Kong, Hong Kong
Chuandong Li, Chongqing University, China
Zhigang Zeng, Huazhong University of Science & Technology, China
Program Committee Members
Sabri Arik
Emili Balaguer Ballester
Gang Bao
Hamid Bouchachia
Matthew Casey
Li Chai
Jonathan Chan
Mou Chen
Yangquan Chen
Mingcong Deng
Ji-Xiang Du
El-Sayed El-Alfy
Osman Elgawi
Peter Erdi
Wai-Keung Fung
Yang Gao
Erol Gelenbe
Nistor Grozavu
Ping Guo
Fei Han
Bin He
Hanlin He
Shan He
Jinglu Hu
Junhao Hu
He Huang
Kaizhu Hunag
Jihad Mohamad Jaam
Minghui Jiang
John Keane
Sungshin Kim
Irwin King
Sid Kulkarni
H. K. Kwan
James Kwok
W. K. Lai
James Lam
Soo-Young Lee
Chi Sing Leung
Bin Li
Bo Li
Hai Li
Ruihai Li
Tieshan Li
Xiaodi Li
Yangmin Li
Lizhi Liao
Chee-Peng Lim
Honghai Liu
Jing Liu
Ju Liu
C. K. Loo
Luis Martínez López
Wenlian Lu
Yanhong Luo
Jinwen Ma
3
ICONIP 2012
Mufti Mahmud
Jacek Mańdziuk
Muhammad Naufal Bin Mansor
Yan Meng
Xiaobing Nie
Sid-Ali Ouadfeul
Seiichi Ozawa
Shaoning Paul Pang
Anhhuy Phan
Uvais Qidwai
Ruiyang Qiu
Hendrik Richter
Mehdi Roopaei
Thomas A. Runkler
Miguel Angel Fernández Sanjuán
Ruhul Sarker
Naoyuki Sato
Qiankun Song
Jochen Steil
John Sum
Bing-Yu Sun
Norikazu Takahashi
Kay Chen Tan
Ying Tan
Hongying Tang
Huajin Tang
Jinshan Tang
Ke Tang
Maolin Tang
Peter Tino
Haifeng Tou
Dat Tran
Michel Verleysen
Dan Wang
Dianhui Wang
Ning Wang
Xin Wang
Yong Wang
Zhanshan Wang
Ailong Wu
Bryant Wysocki
Bingji Xu
Shengxiang Yang
Yingjie Yang
Wen Yu
Wenwu Yu
Xiao-Jun Zeng
Xiaoqin Zeng
Jie Zhang
Junping Zhang
Wei Zhang
Zhong Zhang
Dongbin Zhao
Hongyong Zhao
Huaqing Zhen
Special Sessions Chairs
Zijian Diao, Ohio University, USA
Hassab Elgawi Osman, The University of Tokyo, Japan
Paul Pang, Unitec Institute of Technology, New Zealand
Publicity Chairs
Mehdi Roopaei, Shiraz University, Iran
Enchin Serpedin, Texas A&M University, USA
Maolin Tang, Queensland University of Technology, Australia
4
ICONIP 2012
Platinum Sponsor
United Development Company PSC (UDC)
United Development Company PSC (UDC) is one of Qatar’s leading private sector
shareholding companies. UDC’s mission is to identify and invest in long-term projects
contributing to Qatar’s growth and providing good shareholder value. The company was
established in 1999 and listed on the Qatar Exchange in June 2003. It has an authorized share
capital of QR 1.609 billion, total assets of QR 11.008 billion as of 31 March 2011 and a market
capitalization.
UDC’s target areas of interest include: infrastructure, energy-intensive industries, hydrocarbon
downstream manufacturing, real estate, maritime and environment-related businesses, urban
development and utilities, hospitality, retail and fashion, information technology, media and
communications, insurance and other services.
From day one, the Company’s mission has been to become a cornerstone in the developments
of Qatar and the region, creating lasting value and maximizing returns for partners and
shareholders. Through a combination of project activities and commercial enterprise, UDC has
developed into the first-choice private sector and joint venture partner for international
investors in Qatar, and has successfully established several new companies and investment
vehicles across the region.
Due in great measure to the unique conditions for sustainable economic activity in Qatar
created by the country’s leadership under His Highness the Emir, Sheikh Hamad Bin Khalifa
Al Thani, UDC has established a stable business platform generating wealth and returning
value through investment and joint venture activities.
Since 1999, UDC has moved from researching projects into development, production and
operations. Project research has led to the creation of companies, considered to be among the
most successful in their related fields. The Company prides itself in its ability to create quality
investment opportunities, both at home and overseas.
UDC’s founders and current Board Members are among Qatar’s most successful investors and
developers. Qatari shareholders own 75 percent of the Company’s total shares while the
remaining 25 percent are held by international investors.
The Company continues its quest for excellence and progress by identifying and adding new
investments and partnerships to its diversified portfolio of excellent businesses.
5
ICONIP 2012
Gold Sponsors
Qatar Petrochemical Co. Ltd.
Qatar Petrochemical Company (QAPCO) was established in the year 1974 as a multi-national
joint venture between Industries Qatar (80%) and French Total Petrochemical Company (20%)
to be a leading Middle East company in the field of petrochemicals producing high quality
ethylene and low density polyethylene (LDPE). The company is made up of an ethylene plant,
producing 720000 MT/Y, two LDPE plants (1 & 2) with a production capacity of 400000
MT/Y, and a sulfur plant producing 70000 MT/Y. Commercial production started in 1982. A
new polyethylene plant (3), once fully operational, is expected to produce 300000 MT/Y, thus
raising the overall production capacity to 700000 MT/Y of low density polyethylene.
The new ethylene plant increased ethylene production to 800000 MT/Y, thus bringing QAPCO
back to the forefront of ethylene production and exportation. The ethylene produced will
provide the feedstock needs of Qatar Vinyl Company (QVC) and the new polyethylene plant
(3). The extra ethylene will be exported to international markets, including India, South East
Asia, and Western Europe.
Qatar Petrochemical Company (QAPCO) is one of the leading producers of ethylene and low
density polyethylene (LDPE) in the Middle East region. LDPE is being marketed under the
“LOTRENE” trade name.
ExxonMobil
ExxonMobil is the world’s largest publicly traded international oil and gas company. We hold
an industry-leading inventory of global oil and gas resources. We are the world’s largest refiner
and marketer of petroleum products, and our chemical company ranks among the world’s
largest. We are also a technology company, applying science and innovation to find better,
safer and cleaner ways to deliver the energy the world needs.
Over the last 125 years ExxonMobil has evolved from a regional marketer of kerosene in the
U.S. to the largest publicly traded petroleum and petrochemical enterprise in the world. Today
we operate in most of the world's countries and are best known by our familiar brand names:
Exxon, Esso and Mobil. We make the products that drive modern transportation, power cities,
lubricate industry and provide petrochemical building blocks that lead to thousands of
consumer goods. Learn more by using the slider or the arrows below to browse our history
6
ICONIP 2012
over time.
ExxonMobil has a long history of leadership in the petroleum and petrochemical industries.
The discipline and commitment we apply in the execution of our business strategies have led to
sustainable competitive advantages. Learn more about our senior leadership.
ExxonMobil uses innovation and technology to deliver energy and petrochemical products to
meet the world’s growing demand. Our people, technical expertise, financial strength, and
global reach provide a competitive advantage and ensure broad exposure to high-quality
opportunities—from conventional exploration to opportunities that require close integration
across our businesses. Our extensive research programs support operations, enable continuous
improvement in each of our business lines, and explore new and emerging energy sources and
technologies. The Corporation comprises 10 separate companies, making up the Upstream,
Downstream, and Chemical businesses.
Qatar Petroleum
Committed to Excellence
The operations and activities of QP are conducted at various onshore locations, including
Doha, Dukhan and the Mesaieed and Ras Laffan Industrial Cities, as well as in offshore areas,
including Halul Island, offshore production stations, drilling platforms and the North Field.
Thriving on a spirit of enterprise, each of our joint ventures is underpinned by transparency,
innovation and determination to achieve unparalleled standards of both quality and service.
At Qatar Petroleum, we are committed to one thing above all: Excellence.
Qatar Petroleum (QP), formerly Qatar General Petroleum Corporation, is a state-owned
corporation established by Emiri Decree No. 10 in 1974. It is responsible for all oil and gas
production and processing in Qatar.
The principal activities of QP and its subsidiaries and joint ventures are the exploration,
production and sale of crude oil, natural gas and gas liquids and refined products, liquefied
natural gas (LNG), production and sale of petrochemicals, fuel additives, fertilizers, steel,
aluminum, underwriting insurance and other services.
QP’s strategy of conducting hydrocarbon exploration and development are through Exploration
and Production Sharing Agreements (EPSA) and Development and Production Sharing
Agreements (DPSA) concluded with major international oil and gas companies.
7
ICONIP 2012
Organizer
Texas A&M University at Qatar
Texas A&M University, recognized as having one of the premier engineering programs in the
world, has offered undergraduate degrees in chemical, electrical, mechanical and petroleum
engineering at Qatar Foundation's Education City campus since 2003. One hundred fifty one
engineers have graduated from Texas A&M at Qatar since 2007.
In addition to engineering courses, Texas A&M at Qatar provides classes in science,
mathematics, liberal arts and the humanities. All four of the engineering programs offered at
Texas A&M at Qatar are accredited by ABET. The curricula offered at Texas A&M at Qatar
are materially identical to those offered at the main campus in College Station, Texas, and
courses are taught in English in a co-educational setting. The reputation for excellence is the
same, as is the commitment to equip engineers to lead the next generation of engineering
advancement. Faculty from around the world are attracted to Texas A&M at Qatar to provide
this educational experience and to participate in research activities now valued at $70 million,
and that address issues important to the State of Qatar.
Technical Sponsors
Asia Pacific Neural Network Assembly
IEEE Computaional Intelligence Society
The International Neural Network Society
The European Neural Network Society
Japanese Neural Network Society
Springer
8
ICONIP 2012
Keynote Speeches
Shunichi Amari
RIKEN Brain Science Institute, Japan
Title: Brain, Stochastic World and Information Geometry
Abstract: The brain is a highly complex system, working surprisingly well. It uses spikes as
information carriers which show stochastic behaviors. We need to understand the secret why
information is processed accurately by using stochastically fluctuating units. Information would
be represented in the form of related probability distributions in the brain, where Bayesian
calculations take place. These ideas lead us to the stochastic world of computation. Information geometry is a
mathematical theory emerged from intrinsic properties of manifolds of probability distributions. It provides useful
tools for studying the stochastic world. The present talk introduces information geometry and show how its
applications to neural spike analysis, dynamical behaviors of learning machines, sparse signal processing and others.
Biography: Dr. Amari earned his Ph.D. from the University of Tokyo. After that, he worked as an Associate
Professor at Kyushu University and the University of Tokyo, and then a Full professor at the University of Tokyo,
and is now Professor-Emeritus. He served as Director of RIKEN Brain Science Institute for five years, and is now
its senior advisor. He has been engaged in research in wide areas of mathematical engineering, in particular,
mathematical foundations of neural networks, including statistical neurodynamics, dynamical theory of neural fields,
associative memory, self-organization, and general learning theory. Another main subject of his research is
information geometry initiated by himself, which provides a new powerful method to information sciences and
neural networks.
Dr. Amari served as President of Institute of Electronics, Information and Communication Engineers, Japan and
President of International Neural Networks Society. He received Emanuel A. Piore Award and Neural Networks
Pioneer Award from IEEE, the Japan Academy Award, Gabor Award from INNS, Caianiello Award, and C&C
award, among many others. He is a Fellow of IEEE.
Leon Chua
University of California at Berkeley, USA
Title: Memristor, Hodgkin Huxley, and Edge of Chaos
Abstract: This talk shows why brains are made of memristors. It will also resolve the numerous
anomalies of the classic Hodgkin-Huxley neuron and identify the non-linear dynamical
mechanisms of the action potentialto be the same as the heretofore unresolved mechanism
which gives rise to Turing's Morphological phenomena and Smales' Paradox, namely, a global
bifurcation from the edge of chaos.
Biography: Dr. Chua received his MS and PhD degrees from the Massachusetts Institute of Technology and the
University of Illinois at Champaign-Urbana, respectively. He has been a professor at the University of California,
Berkeley since 1971. In 2011, Prof. Chua was appointed a Distinguished Professor at the Technical University of
Munich. His research interests include cellular neural/nonlinear networks, nonlinear circuits and systems, nonlinear
dynamics, bifurcation and chaos. He has published more than 500 papers. He is the Honorary Founding Editor-in-
Chief of International Journal of Bifurcation and Chaos. Considered to be the “father of nonlinear circuit theory and
cellular neural networks”, he is also the inventor and namesake of “Chua's circuit” and was the first to conceive the
theories behind, and postulate the existence of, the solid-state memristor. Thirty-seven years after he predicted its
existence, a working solid-state memristor was created by a team led by R. Stanley Williams at Hewlett Packard.
He received many awards including the first recipient of the Gustav Kirchhoff Award, and the Guggenheim Fellow
award, IEEE Neural Networks Pioneer Award. He has been a Fellow of IEEE since 1974. He was awarded 7 patents
and 13 Honorary doctorates and was elected a foreign member of the Academia Europaea, and of the Hungarian
Academy of the Sciences.
9
ICONIP 2012
Robert Desimone
MIT, USA
Title: Prefrontal Control of Visual Attention
Abstract: The voluntary control of visual attention to behaviorally relevant stimuli is thought to
involve “top-down” feedback to visual processing areas. For spatially-directed attention, one key
source of top-down attention is the frontal eye fields (FEF). We have found that feedback to
visual cortex from FEF causes enhanced responses to stimuli at attended locations, and leads to
synchronized neural activity in the gamma frequency range between FEF and visual processing areas. Recent
evidence suggests that the pulvinar may also serve as an important relay of attentional feedback to visual cortex, and
it may also serve to desynchronize cortical activity in the alpha frequency range. The neural basis of feature, or
object attention has been much more difficult to understand. One possibility is that attention to objects with
particular features causes spatially directed attention to be directed to those objects, utilizing known pathways for
spatial attention. Another possibility is that attention to objects or features such as faces, colors, or shapes, depends
on feedback to visual cells that are selective for those features, biasing activity in favor of those stimuli. Such a
mechanism would be similar to what is thought to mediate visual recall memory. We have recently found evidence
for both types of mechanisms in prefrontal cortex. Neurophysiological studies show that when monkeys direct
attention to an object with a particular color or shape in the visual field, responses of cells in the FEF with receptive
fields containing that location become selectively potentiated. Feedback from FEF to visual cortex then serves to
highlight these salient locations. To help identify sources of direct object-related feedback to visual cortex, we have
tested humans in a task that requires attention to one of two spatially overlapping objects (faces and houses),
precluding the use of spatial atention. Neural activity was recording using magnetoencephalography (MEG) and
fMRI. In this task, we found that attention to faces of houses causes enhanced activity and synchrony infusiform
face area or the parahippocampal place area, respectively, and these areas synchronize their activity with the inferior
frontal gyrus, an area in prefrontal cortex with known object selectivity. Thus, attention to locations and objects
involves different feedback mechanisms in the prefrontal cortex.
Biography: Dr. Desimone studies the brain mechanisms that allow us to focus our attention on a specific task while
filtering out irrelevant distractions. Our brains are constantly bombarded with sensory information. The ability to
distinguish relevant information from irrelevant distractions is a critical skill, one that is impaired in many brain
disorders. By studying the visual system of humans and animals, Dr. Desimone has shown that when we attend to
something specific, neurons in certain brain regions fire in unison -- like a chorus rising above the noise -- allowing
the relevant information to be ‘heard’ more efficiently by other regions of the brain.
Dr. Desimone is director of the McGovern Institute and the Doris and Don Berkey Professor in the Department of
Brain and Cognitive Sciences. Prior to joining the McGovern Institute in 2004, he was director of the Intramural
Research Program at the National Institutes of Mental Health, the largest mental health research center in the world.
He is a member of the National Academy of Sciences and the American Academy of Arts and Sciences and a
recipient of numerous awards, including the Troland Prize of the National Academy of Sciences, and the Golden
Brain Award of the Minerva Foundation.
Stephen Grossberg
Boston University, USA
Title: Neural dynamics of invariant object learning, attention, recognition, and search
Abstract: Major progress in modeling how brains give rise to minds has disclosed new paradigms
whereby the brain computes: Complementary Computing clarifies the nature of brain specialization,
and Laminar Computing clarifies why all neocortical circuits exhibit a layered architecture. This
talk will summarize modeling results that illustrate these two paradigms, including how the brain
may learn to recognize objects from multiple viewpoints as a scene is freely scanned with eye movements. The
ARTSCAN model clarifies how multiple brain processes are coordinated to achieve this goal, including spatial attention,
object attention, category learning, figure-ground separation, and predictive remapping. These results clarify how our
eyes can scan an interesting object even before we know what it is, and how perceptual stability is achieved despite the
evanescent nature of visual cues during visual scanning. The talk will also summarize revolutionary general properties
10
ICONIP 2012
that are realized by Laminar Computing, as well as finer details of the interactions between laminar cortical and
thalamic circuits during category learning, such as the SMART model prediction of how fast gamma oscillations and
slower beta oscillations may be triggered in top-down attentive match vs. mismatch conditions, a prediction that has
supportive data from neurophysiological experiments in V1, hippocampus, and FEF; and how attentive vigilance may
be regulated by acetylcholine release via the nucleus basalis of Meynert.
Biography: Dr. Grossberg is Wang Professor of Cognitive and Neural Systems and Professor of Mathematics,
Psychology, and Biomedical Engineering at Boston University. He has published over 500 research articles, 17 books
or journal special issues, and has 7 patents. He founded and was first President of the International Neural Network
Society (INNS). He founded the Society's official journal, Neural Networks. Dr. Grossberg has also served as an editor
for 30 journals. He was general chairman of the IEEE First International Conference on Neural Networks and played a
key role in organizing the first annual meeting of INNS, whose fusion led to the International Joint Conference on
Neural Networks (IJCNN). He founded the Department of Cognitive and Neural Systems at Boston University, which
he built into a leading institution for advanced training in biological neural networks and neuromorphic technology. He
is the founder and Director of the Center for Adaptive Systems, which he built into one of the world's leading academic
research institutes in computational neuroscience and neural network technology. His year-long lecture series at MIT
Lincoln Laboratory on neural network technology motivated the laboratory to initiate the national DARPA Neural
Network Study in 1987. He organized and is founding Director of the NSF Center of Excellence for Learning in
Education, Science, and Technology.
Dr. Grossberg won the 1991 IEEE Neural Network Pioneer Award, the 1992 INNS Leadership Award, the 1992 Boston
Computer Society Thinking Technology Award, the 2000 Information Science Award of the Association for Intelligent
Machinery, the 2002 Charles River Laboratories prize of the Society for Behavioral Toxicology, and the 2003 INNS
Helmholtz Award. He is a 1991 member of the Memory Disorders Research Society, a 1994 Fellow of the American
Psychological Association, a 1996 member of the Society of Experimental Psychologists, a 2002 Fellow of the
American Psychological Society, a 2005 IEEE Fellow, a 2008 Inaugural Fellow of the American Educational Research
Association, and a 2012 INNS Fellow.
Michael I. Jordan
University of California, Berkeley
Title: Divide-and-Conquer and Statistical Inference for Big Data
Abstract: I present some recent work on statistical inference for Big Data. Divide-and-conquer is a
natural computational paradigm for approaching Big Data problems, particularly given recent
developments in distributed and parallel computing, but some interesting challenges arise when
applying divide-and-conquer algorithms to statistical inference problems. One interesting issue is
that of obtaining confidence intervals in massive datasets. The bootstrap principle suggests
resampling data to obtain fluctuations in the values of estimators, and thereby confidence intervals, but this is infeasible
with massive data. Subsampling the data yields fluctuations on the wrong scale, which have to be corrected to provide
calibrated statistical inferences. I present a new procedure, the “bag of little bootstraps”, which circumvents this
problem, inheriting the favorable theoretical properties of the bootstrap but also having a much more favorable
computational profile. Another issue that I discuss is the problem of large-scale matrix completion. Here divide-and-
conquer is a natural heuristic that works well in practice, but new theoretical problems arise when attempting to
characterize the statistical performance of divide-and-conquer algorithms. Here the theoretical support is provided by
concentration theorems for random matrices, and I present a new approach to this problem based on Stein's method.
Biography: Dr. Jordan is the Pehong Chen Distinguished Professor in the Department of Electrical Engineering and
Computer Science and the Department of Statistics at the University of California, Berkeley. His research in recent
years has focused on Bayesian nonparametric analysis, probabilistic graphical models, spectral methods, kernel
machines and applications to problems in statistical genetics, signal processing, computational biology, information
retrieval and natural language processing.
Dr. Jordan is a member of the National Academy of Sciences, a member of the National Academy of Engineering and a
member of the American Academy of Arts and Sciences. He is a Fellow of the American Association for the
Advancement of Science. He has been named a Neyman Lecturer and a Medallion Lecturer by the Institute of
Mathematical Statistics. He is a Fellow of the ACM, the IMS, the IEEE, the AAAI and the ASA.
11
ICONIP 2012
Plenary Speeches
Majid Ahmad
University of Windsor, Canada
Title: Human Face Recognition Under Illumination Variation
Abstract: Human Face Recognition has been used for advanced video surveillance, access control,
human computer interface, border crossing monitoring, criminal identification etc. for the last two
decades. There are many face recognition algorithms with outstanding recognition rates under
controlled conditions reported in the literature. However, there are still many challenges to overcome when images
are taken under varying illumination conditions, blur, occlusion, aging, low resolution images. In this talk a
comprehensive study of different feature extractors, classifiers and their effectiveness in human face recognition is
presented. Furthermore, a solution for human face recognition under varying illumination conditions is outlined.
Biography: Dr. Ahmadi received the BSc degree in electrical engineering from Sharif University (formerly known
as Arya Mehr University), Tehran, Iran, and the PhD degree in electrical engineering from Imperial College of
London University in 1971 and 1977 respectively. Dr. Majid Ahmadi has been with the Department of Electrical
and Computer Engineering at the University of Windsor 1980, currently a university Professor and Director of the
Research Center for Integrated Microsystems. His research interests include digital signal processing, machine
vision, pattern recognition, neural network architectures and VLSI implementation as well as computer arithmetic.
He has co-authored the book, Digital Filtering in 1-D and 2- Dimensions; Design and Applications (New York:
Plennum 1989) and has published more than 400 articles in the above areas.
Dr. Ahmadi is the regional editor for the journal of Circuits, Systems and Computers and the Associate Editor for
the Pattern Recognition journal. He was the IEEE-CAS representative on the Neural Network Council and the Chair
of the IEEE-CAS Neural Systems Application Technical Committee. He was recipient of an Honorable Mention
award from the editorial Board of the Pattern Recognition journal in 1992 and received the Distinctive Contributed
Paper award from Multiple-Valued Logic Conference Technical Committee and the IEEE Computer Society in 1999.
He is a Fellow of the IEEE (USA) and a Fellow of IET (UK).
Guanrong (Ron) Chen
City University of Hong Kong, Hong Kong
Title: Searching for Undirected Networks with Best Synchronizability
Abstract: The synchronizability of a connected undirected network is essentially determined by
the spectrum of its Laplacian matrix, which reflects most topological characteristics of the network
such as degree distribution, shortest-path length, betweenness centrality, among others. Recently, we found that
networks with best possible synchronizability are in some sense “homogenous” and “symmetric”, with several
common features such as an identical degree sequence, a longest girth, and a shortest path-sum. We have verified
this observation by degree-3 regular networks of small sizes, and conjectured this be true in general.
Biography: Dr. Chen is a Chair Professor and the Founding Director of the Centre for Chaos and Complex
Networks at the City University of Hong Kong. He was elected IEEE Fellow in 1996, named Highly Cited
Researcher in Engineering by Thompson Reuters in 2009, and conferred Honorary Doctorate by Saint Petersburg
State University, Russia in 2011. He received numerous prestigious honors and awards, including the 2011 Euler
Gold Medal honored by the Euler Foundation, Saint Petersburg, Russia, the 2010 Ho-Leung-Ho-Lee Science and
Technology Progress Award, China and the 2008 State Natural Science Award of ChinaAwards in the past.
Moreover, he is Honorary Professor at different ranks of twenty some universities worldwide. Currently, he is the
Editor-in-Chief of the IEEE Circuits and Systems Magazine and of the International Journal of Bifurcation and
Chaos.
12
ICONIP 2012
Nikola Kasabov
Auckland University of Technology, New Zealand
Institute of Neuroinformatics - INI, ETH and University of Zurich, Switzerland
Title: Mapping, Learning and Mining of Brain Spatiotemporal Data with 3D Evolving Spiking
Neurogenetic Models
Abstract: Spatio- and spectro-temporal data are the most common data in many domain areas,
including bioinformatics and neuroinformatics. Still there are no sufficient methods to model such data and to
discover complex spatio-temporal patterns from it. The brain is functioning as a spatio-temporal information
processing machine and brilliantly deals with spatio-temporal data, thus being a natural inspiration for the
development of new methods for brain data modeling and pattern recognition. The presented research aims at the
development of a 3D neurogenetic model of the human brain, called NeuCube, that can be efficiently utilized for
spatio-temporal brain-gene data modeling and pattern recognition. The NeuCube is a 3D evolving probabilistic SNN
(epSNN).
epSNN are built on the principles of evolving connectionist systems [1] and eSNN in particular [2,3] and on
probabilistic neuronal models (e.g. [4]). The latter extent the popular leaky integrate-and-fire spiking model with the
introduction of some biologically plausible probabilistic parameters. The epSNN are evolving structures that learn
and adapt to new incoming data in a fast incremental way.
The overall architecture of the NeuCube is presented in [5]. It consists of a reservoir type brain structural map, an
input module for converting input stimuli into spike trains, an eSNN classifier and a gene regulatory network
module. The research explores different types of neuronal models and dynamic synapses, including a SPAN model
[6,7] and a novel deSNN model that implements the time-to-first spike principle and Fusi’s algorithm implemented
on the INI Zurich (www.ini.unizh.ch) SNN chip [8].
Examples of using the NeuCube architecture for brain data modeling are given on EEG-, fMRI-, MEG- and other
types of brain spatio-temporal data with applications including BCI. Neurogenetic models are promising for
modeling and prognosis of neurodegenerative diseases such as Alzheimer’s disease [9,10] and for personalized
medicine in general [11]. Future research is expected to continue through tighter integration of knowledge and
methods from information science, bioinformatics and neuroinformatics [12]. The research is relevant to the future
development in the neuromorphic engineering area.
The research is funded by the EU FP7 Marie Curie project ‘EvoSpike’ and the Knowledge Engineering and
Discovery Research Institute KEDRI (www.kedri.info) of the Auckland University of Technology.
References
[1] N. Kasabov (2007) Evolving Connectionist Systems: The Knowledge Engineering Approach, Springer, London
(first edition published in 2002) .
[2] S. Wysoski, L. Benuskova, N. Kasabov, Evolving Spiking Neural Networks for Audio-Visual Information
Processing, Neural Networks, vol 23, issue 7, pp 819-835, September 2010.
[3] Benuskova and N. Kasabov (2007) Computational Neurogenetic Modelling, Springer, New York
[4] N. Kasabov, To spike or not to spike: A probabilistic spiking neural model, Neural Networks, Volume 23, Issue
1, January 2010, Pages 16-19
[5] Kasabov, N, NeuCube EvoSpike Architecture for Spatio-Temporal Modelling and Pattern Recognition of Brain
Signals, in: Mana, Schwenker and Trentin (Eds) ANNPR, Springer LNAI, 2012, 225-243.
[6] Mohemmed, A., S. Schliebs, S. Matsuda and N. Kasabov, SPAN: Spike Pattern Association Neuron for Learning
Spatio-Temporal Sequences, International Journal of Neural Systems, Vol. 22, No. 4 (2012) 1-16.
[7] Mohemmed, A., S. Schliebs, S. Matsuda and N. Kasabov, Training Spiking Neural Networks to Associate
Spatio-temporal Input-Output Spike Patterns, Neurocomputing, in print, 2012
[8] Kasabov, N., Dhoble, K., Nuntalid, N. and G. Indiveri, Dynamic Evolving Spiking Neural Networks for On-
line Spatio- and Spectro-Temporal Pattern Recognition, Neural Networks, accepted, 2012
[9] Kasabov, N., Evolving Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal
Data Modelling and Pattern Recognition, Springer-Verlag Berlin Heidelberg 2012, J. Liu et al. (Eds.): IEEE WCCI
2012, LNCS 7311, pp. 234–260, 2012.
13
ICONIP 2012
[10] Kasabov, N., R. Schliebs and H. Kojima Probabilistic Computational Neurogenetic Framework: From
Modelling Cognitive Systems to Alzheimer’s Disease, IEEE Transactions of Autonomous Mental Development, 3:(4)
300-3011, 2011
[11] N. Kasabov, Y. Hu (2010) Integrated optimisation method for personalised modelling and case study
applications, Int. Journal of Functional Informatics and Personalised Medicine, vol.3,No.3,236-256.
[12] N. Kasabov (ed) (2012) The Springer Handbook of Bio- and Neuroinfortics, Springer, in print
Biography: Dr. Kasabov is the Director of the Knowledge Engineering and Discovery Research Institute (KEDRI),
Auckland. He holds a Chair of Knowledge Engineering at the School of Computing and Mathematical Sciences at
Auckland University of Technology. He is a Fellow of IEEE and Fellow of the Royal Society of New Zealand. He is
Marie Curie Fellow at the Institute of Neuroinformatics, ETH/University of Zurich. He is the Immediate Past
President of the International Neural Network Society (INNS) and a Past President of the Asia Pacific Neural
Network Assembly (APNNA). He is a member of several technical committees of IEEE Computational Intelligence
Society and IFIP and Distinguished Lecturer of the IEEE CIS. Kasabov has served as Associate Editor of Neural
Networks, IEEE TrNN, IEEE TrFS, Information Science, J. Theoretical and Computational Nanosciences, Applied
Soft Computing and other journals. Kasabov holds MSc and PhD from the Technical University of Sofia, Bulgaria.
His main research interests are in the areas of intelligent information systems, soft computing, neuro-computing,
bioinformatics, brain study, novel methods for data mining and knowledge discovery. He has published more than
450 publications that include 15 books, 130 journal papers, 60 book chapters, 28 patents and numerous conference
papers. He has extensive academic experience at various academic and research organisations. Prof. Kasabov has
received the Bayer Science Innovation Award, the RSNZ Science and Technology Silver Medal, the APNNA
Excellent Service Award, the AUT VC Individual Research Excellence Award, and others. He is Invited Guest
Professor at the Shanghai Jiao Tong University (2010-2012).
Juergen Kurths
Humboldt-Universität zu Berlin, Institute of Physics, Germany
Potsdam Institute for Climate Impact Research, Germany
King s College, University of Aberdeen, UK
Title: Complex Synchronization and Recurrence Analyses
Abstract: Biological systems are typically composed of several subsystems which interact via
several feedbacks. They are, therefore, typical examples of complex systems which are able to self-organization and
complex structure formation even for rather weak changes of parameters or environment.
Basing on modern measurement techniques, such systems can be quantified by multivariate time series. To interpret
these records and to understand basic properties of the underlying complex dynamics, it is, however, necessary to
apply methods from Nonlinear Dynamics and Complex Systems Theory. Note that linear techniques, such as
spectral and correlation analysis, can uncover only linear structures.
We present some modern nonlinear analysis techniques, apply them to multivariate biosignals and discuss their
potentials resp. limits in comparison with well-known linear methods. We especially discuss two main approaches: i)
synchronization analysis of even weakly coupled subsystems, and ii) quantification of (complex) recurrence
properties.
The corresponding techniques will be applied to understand the implications of such network structures on the
functional organization of the brain activities. We investigate synchronization dynamics on the cortico-cortical
network of mammals and find that the network displays clustered synchronization behaviour and the dynamical
clusters coincide with the topological community structures observed in the corresponding anatomical network.
Next, we aim at investigating how graph theoretical approaches can help to discover systematic and task-dependent
differences in high-level cognitive processes such as language perception. We will show that such an approach is
feasible and that the results coincide well with the findings from neuroimaging studies.
14
ICONIP 2012
Biography: Dr. Kurths studied mathematics at the University of Rostock and got his PhD in 1983 at the GDR
Academy of Sciences and his Dr. habil. in 1990. He was full Professor at the University of Potsdam from 1994-2008
and has been Professor of Nonlinear Dynamics at the Humboldt University, Berlin and chair of the research domain
Transdisciplinary Concepts of the Potsdam Institute for Climate Impact Research since 2008 and a 6th century chair
at the Institute for Complex Systems and Mathematical Biology at the Aberdeen University (UK) since 2009.
He is a fellow of the American Physical Society and of the Fraunhofer Society (Germany). He got a Humboldt-CSIR
research price in 2005 and a Dr. h.c. in 2008. He has become a member of the Academia Europaea in 2010.
His main research interests are complex synchronization phenomena, complex networks, time series analysis and
their applications in climatology, sustainability, physiology, systems biology and engineering. He has supervised
more than 50 PhD students from about 20 countries; more than 20 of them have now tenured positions in various
countries. He has published more than 400 papers and two monographs which are cited more than 15,000 times (H-
factor: 51). He is in the editorial board of more than 10 journals, among them CHAOS, Philosophical Trans. Royal
Soc. A, PLoS ONE, European J. Physics ST and Nonlinear Processes in Geophysics.
Erkki Oja
Aalto University, Finland
Title: Inference by matrix factorizations
Abstract: Many standard inference problems involve combinatorial optimizations. A typical
example is clustering in which some items are placed into groups, where the items within each
group are more similar than items belonging to different groups. Another related example is graph bipartitioning
where we want to split a graph into two subgraphs with maximal number of edge weights within the subgraphs and
minimal number of edge weights between them. Yet another generic problem is solving for graph isomorphisms.
This kind of problems can be often presented as matrix decompositions with constraints; typically the solution is
given by a binary orthogonal indicator matrix. The talk reviews an approach where the binary indicator matrix is
replaced by a nonnegative approximately orthogonal continuous-valued matrix. Then the hard combinatorial
optimization is replaced by continuous-space gradient optimization which is computationally much lighter and
results in unsupervised machine learning rules. Correct and convergent versions of the learning rules are presented,
as well as a number of experimental comparisons in various inference problems.
Biography: Dr. Oja (IEEE Fellow) received the D.Sc. degree from Helsinki University of Technology in 1977. He
is Director of the Adaptive Informatics Research Centre and Professor of Computer Science at the Laboratory of
Computer and Information Science, Aalto University (former Helsinki University of Technology), Finland, and the
Chairman of the Finnish Research Council for Natural Sciences and Engineering. He holds an honorary doctorate
from Uppsala University, Sweden. He has been research associate at Brown University, Providence, RI, and visiting
professor at the Tokyo Institute of Technology, Japan. He is the author or coauthor of more than 300 articles and
book chapters on pattern recognition, computer vision,and neural computing, and three books: “Subspace Methods
of Pattern Recognition” (New York: Research Studies Press and Wiley, 1983), which has been translated into
Chinese and Japanese; “Kohonen Maps” (Amsterdam, The Netherlands: Elsevier, 1999), and “Independent
Component Analysis” (New York: Wiley, 2001; also translated into Chinese and Japanese). His research interests
are in the study of principal component and independent component analysis, self-organization, statistical pattern
recognition, and applying artificial neural networks to computer vision and signal processing.
Dr. Oja is a member of the Finnish Academy of Sciences, Fellow of the IEEE, Founding Fellow of the International
Association of Pattern Recognition (IAPR), Past President of the European Neural Network Society (ENNS), and
Fellow of the International Neural Network Society (INNS). He is a member of the editorial boards of several
journals and has been in the program committees of several recent conferences including the International
Conference on Artificial Neural Networks (ICANN), International Joint Conference on Neural Networks (IJCNN),
and Neural Information Processing Systems (NIPS). Prof. Oja is the recipient of the 2006 IEEE Computational
Intelligence Society Neural Networks Pioneer Award.
15
ICONIP 2012
Marios M. Polycarpou
University of Cyprus, Cyprus
Title: Distributed Fault Diagnosis in Uncertain Dynamical Systems
Abstract: The emergence of networked embedded systems and sensor/actuator networks has
given rise to advanced monitoring and control applications, where a large amount of sensor data is
collected and processed in real-time in order to activate the appropriate actuators and achieve the
desired control objectives. However, in situations where a fault arises in some of the components, or an unexpected
event occurs in the environment, this may lead to a serious degradation in performance or to an overall system
failure. The goal of this presentation is to motivate the need for health monitoring, fault diagnosis and security of
complex distributed dynamical systems and to provide a fault diagnosis methodology for detecting, isolating and
accommodating both abrupt and incipient faults in a class of complex nonlinear dynamic systems. A detection and
approximation estimator based on computational intelligence techniques is used for online health monitoring.
Various adaptive approximation techniques and learning algorithms will be presented and illustrated, and directions
for future research will be discussed.
Biography: Marios M. Polycarpou is a Professor of Electrical and Computer Engineering and the Director of the
KIOS Research Center for Intelligent Systems and Networks at the University of Cyprus. He received the B.A.
degree in Computer Science and the B.Sc. degree in Electrical Engineering both from Rice University, USA in 1987,
and the M.S. and Ph.D. degrees in Electrical Engineering from the University of Southern California, in 1989 and
1992 respectively. In 1992, he joined the University of Cincinnati, Ohio, USA, where he reached the rank of
Professor of Electrical and Computer Engineering and Computer Science. In 2001, he was the first faculty to join
the newly established Department of Electrical and Computer Engineering at the University of Cyprus, where he
served as founding Department Chair from 2001 to 2008. His teaching and research interests are in intelligent
systems and networks, automation and computational intelligence, fault diagnosis and distributed systems. Dr.
Polycarpou has published more than 220 articles in refereed journals, edited books and refereed conference
proceedings, and he is the holder of 3 patents. Prof. Polycarpou is a Fellow of the IEEE and currently serves as the
President of the IEEE Computational Intelligence Society. He has served as the Editor-in-Chief of the IEEE
Transactions on Neural Networks and Learning Systems between 2004-2010. He has been invited as Keynote
Plenary Speaker at more than 15 international conferences during the last three years and is currently an IEEE
Distinguished Lecturer in computational intelligence. He participated in more than 50 research projects/grants,
funded by several agencies and industry in the European Union, the United States, and by the Research Promotion
Foundation of Cyprus. He has recently been awarded the prestigious European Research Council (ERC) Advanced
Grant by the European Commission.
Leszek Rutkowski
Czestochowa University of Technology, Poland
Title: On Stream Data Mining - New Results and Challenges
Abstract: Data stream mining became recently a very challenging task in the data mining
community. Unlike the static dataset, data stream is of infinite size. Data elements arrive to the
system continuously, often with very high rates. Moreover, the concept of data can evolve in
time, what is known as the concept drift. For these reasons, commonly known data mining algorithms cannot be
directly applied to the data streams. In this presentation we focus on clustering and classification for data stream. A
review of available techniques is presented, new algorithms are described and challenges for future work are
outlined.
Biography: Dr. Rutkowski (IEEE Fellow 2005) received the M.Sc. and Ph. D. degrees in 1977 and 1980,
respectively, both from the Technical University of Wroclaw, Poland. Since 1980, he has been with the Technical
University of Czestochowa where he is currently a Professor and Chairman of the Computer Engineering
16
ICONIP 2012
Department. From 1987 to 1990 he held a visiting position in the School of Electrical and Computer Engineering at
Oklahoma State University. His research interests include neural networks, fuzzy systems, computational
intelligence, pattern classification and expert systems. In May and July 2004 he presented in the IEEE Transaction
on Neural Networks a new class of probabilistic neural networks and generalized regression neural networks
working in a time-varying environment. He published over 170 technical papers including 20 in various series of
IEEE Transactions. He is the author of the following books: Computational Intelligence published by Springer
(2008), New Soft Computing Techniques For System Modeling, Pattern Classification and Image Processing
published by Springer (2004), Flexible Neuro-Fuzzy Systems published by Kluwer Academic Publishers (2004),
Methods and Techniques of Artificial Intelligence (2005, in Polish), Adaptive Filters and Adaptive Signal
Processing (1994, in Polish), and co-author of two others (1997 and 2000, in Polish) Neural Networks, Genetic
Algorithms and Fuzzy Systems and Neural Networks for Image Compression. Dr. Leszek Rutkowski is President
and Founder of the Polish Neural Networks Society. He organized and served as a General Chair of the International
Conferences on Artificial Intelligence and Soft Computing held in 1996, 1997, 1999, 2000, 2002, 2004, 2006, 2008,
2010 and 2012. Dr. Leszek Rutkowski is past Associate Editor of the IEEE Transactions on Neural Networks (1998-
2005) and IEEE Systems Journal (2007-2010). He is Editor-in-Chief of Journal of Artificial Intelligence and Soft
Computing Research and he is on the editorial board of the International Journal of Applied Mathematics and
Computer Science (1996-present) and International Journal of Biometric (2008-present). In 2004 Dr. Leszek
Rutkowski was awarded by the IEEE Fellow Membership Grade for contributions to neurocomputing and flexible
fuzzy systems. He is a recipient of the IEEE Transactions on Neural Networks 2005 Outstanding Paper Award. Dr.
Leszek Rutkowski served in the IEEE Computational Intelligence Society as the Chair of the Distinguished Lecturer
Program (2008-2009) and the Chair of the Standards Committee (2006-2007). He is the Founding Chair of the
Polish Chapter of the IEEE Computational Intelligence Society which won 2008 Outstanding Chapter Award. In
2004 he was elected as a member of the Polish Academy of Sciences.
Ron Sun
Renasselaer Polytechnic Institute, USA
Title: The CLARION Cognitive Architecture: Motivation, Personality, and Social Interaction
Abstract: In this talk, I will focus on a hybrid cogntiive architecture that has been developed
over many years, CLARION. In this dual-process cognitive architecture, the interaction
between implicit and explicit cognitive processes is emphasized. Using the cognitive
architecture, various psychological effects of the interaction between the two types of processes have been
accounted for and explained. Thus far, CLARION has been capturing a wide range of quantitative human behavioral
data, including in the areas of human motivation, personality, and cognitive social simulation, all of which further
validate the cognitive architecture, and its focus on the dual processes of and the interaction between the implicit
and the explicit. Many new simulations have been conducted and new human experiments have generated relevant
data.
Biography: Dr. Sun is Professor of Cognitive Science at RPI. His research interests center around the study of
cognition, especially in the areas of cognitive architectures, human reasoning and learning, cognitive social
simulation, and hybrid connectionist-symbolic models. He published many papers in these areas, as well as nine
books, including: (Duality of the Mind) and (Cambridge Handbook of Computational Psychology). For his paper on
integrating rule-based and connectionist models for accounting for human everyday reasoning, he received the 1991
David Marr Award from Cognitive Science Society. For his work on human skill learning, he received the 2008
Hebb Award from International Neural Network Society.
He is the founding co-editor-in-chief of the journal (Cognitive Systems Research), and also serves on the editorial
boards of many other journals. He chaired a number of major international conferences (such as CogSci and IJCNN).
He is a member of the Governing Boards of Cognitive Science Society and International Neural Networks Society,
and President of INNS 2011-2012.
17
ICONIP 2012
Jun Wang The Chinese University of Hong Kong, Hong Kong Dalian University of Technology, China Title: Neural Network Approaches to Nonlinear and Robust Model Predictive Control
Abstract: In this talk, a model predictive control (MPC) scheme will be presented for partially
known nonlinear dynamical systems based on feedforward and recurrent neural networks. To
avoid the convexity of problem formulation with nonlinear systems, the original nonconvex
optimization problem associated with nonlinear MPC is relaxed as a convex one by means of Jacobian
decomposition via Taylor expansion. An online supervised learning algorithm is developed for estimating the
unknown residual term resulted from the Jacobian linearization To save time, offline supervised learning is also
carried out based on feedforward neural networks and support vector machines for parameter estimation. The
proposed neural network approaches have many desirable properties with superior performance for trajectory
tracking and disturbance rejection. Simulation results of many examples will be provided to demonstrate the
effectiveness and performance of the proposed approach. The results of the applications to control underactuated
marine surface vessels and autonomous underwater vehicles will also be discussed.
Biography: Dr. Wang is a Professor in the Department of Mechanical and Automation Engineering at the Chinese
University of Hong Kong. Prior to this position, he held various academic positions at Dalian University of
Technology, Case Western Reserve University, and University of North Dakota. He also held various short-term
visiting positions at USAF Armstrong Laboratory (1995), RIKEN Brain Science Institute (2001), Universite
Catholique de Louvain (2001), Chinese Academy of Sciences (2002), Huazhong University of Science and
Technology (200607), and Shanghai Jiao Tong University (2008-2011) as a Changjiang Chair Professor. He
received a B.S. degree in electrical engineering and an M.S. degree in systems engineering from Dalian University
of Technology, Dalian, China. He received his Ph.D. degree in systems engineering from Case Western Reserve
University, Cleveland, Ohio, USA. His current research interests include neural networks and their applications. He
published about 150 journal papers, 12 book chapters, 10 edited books, and numerous conference papers in these
areas. He has been an Associate Editor of the IEEE Transactions on Systems, Man, and Cybernetics, Part B since
2003 and a member of the Editorial Advisory Board of the International Journal of Neural System since 2006. He
also served as an Associate Editor of the IEEE Transactions on Neural Networks (1999-2009) and IEEE
Transactions on Systems, Man, and Cybernetics, Part C (2002-2005). He is an IEEE Fellow, an IEEE Distinguished
Lecturer, and a recipient of the Outstanding Paper Award for a paper published in the IEEE Transactions on Neural
Networks in 2008, Research Excellence Award from the Chinese University of Hong Kong for 2008-2009 and
Shanghai Natural Science Award (first class) in 2009.
18
ICONIP 2012
Invited Speeches
Cesare Alippi
Politecnico di Milano, Italy
Title: A Just-In-Time Learning strategy for Adaptive Classifiers
Abstract: Most of machine learning applications assume the stationarity hypothesis for the
process generating the data. This amenable assumption is so widely –and implicitly- accepted that
sometimes we even forget that it does not generally hold in the practice due to concept drift (i.e., a
structural change in the process generating the acquired datastream).
The ability to detect concept drift and react accordingly is hence a major achievement for intelligent learning
machines and constitutes one of the hottest research topics. The talk will focus on the active just-in-time approach
where changes e.g., induced by faults, time variance in the environment and ageing effects are detected by triggering
mechanisms. After change detection the system immediately reacts to mitigate the accuracy loss by tracking the
system evolution (just-in-time approach). Machine learning-based change detection tests will be introduced and
coupled with the classifier case to generate adaptive classification systems.
Biograph: Cesare Alippi received the Dr.Ing. Degree in electronic engineering (summa cum laude) in 1990 and the
Ph.D. degree in computer engineering in 1995, both from Politecnico di Milano, Milan, Italy. He has been a visiting
researcher at the University College London, London, U.K., the Massachusetts Institute of Technology, Cambridge,
USA, the École Supérieure de Physique et de Chimie Industrielles, France, the University of Lugano, Switzerland,
and the Chinese Academy of Sciences, China.
Alippi was a research scientist of the Italian National Research Council (1996-1998), then Reader and Associate
Professor at Politecnico di Milano. Since 2002, he has been a Full Professor in Information Processing Systems at
the same institution. In 2004 he received the IEEE Instrumentation and Measurement Society Young Engineer
Award; in 2011 he has been awarded Knight of the Order of Merit of the Italian Republic. Current research activity
addresses adaptation and learning in non-stationary and evolving environments and Intelligent Embedded Systems;
Alippi holds 5 patents and has published about 200 papers in international journals and conference proceedings.
Cesare Alippi is a Fellow of the IEEE, Vice President-elect for Education of the IEEE Computational Intelligent
Society (CIS), Chair of the Awards Committee of the CIS (2012), Associate Editor of the IEEE-TNN (2004-2011),
Associate Editor of the IEEE-TIM (2003-2010), Chair of the IEEE CIS NNTC (2008-2010). He was General Chair
of IJCNN 2012 and will be program chair of IJCNN 2014.
Tianping Chen
Fudan University, China
Title: Coordination of complex networks
Abstract: Coordination of complex networks is a hot topic in the theoretical research and
applications. Today, the study of synchronization in complex dynamical systems has become a
subject of great interest due to its applications and potential applications in a variety of fields,
such as communication, seismology, and neural networks. In this talk, I will address coordination of complex
networks, which includes synchronization, stability, consensus and pinning control. In particular, I will address the
relations and differences among these concepts and clarify some misunderstandings. I will also address some pulse-
coupled networks with time-delay and show the essential difference between the case without delay and with delay.
Biography: Tianping Chen graduated as a Postgraduate Student from Mathematics Department, Fudan University,
Shanghai, China, in 1965. Currently, he is a Professor at the School of Mathematical Sciences, Fudan University.
His research interests include complex networks, neural networks, signal processing, dynamical systems, and
complex networks, harmonic analysis, approximation theory. Prof. Chen is a recipient of several awards, including
second prize of 2002 National Natural Sciences Award of China, 1997 Outstanding Paper award of the IEEE
Transactions on Neural Networks, and 1997 Best Paper award of the Japanese Neural Network Society.
19
ICONIP 2012
Yiran Chen
University of Pittsburgh
Title: Centaur: Bio-inspired Ultra Low-Power Hybrid Embedded Computing Engine Beyond
One TeraFlops/Watt
Abstract: As technology scaling down becomes more and more difficult, the traditional von
Neumann computer architecture cannot satisfy people’s unlimited demand on high performance
computation. Consequently, the neuromorphic hardware systems providing the capabilities of
biological perception and information processing at compact and energy-efficient platform have drawn people’s
attention. Realizing neural network algorithms requires a large volume of memory and being adaptive to
environment, which results in high design complexity and hardware cost. Besides the advantaves such as non-
volatility, low-power consumption, high integration density, and excellent scalability, the recently rediscovered
memristor devices have the unique property to record the historical profile of the excitations on the device, making it
an ideal candidate to realize the synapse behavior in electronic neural networks. In this talk, I will introduce the
utilizations of memristors in dynamic reconfigurable systems and in hardware realization of neuromorphic
algorithms, named “Centaur”. Centaur can offer extremely high computation parallelism, high resilience to process
variations and transient run-time errors, and high power efficiency with ultra-low hardware cost and small footprint.
Moreover, our design is fully compatible to the present-day CMOS fabrication process, demonstrating an excellent
scalability.
Biography: Dr. Yiran Chen: Dr. Chen is an assistant professor in the Department of Electrical and Computer
Engineering at the University of Pittsburgh. He received his Ph. D. in 2005 from Purdue University. He joined the
University of Pittsburgh with 5-year industry experiences in 2010. Dr. Chen has over 100 refereed publications and
64 granted US patents (and other 19 pending applications) in the area of post-silicon device, VLSI design, low
power circuit and architecture, nueromorphic computing and sensing technology. His research work has been
featured by two times AFRL visiting faculty fellowships, seven times best paper awards and nominations, three
times professional society and industry awards, and A. Richard Newton Scholarship. His research work has been
supported by NSF, AFRL, HP, DAC, etc.
Gang Feng
City University of Hong Kong, Hong Kong
Title: Universal Neural Controllers for General Nonlinear Systems
Abstract: This talk investigates the universal neural controller problem for continuous-time
multi-input-multi-output general nonlinear systems based on a class of generalized dynamic
neural network models. By using their function approximation capability, this kind of
generalized dynamic neural network models are shown to be universal neural models for general
nonlinear systems under some sufficient conditions. It is then shown that the stabilization problem of a general
nonlinear system can be solved as the robust stabilization problem of its generalized dynamic neural network model
with the approximation errors as the uncertainty term. Then the results of universal neural controllers for general
nonlinear systems are also provided. Finally, a numerical example is presented to demonstrate the effectiveness of
the proposed approach.
Biograph: Gang Feng received the B. Eng and M. Eng. degrees in Automatic Control from Nanjing Aeronautical
Institute, China in 1982 and in 1984 respectively, and the Ph. D. degree in Electrical Engineering from the
University of Melbourne, Australia in 1992. He has been with City University of Hong Kong since 2000 where he is
now a Chair Professor of Mechatronic Engineering. He is also a ChangJiang Chair Professor at Nanjing University
of Science and Technology, awarded by Ministry of Education, China. He was lecturer/senior lecturer at School of
Electrical Engineering, University of New South Wales, Australia, 1992-1999. He was awarded an Alexander von
Humboldt Fellowship in 1997-1998, and the IEEE Transactions on Fuzzy Systems Outstanding Paper Award in
2007. He has authored/co-authored over 200 international journal papers including over 90 in IEEE Transactions
and numerous conference papers. His current research interests include intelligent systems & control, networked
systems & control, and multi-agent systems & control.
Prof. Feng is an IEEE Fellow, an associate editor of IEEE Transactions on Fuzzy Systems, and was an associate
editor of IEEE Transactions on Automatic Control, IEEE Transactions on Systems, Man & Cybernetics, Part C,
Mechatronics, and Journal of Control Theory and Applications.
20
ICONIP 2012
David Y Gao
University of Ballarat, Victoria, Australia
Title: Canonical Duality and Triality: Unified Understanding for Modeling and Simulation of
Complex Systems with Applications in Neural Information Processing
Abstract: Duality is a beautiful, inspiring, and fundamental concept that underlies all natural
phenomena. In mathematical modeling and simulation of complex systems, information theory
and decision science, neurodynamic optimization and learning algorithms, nonconvex analysis
and chaotic dynamics, global optimization and control, numerical methods and scientific computation, etc, duality
principles and methods are playing more and more important roles. The canonical duality theory is a potentially
powerful methodology, which can be used to model complex systems within a unified framework. The associated
triality theory reveals an interesting multi-scale duality pattern of natural phenomena, which can be used to identify
both global and local extrema and to design powerful algorithms for solving a wide class of challenging problems in
both discrete and continuous systems
Beginning with some typical nonconvex problems in neural networks and nonlinear dynamical systems, the speaker
will present a brief introduction to the canonical duality theory and its role for solving general challenging problems
in complex systems. By using the canonical dual transformation, a class of nonconvex/nonsmooth/discrete problems
can be reformed as a unified canonical dual problem in continuous space, which can be solved completely (under
certain conditions) to obtain all possible solutions. Therefore, a unified analytical solution form can be obtained for a
large class of problems in nonlinear analysis and global optimization; both global and local optimal solutions can be
identified by the triality theory. Results will show that for many nonconvex variational problems, the global optimal
solutions are usually nonsmooth, and cannot be captured by any traditional Newton-type direct approaches. For
problems in radial basis neural networks, the global minimum may not be the optimal solution, instead, certain local
minima could play important roles in machine learning and database analysis. Applications will be illustrated by
certain well-known NP-hard problems in computational sciences, chaotic systems, network communications and
optimization.
Biography: David Y Gao is the Alexander Rubinov Chair Professor of Mathematical Science in School of Science,
Information Technology and Engineering at the University of Ballarat and Professor of Engineering Mechanics in
Research School of Engineering at the Australia National University. He received his Ph. D. from Tsinghua
University. Since then, he has held research and teaching positions in different institutes including MIT (Math), Yale
(Mechanical Engineering), Harvard (Math), University Hong Kong (Civil Engineering), the University of Michigan
(Math and Applied Mechanics), and Virginia Tech (Math/Industrial and Systems Engineering).
Professor Gao’s research interests range over an interdisciplinary fields of applied math, engineering sciences,
global optimization and complex systems theory. His main research contributions include a canonical duality/triality
theory, which can be used for modeling complex systems within a unified framework and for solving a large class of
nonconvex/ nonsmooth/ discrete problems in networks optimization, integer programming, chaotic systems,
bifurcation theory, phase transitions in solids, nonlinear algebraic/partial differential equations, information theory,
decision science, numerical methods and computational science. He has published about 10 monograph/ handbook/
edited books and more than 150 research papers.
Professor Gao is an editor-in-chief for three book series including Advances in Mechanics and Mathematics by
Springer. He is also an associate editor of about eight international journals. Currently, he is serving as the
Secretary-General and Vice President of the International Society of Global Optimization.
Haibo He
University of Rhode Island, USA
Title: Adaptive Learning and Control for Machine Intelligence
Abstract: With the recent development of brain research and modern technologies, scientists
and engineers might hopefully find efficient ways to develop brain-like intelligent systems that
are highly robust, adaptive, and fault tolerant to uncertain and unstructured environments. Yet,
developing such truly intelligent systems requires significant research on both fundamental
21
ICONIP 2012
understanding of brain intelligence as well as complex engineering design. This talk aims to present the recent
research developments in computational intelligence with a focus on learning and control to advance the machine
intelligence research and explore their wide applications across different critical engineering domains.
Specifically, this talk covers numerous aspects of the foundations and architectures of adaptive learning and control.
The key objective is to achieve cognitive-alike optimization and prediction capability through learning. An essential
component of this talk is a recent development of a hierarchical adaptive/ approximate dynamic programing (ADP)
architecture for improved learning and optimization capability over time. This architecture integrates a hierarchical
goal generator network to provide the system a more informative and detailed goal representation to guide its
decision making. In this way, instead of using a typical binary reinforcement signal to represent “success” or
“failure” of the system, we propose a more informative internal reinforcement representation for the intelligent
system to make better choice of actions. Applications of our research to complex systems such as smart grid will be
discussed.
Brief Biography: Dr. Haibo He is an Associate Professor of Electrical Engineering at the University of Rhode
Island, Kingston, RI. He currently directs the Computational Intelligence and Self-Adaptive (CISA) Laboratory. He
has published one research book (Wiley), edited 6 conference proceedings (Springer), and authored/co-authors over
100 peer-reviewed journal and conference papers, including one most-cited paper in the IEEE Transactions on
Knowledge and Data Engineering. His researches have been covered by various media such as IEEE Smart Grid
Newsletter, The Wall Street Journal, Providence Business News, among others. He has served regularly on the
organizing committees and program committees of numerous international conferences. Currently, he is an
Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems, and IEEE Transactions on
Smart Grid. He received the National Science Foundation (NSF) CAREER Award (2011) and the Providence
Business News (PBN) “Rising Star Innovator” of The Year Award (2011).
Amir Hussain
University of Stirling, Scotland, UK
Title: Towards Cognitive Control of Autonomous Systems
Abstract: Autonomous vehicle control (AVC) is a rapidly growing research area that promises
improved performance, fuel economy, emission levels, comfort and safety in next generation
intelligent transportation systems. The key AVC problem of selecting from amongst a set of
actions or behaviours is also a central problem for animals and there is growing evidence that a set of central brain
nuclei - the basal ganglia (BG) - are used by all vertebrates to help solve this problem. Research over the last decade
has focused on developing computational models of how the basal ganglia support behavioural selection and process
brain information. Thus, it is believed that the basal ganglia act as a central ‘selector’ or ‘switch’ in all vertebrate
brains, in that they examine requests for behaviour and allow the most urgent or salient requests to be selected for
behavioural expression. Given the inherent similarities between the two problem domains of AVC and action
selection in animals, a new ambitious multi-disciplinary research project led by Professor Hussain at the University
of Stirling in Scotland, funded by the UK Engineering and Physical Sciences Research Council (EPSRC) and
industry, is aiming to leverage new results from psychology and neurobiology and apply them to develop the next-
generation of cognitive AVC controllers. The benefits of the developed controllers will be evaluated within the
challenging context of regular road driving and planetary rover vehicles. In this talk, preliminary simulation results
using realistic vehicle models under different driving scenarios will be presented to demonstrate the effectiveness of
our proposed BG-based soft-switching approach to cognitive control of autonomous vehicles. The talk will also
outline the potential impact of the on-going multi-disciplinary research and its ramifications across a number of
areas including: intelligent transportation systems, adaptive control systems engineering in general, and cognitive
and computational neuroscience.
Biography: Dr Hussain obtained his BEng (with the highest 1st Class Honours) and PhD in Electronic and Electrical
Engineering from the University of Strathclyde in Glasgow, in 1992 and 1997 respectively. Following a post-
doctoral Research Fellowship at the University of Paisley (1996-98) and a research Lectureship at the University of
22
ICONIP 2012
Dundee (1998-2000), he joined the University of Stirling in 2000, where is currently Professor of Computing
Science and founding Director of the Cognitive Signal-Image Processing and Control Systems Research (COSIPRA)
Laboratory. He has (co)authored/edited ten Books and around 200 papers to-date in leading international journals
and refereed Conference proceedings. Since 2000, he has generated over £1m in research income as principal
investigator, including from UK research councils, EU FP6/7, international charities and industry. He is founding
Editor-in-Chief of both Springer’s Cognitive Computation journal and SpringerBriefs in Cognitive Computation,
Associate Editor for the IEEE Transactions on Neural Networks & Learning Systems and serves on the Editorial
Board of a number of other journals. He regularly serves as invited speaker, general and program (co)chair and
organizing committee member for leading international conferences. He is Chair of the IEEE UK & Republic of
Ireland (RI) Industry Applications Society Chapter.
Daisuke Inoue
National Institution of Information and Communications Technology, Japan
Title: Fight against Emerging Security Threats with Data Mining Technologies
Abstract: Emotion is essential for humans. It not only contributes to communication between
humans, but also plays a critical role in rational and intelligent behavior. Its functions can be seen
in many aspects of our daily lives. Thus, the study of automatic emotion recognition techniques is
indispensable. In this talk, we present a study on finding the relationship between EEG and human emotion activities.
EEG signals were utilized to classify two kinds of emotion, positive and negative. First, we extracted features from
original EEG data and used a linear dynamic system to smooth these features. An average testing accuracy of
87.53% was obtained by using all of the features together with a support vector machine. Next, we reduced the
dimension of features through correlation coefficients. The top 100 and top 50 subject-independent features were
achieved, with average testing accuracies of 89.22% and 84.94%. At last, a manifold model was applied to find the
trajectory of emotion changes.
Malwares, such as worms, virus, and bots are spread all over cyberspace and often lead to serious security incidents
that can cause significant damages to both infrastructures and end users. To grasp the present trends of malware
activities over networks, we have been developing the Network Incident analysis Center for Tactical Emergency
Response (nicter) that presently monitors large-scale darknet, a set of unused IP addresses. However, several new
types of security threads, such as drive-by download, SNS malwares, advanced persistent threat etc., have arisen,
which require developing new security frameworks with data mining technologies. This presentation will provide
current achievement of the nicter system and the landscape of emerging security threats in order to share the newest
security issues between both research fields on cybersecurity and data mining.
Biography: Daisuke Inoue received his B.E. and M.E. degrees in electrical and computer engineering and Ph.D.
degree in engineering from Yokohama National University in 1998, 2000 and 2003, respectively. He joined the
Communications Research Laboratory (CRL), Japan, in 2003. The CRL was relaunched as the National Institute of
Information and Communications Technology (NICT) in 2004, where he is the director of Cybersecurity Laboratory
in Network Security Research Institute. His research interests include security and privacy technologies in wired and
wireless networks, incident analysis and response technologies based on network monitoring and malware analysis.
He received the best paper award at the 2002 Symposium on Cryptography and Information Security (SCIS 2002),
and the commendation for science and technology by the minister of MEXT, Japan, in 2009.
Qing Nie
University of California Irvine, USA
Title: Noise Attenuation and Robustness in Cell Signaling and Patterning
Abstract: Noises and stochastic effects usually exist in every biological system due to many
intrinsic and extrinsic factors. In this talk, I will discuss strategies and principles for noise
attenuation and robustness to genetic or/and environmental perturbations in cell signaling and
23
ICONIP 2012
embryonic patterning. In one case, I will introduce a critical quantity that dictates capability of attenuating temporal
noises in feedback systems. In another case, I will show that noises in signal transduction actually enable reduction
of stochastic effects in spatial patterns. In addition, I will present several new experimental data in yeast cells and
zebrafish embryo that support our modeling and computational predictions.
Biography: Qing Nie is a Professor of Mathematics and Biomedical Engineering at University of California, Irvine
(UCI). He received Ph.D. in Mathematics (1995) at The Ohio State University. Prior to joining UCI in 1999, he
was at University of Chicago working in the areas of computational fluid and solid mechanics. Since 2001, his
research interests have been on systems biology, cell signaling, stem cell, and morphogenesis. He is a Chancellor
Fellow, the director of Center for Mathematical and Computational Biology, the acting director of a Ph.D. training
program on systems biology at UCI, and the associate director for Center for Complex Biological Systems – one of
the NIH funded National Centers for Systems Biology. He also serves in numerous NIH study sections and NSF
panels, and he is in editorial boards for several journals.
G. Kumar Venayagamoorthy
Clemson University, USA
Title: Dynamic Scalable Monitoring and Control Technologies for Smart Grids
Abstract: The smart electric power grid will evolve into a very complex adaptive and
reconfigurable system under semi-autonomous distributed control. Its spatial and temporal
complexity, non-convexity, non-linearity, non-stationarity, variability and uncertainties exceed
the characteristics found in today’s traditional power system. The distributed integration of
intermittent sources of energy and energy storage in a smart grid further adds complexity and challenges to its
modeling, control and optimization. Innovative technologies are needed for a smart grid to handle the growing
complexity, stochastic bidirectional optimal power flows, and maximization of penetration of renewable energy and
utilization of available energy storage.
Smart grids will need to be monitored continuously to maintain stability, reliability and efficiency under normal and
abnormal operating conditions and disturbances. A combination of capabilities for forecasting, predictive state
estimation, dynamic power flow, system optimization, and solution practicability verification and validation will be
necessary. The optimization and control systems for a smart grid environment will require innovative information
and computational capabilities to handle the uncertainties and variability that exist. Intelligent technologies needed
for sense-making, situational awareness, decision-making, control and optimization in a smart grid environment will
be presented in this talk.
Biography: Ganesh Kumar Venayagamoorthy received his Ph. D. degree in electrical engineering from the
University of Natal, Durban, South Africa, in 2002. He is the Duke Energy Distinguished Professor of Electrical and
Computer Engineering at Clemson University, Clemson, USA. Prior to that, he was a Professor of Electrical and
Computer Engineering at the Missouri University of Science and Technology (Missouri S&T), Rolla, USA. He was
a Visiting Researcher with ABB Corporate Research, Sweden, in 2007. Dr. Venayagamoorthy is Founder and
Director of the Real-Time Power and Intelligent Systems Laboratory (http://rtpis.org). His research interests are in
the development and applications of advanced computational algorithms for real-world applications, including
power systems stability and control, smart grid applications, sensor networks and signal processing. He has
published 2 edited books, 6 book chapters, and over 90 refereed journals papers and 290 refereed conference
proceeding papers. Dr. Venayagamoorthy is a recipient of several awards including a 2008 US National Science
Foundation (NSF) Emerging Frontiers in Research and Innovation Award, a 2007 US Office of Naval Research
Young Investigator Program Award, a 2004 NSF CAREER Award, the 2010 Innovation Award from St. Louis
Academy of Science, the 2010 IEEE Region 5 Outstanding Member Award, the 2006 IEEE Power and Energy
Society Outstanding Young Engineer Award, and the 2003 International Neural Network Society’s Young
Investigator Award. He is the recipient of the 2012 Institution of Engineering and Technology (IET) Generation,
Transmission and Distribution Premier Award for the best research paper published during last two years for the
paper “Wide area control for improving stability of a power system with plug-in electric vehicles”. Dr.
24
ICONIP 2012
Venayagamoorthy is involved in the leadership and organization of many conferences including the co-Chair of the
2013 IEEE Symposium of Computational Intelligence Applications in Smart Grid (CIASG). He is currently the
Chair of the IEEE PES Working Group on Intelligent Control Systems, the Founder and Chair of IEEE
Computational Intelligence Society (CIS) Task Force on Smart Grid, and the Chair of the IEEE PES Intelligent
Systems Subcommittee. He is currently an Editor of the IEEE Transactions on Smart Grid.
Dr. Venayagamoorthy is a Senior Member of the IEEE, and a Fellow of the IET, UK, and the SAIEE.
Michel Verleysen
Univ. cat. Louvain, Louvain-la-Neuve, Belgium
Title: About the optimality of mutual information for feature selection
Abstract: Feature selection is an essential task in machine learning. Feature selection is
helpful for decreasing the dimension of the data space, therefore fighting the curse of
dimensionality, and to extract meaningful features that can be interpreted by the application
experts. Among the filter methods to perform feature selection, mutual information is
considered as an appropriate choice in the literature, for its ability to deal with multivariate feature choices and with
non-linear relations between variables, and for its natural interpretation in terms of feature relevance. Nevertheless,
the exact link between optimality of features under the mutual information criterion, and model performance
enhancement, has never been investigated in depth. This talk will show that, although efficient in practice, the
mutual information criterion might fail, in specific circumstances, to select the subset of features that will reduce the
probability of misclassification of a model built on this subset.
Biography: Michel Verleysen is Full Professor at the Université catholique de Louvain, and Honorary Research
Director of the Belgian F.N.R.S. (National Fund for Scientific Research). He was an invited professor at the Swiss
E.P.F.L. (Ecole Polytechnique Fédérale de Lausanne, Switzerland) in 1992, at the Université d'Evry Val d'Essonne
(France) in 2001, and at the Université ParisI-Panthéon-Sorbonne from 2002 to 2012, respectively. He is editor-in-
chief of the Neural Processing Letters journal (published by Springer), chairman of the annual ESANN conference
(European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning), past
associate editor of the IEEE Trans. on Neural Networks journal, and member of the editorial board and program
committee of several journals and conferences on neural networks and learning. He was the chairman of the IEEE
Computational Intelligence Society Benelux chapter (2008-2010), and member of the executive board of the
European Neural Networks Society (2005-2010). He is author or co-author of more than 250 scientific papers in
international journals and books or communications to conferences with reviewing committee. He is the co-author
of the scientific popularization book on artificial neural networks in the series “Que Sais-Je?”, in French, and of the
“Nonlinear Dimensionality Reduction” book published by Springer in 2007.
Rubin Wang
East China University of Science and technology, China
Title: Action and rule of neuronal energy in signal processing of cerebral cortex
Abstract: By re-examining the energy model for neuronal activities, we show the inadequacy
in the current understanding of the energy consumption associated with the activity of a neuron.
Specifically, we show computationally that a neuron first absorbs energy and then consumes
energy during firing action, and this result cannot be produced from any current models of neurons or biological
neural networks. Based on this finding, we provide an explanation for the observation that when neurons are excited
in the brain, blood flow increases significantly while the incremental consumption of oxygen is very small. We can
also explain why external stimulation and perceptual emergence are synchronized. Here we also show that the
negative energy of neurons at sub-threshold state is an essential reason which leads to response time of blood flow
increasing being delay than neural activity.
25
ICONIP 2012
Biography: Professor Rubin Wang is a native of the People’s Republic of China, and was born in the city of Hang
Zhou in the Zhe Jiang region on February 23, 1951. He obtained his Master of Science degree from the Department
of Mechanical Engineering of Kyushu Sangyo University in 1996, and his Ph.D. from the Department of Electronic-
Mechanical Engineering of Nagoya University of Japan in 1998. Dr. Wang was awarded his Ph. D. degree one year
early because of his excellent academic achievement. From April 1998 to March 2000 he becomes a postdoctoral
fellow at Japan Society for the Promotion of Science (JSPS). In 2000 he was appointed as professor and advisor of
doctoral student at Donghua University in Shanghai of China, and from 2001 to 2004 he was appointed as professor
of Institute for Computational Science and Engineering at Ocean University of China. He visited Brain Science
Institute (BSI) of Japan on 2004 and 2005. Starting from 2005 he is appointed as professor and advisor of doctoral
student at East China University of Science and Technology in Shanghai (ECUST). He is a director of Institute for
Cognitive Neurodyanmics in ECUST. His interests include neuroinformatics and cognitive neurodynamics,
dynamics of complex systems. His is an Editor-in-Chief of Cognitive Neurodynamics published by Springer. He is
also a conference chair of ICCN 2007 and ICCN 2009 and a conference co-chair of ICCN 2011 and ICCN 2013.
Zidong Wang
Brunel University, UK
Title: A Sampled-Data Approach to Analysing Complex Networks
Abstract: In this talk, we will address the sampled-data synchronization control problem for a
class of general complex networks, and then deal with the sampled-data filtering problems for
two special classes of complex networks - wireless sensor networks and genetic regulatory
networks. The sampling period considered here is time-varying that is allowed to switch
between two different values in a random way. The main purpose is to deliver the message that sampled-data issue
is vitally important for the applications of complex network theory and the sampled-data filtering/control problems
are interesting yet challenging. Both the theoretical research and engineering applications will be discussed, and a
series of recently published results will be reported.
Biography: Zidong Wang is currently Professor of Dynamical Systems and Computing at Brunel University, West
London, United Kingdom. Professor Wang's research interests include dynamical systems, signal processing,
bioinformatics, control theory and applications. He has published more than 200 papers in refereed international
journals. He serves as an Associate Editor for 12 international journals including IEEE Transactions on Automatic
Control, IEEE Transactions on Neural Networks, IEEE Transactions on Signal Processing, IEEE Transactions on
Systems, Man, and Cybernetics - Part C, and IEEE Transactions on Control Systems Technology.
Xingfu Zou
University of Western Ontario, Canada
Title: Advantage of discrete neural networks: Co-existence of chaos and stable periodic orbits in
discrete neural networks with delay
Abstract. We show that in very simple discrete neural networks, there may exist large number
of periodic orbits in some regions in the phase space, while in the mean time chaotic behaviours
are also possible in other regions. This seems to reveal an essential difference between
“discrete” and “continuous”, and may suggest possible applications to design of multiple purpose networks.
Biography: Dr. Xingfu Zou is a full professor in the department of applied mathematics at the University of
Western Ontarion. His research areas are dynamical systems and mathematical biology including the dynamics of
neural networks. He has published more than 100 papers in refereed journals, and is currently a co-chief-editor of
the journal Dynamical Systems and Differential Equations (Springer) and associate editors for several other journals.
Among the honors ane awards he has received are a Petro-Canada Young Innovator Award (Canada, 2002),
Premier's Research Excellence Award (Ontario, Canada, 2005), and Distinguished Research Professorship (UWO's
Faculty of Science, 2011).
26
ICONIP 2012
Panelists
Shunichi Amari: Dr. Amari earned his Ph. D. from the University of Tokyo. After that, he
worked as an Associate Professor at Kyushu University and the University of Tokyo, and then a
Full professor at the University of Tokyo, and is now Professor-Emeritus. He served as Director
of RIKEN Brain Science Institute for five years, and is now its senior advisor. He has been
engaged in research in wide areas of mathematical engineering, in particular, mathematical
foundations of neural networks, including statistical neurodynamics, dynamical theory of neural
fields, associative memory, self-organization, and general learning theory. Another main subject
of his research is information geometry initiated by himself, which provides a new powerful method to information
sciences and neural networks.
Dr. Amari served as President of Institute of Electronics, Information and Communication Engineers, Japan and
President of International Neural Networks Society. He received Emanuel A. Piore Award and Neural Networks
Pioneer Award from IEEE, the Japan Academy Award, Gabor Award from INNS, Caianiello Award, and C&C
award, among many others. He is a Fellow of IEEE.
Leon Chua: Dr. Chua received his MS and Ph. D. degrees from the Massachusetts Institute of
Technology and the University of Illinois at Champaign-Urbana, respectively. He has been a
professor at the University of California, Berkeley since 1971. In 2011, Prof. Chua was
appointed a Distinguished Professor at the Technical University of Munich. His research
interests include cellular neural/nonlinear networks, nonlinear circuits and systems, nonlinear
dynamics, bifurcation and chaos. He has published more than 500 papers. He is the Honorary
Founding Editor-in-Chief of International Journal of Bifurcation and Chaos. Considered to be the
“father of nonlinear circuit theory and cellular neural networks”, he is also the inventor and namesake of “Chua's
circuit” and was the first to conceive the theories behind, and postulate the existence of, the solid-state memristor.
Thirty-seven years after he predicted its existence, a working solid-state memristor was created by a team led by R.
Stanley Williams at Hewlett Packard.
He received many awards including the first recipient of the Gustav Kirchhoff Award, and the Guggenheim Fellow
award, IEEE Neural Networks Pioneer Award. He has been a Fellow of IEEE since 1974. He was awarded 7 patents
and 13 Honorary doctorates and was elected a foreign member of the Academia Europaea, and of the Hungarian
Academy of the Sciences.
Robert Desimone: Dr. Desimone studies the brain mechanisms that allow us to focus our attention
on a specific task while filtering out irrelevant distractions. Our brains are constantly bombarded
with sensory information. The ability to distinguish relevant information from irrelevant
distractions is a critical skill, one that is impaired in many brain disorders. By studying the visual
system of humans and animals, Dr. Desimone has shown that when we attend to something
specific, neurons in certain brain regions fire in unison -- like a chorus rising above the noise --
allowing the relevant information to be ‘heard’ more efficiently by other regions of the brain.
Dr. Desimone is director of the McGovern Institute and the Doris and Don Berkey Professor in the Department of
Brain and Cognitive Sciences. Prior to joining the McGovern Institute in 2004, he was director of the Intramural
Research Program at the National Institutes of Mental Health, the largest mental health research center in the world.
He is a member of the National Academy of Sciences and the American Academy of Arts and Sciences and a
recipient of numerous awards, including the Troland Prize of the National Academy of Sciences, and the Golden
Brain Award of the Minerva Foundation.
27
ICONIP 2012
Stephen Grossberg: Dr. Grossberg is Wang Professor of Cognitive and Neural Systems and
Professor of Mathematics, Psychology, and Biomedical Engineering at Boston University. He has
published over 500 research articles, 17 books or journal special issues, and has 7 patents. He
founded and was first President of the International Neural Network Society (INNS). He founded
the Society's official journal, Neural Networks. Dr. Grossberg has also served as an editor for 30
journals. He was general chairman of the IEEE First International Conference on Neural
Networks and played a key role in organizing the first annual meeting of INNS, whose fusion led
to the International Joint Conference on Neural Networks (IJCNN). He founded the Department of Cognitive and
Neural Systems at Boston University, which he built into a leading institution for advanced training in biological
neural networks and neuromorphic technology. He is the founder and Director of the Center for Adaptive Systems,
which he built into one of the world's leading academic research institutes in computational neuroscience and neural
network technology. His year-long lecture series at MIT Lincoln Laboratory on neural network technology
motivated the laboratory to initiate the national DARPA Neural Network Study in 1987. He organized and is
founding Director of the NSF Center of Excellence for Learning in Education, Science, and Technology.
Dr. Grossberg won the 1991 IEEE Neural Network Pioneer Award, the 1992 INNS Leadership Award, the 1992
Boston Computer Society Thinking Technology Award, the 2000 Information Science Award of the Association for
Intelligent Machinery, the 2002 Charles River Laboratories prize of the Society for Behavioral Toxicology, and the
2003 INNS Helmholtz Award. He is a 1991 member of the Memory Disorders Research Society, a 1994 Fellow of
the American Psychological Association, a 1996 member of the Society of Experimental Psychologists, a 2002
Fellow of the American Psychological Society, a 2005 IEEE Fellow, a 2008 Inaugural Fellow of the American
Educational Research Association, and a 2012 INNS Fellow.
Michael I. Jordan: Dr. Jordan is the Pehong Chen Distinguished Professor in the Department of
Electrical Engineering and Computer Science and the Department of Statistics at the University
of California, Berkeley. His research in recent years has focused on Bayesian nonparametric
analysis, probabilistic graphical models, spectral methods, kernel machines and applications to
problems in statistical genetics, signal processing, computational biology, information retrieval
and natural language processing.
Dr. Jordan is a member of the National Academy of Sciences, a member of the National
Academy of Engineering and a member of the American Academy of Arts and Sciences. He is a Fellow of the
American Association for the Advancement of Science. He has been named a Neyman Lecturer and a Medallion
Lecturer by the Institute of Mathematical Statistics. He is a Fellow of the ACM,the IMS, the IEEE, the AAAI and
the ASA.
Derong Liu: Dr. Derong Liu received the Ph. D. degree in electrical engineering from the
University of Notre Dame in 1994. Dr. Liu was a Staff Fellow with General Motors Research
and Development Center, Warren, MI, from 1993 to 1995. He was an Assistant Professor in the
Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken,
NJ, from 1995 to 1999. He joined the University of Illinois at Chicago in 1999, and became a
Full Professor of electrical and computer engineering and of computer science in 2006. He was
selected for the “100 Talents Program” by the Chinese Academy of Sciences in 2008. He has
published 10 books. Dr. Liu has been an Associate Editor of several IEEE publications.
Currently, he is the Editor-in-Chief of the IEEE Transactions on Neural Networks and Learning Systems, and an
Associate Editor of the IEEE Transactions on Control Systems Technology. He was an elected AdCom member of
the IEEE Computational Intelligence Society (2006-2008). He received the Faculty Early Career Development
(CAREER) award from the National Science Foundation (1999), the University Scholar Award from University of
Illinois (2006-2009), and the Overseas Outstanding Young Scholar Award from the National Natural Science
Foundation of China (2008). He is a Fellow of the IEEE.
28
ICONIP 2012
Michel Verleysen: Dr. Michel Verleysen is Full Professor at the Université catholique de
Louvain, and Honorary Research Director of the Belgian F.N.R.S. (National Fund for Scientific
Research). He was an invited professor at the Swiss E.P.F.L. (Ecole Polytechnique Fédérale de
Lausanne, Switzerland) in 1992, at the Université d'Evry Val d'Essonne (France) in 2001, and at
the Université ParisI-Panthéon-Sorbonne from 2002 to 2012, respectively. He is editor-in-chief
of the Neural Processing Letters journal (published by Springer), chairman of the annual ESANN
conference (European Symposium on Artificial Neural Networks, Computational Intelligence and
Machine Learning), past associate editor of the IEEE Trans. on Neural Networks journal, and member of the
editorial board and program committee of several journals and conferences on neural networks and learning. He was
the chairman of the IEEE Computational Intelligence Society Benelux chapter (2008-2010), and member of the
executive board of the European Neural Networks Society (2005-2010). He is author or co-author of more than 250
scientific papers in international journals and books or communications to conferences with reviewing committee.
He is the co-author of the scientific popularization book on artificial neural networks in the series “Que Sais-Je?”, in
French, and of the “Nonlinear Dimensionality Reduction” book published by Springer in 2007.
DeLiang Wang: Dr. DeLiang Wang received the B.S. degree in 1983 and the M.S. degree in
1986 from Peking (Beijing) University, Beijing, China, and the Ph.D. degree in 1991 from the
University of Southern California, Los Angeles, CA, all in computer science. From July 1986 to
December 1987 he was with the Institute of Computing Technology, Academia Sinica, Beijing.
Since 1991, he has been with the Department of Computer Science & Engineering and the
Center for Cognitive Science at The Ohio State University, Columbus, OH, where he is a
Professor. From October 1998 to September 1999, he was a visiting scholar in the Department
of Psychology at Harvard University, Cambridge, MA. From October 2006 to June 2007, he was a visiting scholar
at Oticon A/S, Denmark. Dr. Wang's research interests include machine perception and neurodynamics. Among his
recognitions are the Office of Naval Research Young Investigator Award in 1996, the 2005 Outstanding Paper
Award from IEEE Transactions on Neural Networks, and the 2008 Helmholtz Award from the International Neural
Network Society. He is an IEEE Fellow, and currently serves as Co-Editor-in-Chief of Neural Networks.
Xin Yao: Dr. Xin Yao is a Chair (Professor) of Computer Science and the Director of CERCIA
(Centre of Excellence for Research in Computational Intelligence and Applications) at the
University of Birmingham, UK. He is an IEEE Fellow and a Distinguished Lecturer of IEEE
Computational Intelligence Society (CIS). He won the 2001 IEEE Donald G. Fink Prize Paper
Award, 2010 IEEE Transactions on Evolutionary Computation Outstanding Paper Award, 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 won the prestigious Royal Society Wolfson Research Merit Award in 2012 and was selected to receive the 2013
IEEE CIS Evolutionary Computation Pioneer Award. He was the Editor-in-Chief (2003-2008) of IEEE Transactions
on Evolutionary Computation and is an Associate Editor or Editorial Member of more than ten other journals. He
has been invited to give 65 keynote/plenary speeches at international conferences. His major research interests
include evolutionary computation and neural network ensembles. He has more than 400 refereed publications.
According to Google Scholar, his H-index is 56.
29
ICONIP 2012
ICONIP 2012 Technical Program
Sunday, 11 November
10:00-19:30 Registration
13:30-18:00 Desert Safari Trip (meeting point: Ground Floor, Main Entrance of Renaissance Hotel)
18:00-19:30 Welcome Reception
Monday, 12 November
Mon., Nov. 12
09:00-9:30 Opening Ceremony
Speaker: Dr. Mohammed Bin Saleh Al-Sada, His
Excellency, Minister of Energy & Industry, Qatar
Speaker: Dr. Mark H. Weichold, Dean and CEO, Texas
A&M University at Qatar
Room: Al Areen
Chair: Tingwen Huang
09:35-10:25 Brain, Stochastic World and Information Geometry
Keynote Speaker: Shunichi Amari
Room: Al Areen
Chair: Nikola Kssabov
10:25-10:50 Coffee Break
10:50-11:40 Memristor, Hodgkin Huxley, and Edge of Chaos
Keynote Speaker: Leon Chua
Room: Al Areen
Chair: Xin Yao
11:40-12:30 Prefrontal Control of Visual Attention
Keynote Speaker: Robert Desimone
Room: Al Areen
Chair: Xin Yao
12:30-13:30 Lunch
13:30-14:20 Neural dynamics of invariant object learning, attention,
recognition, and search
Keynote speaker: Stephen Grossberg
Room: Al Areen
Chair: Deliang Wang
14:20-15:10 Divide-and-Conquer and Statistical Inference for Big Data Keynote speaker: Michael I. Jordan
Room: Al Areen
Chair: Deliang Wang
15:10-15:40 Coffee Break
15:40-16:20 Human Face Recognition Under Illumination Variation
Plenary speaker: Majid Ahmadi
Room: Al Areen
Chair: Leszek Rutkowski
16:20-17:00 Mapping, Learning and Mining of Brain Spatiotemporal
Data with 3D Evolving Spiking Neurogenetic Models
Plenary speaker: Nikola Kasabov
Room: Al Areen
Chair: Leszek Rutkowski
17:00-17:40 Neural Network Approaches to Nonlinear and
Robust Model Predictive Control
Plenary speaker: Jun Wang
Room: Al Areen
Chair: Leszek Rutkowski
17:50-18:40 Panel 2: How to write better technical papers for
international journals in computational intelligence?
Panelists: Derong Liu, Michel Verleysen,
Deliang Wang, Xin Yao
Room: Al Areen
Chair: Amir Hussain
17:50-21:30 Dinner Shanghai Garden in City
Center Mall
19:00-22:00 APNNA Governing Board Meeting Al Areen 5
30
ICONIP 2012
Tuesday, 13 November
Mon., Nov. 13
08:00-8:40
Searching for Undirected Networks with
Best Synchronizability
Plenary speaker: Guanrong (Ron) Chen
Room: Al Areen
Chair: Majid Ahmadi
08:40-9:20 Complex Synchronization and Recurrence Analyses
Plenary speaker: Juergen Kurths
Room: A1 Areen
Chair: Majid Ahmadi
9:20-10:00 Inference by matrix factorizations
Plenary speaker: Erkki Oja
Room: Al Areen
Chair: Majid Ahmadi
10:00-10:30 Coffee Break
10:30-11:10 Distributed Fault Diagnosis in Uncertain
Dynamical Systems
Plenary speaker: Marios M. Polycarpou
Room: Al Areen
Chair: Derong Liu
11:10-11:50 On Stream Data Mining - New Results and Challenges
Plenary speaker: Leszek Rutkowski
Room: Al Areen
Chair: Derong Liu
11:50-12:30 The CLARION Cognitive Architecture: Motivation,
Personality, and Social Interaction
Plenary speaker: Ron Sun
Room: Al Areen
Chair: Derong Liu
12:30-13:30 Lunch
13:30-15:30 Panel 1: Challenges and Promises in Computational
Intelligence
Panelists: Shunichi Amari, Leon Chua, Robert
Desimone, Stephen Grossberg, Michael I. Jordan
Room: A1 Areen
Chair: Ron Sun
Invited Session, Parallel Oral Sessions and Poster Sessions
15:30-16:00 Coffee Break
16:00-18:00 Invited Session, Parallel Oral Sessions and Poster Sessions
19:00-22:00 Banquet Al Areen
Wednesday, 14 November
8:00-10:00 Invited Sessions, Parallel Oral Sessions, Poster Sessions, and Workshop
10:00-10:30 Coffee Break
10:30-12:30 Invited Sessions, Parallel Oral Sessions, Poster Sessions, and Workshop
12:30-13:40 Lunch
13:40-15:40 Invited Sessions, Parallel Oral Sessions, Poster Sessions
15:40-16:10 Coffee Break
16:10-17:40 Invited Sessions, Parallel Oral Sessions, Poster Sessions
17:50-21:30 TBA
Thursday, 15 November
9:00-13:30 Desert Safari Trip (meeting point: Ground Floor, Main Entrance of Renaissance Hotel)
9:00-16:30 Buses to several travel sites including Souq Waqif, Museum of Islamic Art, Pearl of Qatar
from 9:00-16:30, buses to airport at 16:30 (meeting point: Ground Floor, Main Entrance of
Renaissance Hotel)
31
ICONIP 2012
13:30-15:30 Tuesday, 13 November Invited Session and Oral Sessions
Tue.
Nov 13
I1 Invited Session
Room: Al Areen 5
Chair:Yiran Chen ID
13:30-14:00 I101 A Just-In-Time Learning strategy for Adaptive Classifiers Cesare Alippi
14:00-14:30 I102 Coordination of complex networks Tianping Chen
14:30-15:00 I103 Centaur: Bio-inspired Ultra Low-Power Hybrid Embedded
Computing Engine Beyond One TeraFlops/Watt
Yiran Chen
15:00-15:30 I104 Universal Neural Controllers for General Nonlinear Systems Gary Feng
Tue.
Nov 13
TA1a Special Session
Computational Models of Cognitive Functions
Room: Al Majida
Chair: Soo-Young Lee ID
13:30-13:45 TA1a1 Determining effective connectivity from fMRI data using a
Gaussian Dynamic Bayesian Network
Xia Wu, Juan Li and Li Yao 56
13:45-14:00 TA1a2 Incremental Face Recognition: Hybrid Approach Using Short-
Term Memory and Long-Term Memory
Sangwook Kim, Rammohan
Mallipeddi and Minho Lee
175
14:00-14:15 TA1a3 Apparent Volitional Behavior Selection Based on Memory
Predictions
Jun-Cheol Park, Jae Hyeon
Yoo, Juhyeon Lee and Dae-
Shik Kim
411
14:15-14:30 TA1a4 Psychophysiological Evaluation of Task Complexity and
Cognitive Performance in a Sudoku HCI Experiment
William Mount, Deborah
Tucek and Hussein Abbass
502
14:30-14:45 TA1a5 Supervised Isomap Based on Pairwise Constraints Jian Cheng, Can Cheng and
Yi-Nan Guo
337
14:45-15:00 TA1a6 Modelling Temporal Aspects of Situation Awareness Tibor Bosse, Robbert-Jan
Merk and Jan Treur
358
15:00-15:15 TA1a7 The Brain’s Sequential Parallelism: Perceptual Decision-
Making and Early Sensory Responses
Tobias Brosch and Heiko
Neumann
39
15:15-15:30 TA1a8 Cross-Camera Feature Level Fusion for Person Identification
in Surveillance Videos
Emdad Hossain and Girija
Chetty
426
Tue.,
Nov 13
TA1b Regular Session
Signal Processing and Image Processing I
Room: Al Anood
Chair: Xinbo Gao ID
13:30-13:45 TA1b1 Efficient Non-Linear Filter for Impulse Noise Removal in
Document Images
Ali Awad 13
13:45-14:00 TA1b2 The Elastic Net as Visual Category Representation:
Visualisation and Classication
Dror Cohen and Andrew
Paplinski
97
14:00-14:15 TA1b3 Sound-based Ranging System in Greenhouse Environment
with Multipath Effect Compensation Using Artificial Neural
Network
Slamet Widodo, Tomoo
Shiigi, Naing Min Than,
Yuichi Ogawa and Naoshi
Kondo
144
14:15-14:30 TA1b4 Analog Neural Network Approach for Source Localization
using Time-of-Arrival Measurements
Chi Sing Leung and H.C. So 179
14:30-14:45 TA1b5 Color Fractal Structure Model for Reduced-Reference
Colorful Image Quality Assessment
Lihuo He, Dongxue Wang,
Xuelong Li, Dacheng Tao,
Xinbo Gao and Fei Gao
316
14:45-15:00 TA1b6 Entropy Based Image Semantic Cycle for Image
Classification
Hongyu Li, Junyu Niu and
Lin Zhang
476
15:00-15:15 TA1b7 Local Structure Divergence Index for Image Quality
Assessment
Fei Gao, Dacheng Tao,
Xuelong Li, Xinbo Gao and
Lihuo He
315
32
ICONIP 2012
Tue.
Nov 13
TA1c Regular Session
Data Clustering
Room: Al Jazi
Chair: Shaoning Pang and
Radu-Tudor Ionescu
ID
13:30-13:45 TA1c1 Improved BTC Algorithm for Gray Scale Images Using k-
Means Quad Clustering
Jayamol Mathews, Madhu S.
Nair and Liza Jo
36
13:45-14:00 TA1c2 Generalized Agglomerative Fuzzy Clustering Kiatichai Treerattanapitak and
Chuleerat Jaruskulchai
48
14:00-14:15 TA1c3 A Novel Self-Adaptive Clustering Algorithm for Dynamic
Data
Ming Liu, Lei Lin, Lili Sha,
and Chengjie Sun
50
14:15-14:30 TA1c4 GPU-based Biclustering for Neural Information Processing Alan W.Y. Lo, Benben Liu
and Ray C.C. Cheung
118
14:30-14:45 TA1c5 Biclustering and Subspace Learning with Regularization for
Financial Risk Analysis
Bernardete Ribeiro and Ning
Chen
193
14:45-15:00 TA1c6 Composite Data Mapping for Spherical GUI Design:
Clustering of Must-Watch and No-Need TV Programs
Masaya Maejima, Ryota
Yokote and Yasuo
Matsuyama
239
15:00-15:15 TA1c7 r-Anonymized Clustering Wenye Li 347
15:15-15:30 TA1c8 Clustering Based on Rank Distance with Applications on
DNA
Liviu Petrisor Dinu, Radu-
Tudor Ionescu
234
Tue.,
Nov 13
TA1d Regular Session
Support Vector Machines
Room:Al Ahood
Chair: Tao Ban ID
13:30-13:45 TA1d1 Consonantal Recognition using SVM and a Hierarchical
Decision Structure based in the Articulatory Phonetics
Adriano De Andrade
Bresolinand Hermes Irineu
Del Monego
580
13:45-14:00 TA1d2 On the Optimization of Multiclass Support Vector Machine D
edicated to Speech Recognition
Freha Mezzoudj and Assia
Benyettou
20
14:00-14:15 TA1d3 Multiple Outlooks Learning with Support Vector Machines Yinglu Liu, Xu-Yao Zhang,
Kaizhu Huang, Xinwen Hou
and Cheng-Lin Liu
108
14:15-14:30 TA1d4 Improving Support Vector Machine Using a Stochastic Local
Search for Classification in Data Mining
Messaouda Nekkaa and Dalila
Boughaci
134
14:30-14:45 TA1d5 Deterministic Annealing Multi-Sphere Support Vector Data
Description
Trung Le, Dat Tran, Wanli
Ma and Dharmendra Sharma
164
14:45-15:00 TA1d6 Wavelet Transform Based Consonant - Vowel (CV)
Classification Using Support Vector Machines
Thasleema T.M. and
Narayanan N.K.
195
15:00-15:15 TA1d7 SVM-based Just-in-Time Adaptive Classifiers Cesare Alippi, Li Bu and
Dongbin Zhao
608
33
ICONIP 2012
13:30-15:30 Tuesday, 13 November Poster Session
Tue.,
Nov 13
TA1P Poster Session Outside Al Areen ball room ID
TA1P01 Neural network learning for blind source separation with
application in dam safety monitoring
Popescu Theodor Dan 4
TA1P02 Estimating Neural Firing Rates: An Empirical Bayes
Approach
Shinsuke Koyama 52
TA1P03 Assessment of Financial Risk Prediction Models with Multi-
Criteria Decision Making Methods
Jose Salvador Sanchez,
Vicente García and Ana Isabel
Marqués
64
TA1P04 Improving Risk Predictions by Preprocessing Imbalanced
Credit Data
Vicente García, Ana Isabel
Marqués and Jose Salvador
Sanchez
65
TA1P05 Centroid Neural Network with Simulated Annealing and Its
Application to Color Image Segmentation
Do-Thanh Sang, Dong-Min
Woo and Dong-Chul Park
7
TA1P06 Petrophysical Parameters Estimation from Well-logs Data
Using Multilayer Perceptron and Radial Basis Function
Neural Networks
Leila Aliouane1, Sid-Ali
Ouadfeul, Noureddine
Djarfour, Amar Boudella
21
TA1P07 Lithofacies Classification Using the Multilayer Perceptron
(MLP) and the Self-Organizing (MAP) Neural Networks
Sid-Ali Ouadfeul, Leila
Aliouane
22
TA1P08 Time Series Prediction Method Based on LS-SVR with
Modified Gaussian RBF
Yangming Guo, Xiaolei Li,
Guanghan Bai and Jiezhong
Ma
23
TA1P09 Study on Rasterization Algorithm for Graphics Acceleration
System
Xuzhi Wang, Wei Xiong,
Xiang Feng, Shuai Yu and
Hengyong Jiang
26
TA1P10 Optimization of a Neural Network for Computer Vision based
Fall Detection with Fixed-Point Arithmetic
Christoph Sulzbachner, Martin
Humenberger, Agoston Srp,
Ferenc Vajda
42
TA1P11 Customer Relationship Management using Partial Focus
Feature Reduction
Yan Tu and Zijiang Yang 44
TA1P12 Double Approximate Identity Neural Networks Universal
Approximation in Real Lebesgue Spaces
Zarita Zainuddin and Saeed
Panahian Fard
314
TA1P13 An Improved Method of Identification Based on Thermal
Palm Vein Image
Ran Wang, Guoyou Wang,
Zhong Chen and Jianguo Liu
27
TA1P14 Gabor-Based Novel Local, Shape and Color Features for
Image Classification
Atreyee Sinha, Sugata
Banerji and Chengjun Liu
241
34
ICONIP 2012
16:00-18:00 Tuesday, 13 November Invited Session and Oral Sessions
Tue.
Nov 13
I2 Invited Session
Room: Al Areen 5
Chair: Daisuke Inoue ID
16:00-16:30 I201 Canonical Duality and Triality: Unified Understanding for
Modeling and Simulation of Complex Systems with
Applications in Neural Information Processing
David Gao
16:30-17:00 I201 Towards Cognitive Control of Autonomous Systems Amir Hussain
17:00-17:30 I203 Fight against Emerging Security Threats with Data Mining
Technologies
Daisuke Inoue
Tue.,
Nov 13
TA2a Special Session
Evolutionary Computation in Networks
Room: Al Majida
Chair: Maolin Tang ID
16:00-16:15 TA2a1 Constrained Multi-Objective Optimization using a Quantum
Behaved Particle Swarm
Heyam Al Baity, Souham
Meshoul and Ata Kaban
354
16:15-16:30 TA2a2 A Genetic Algorithm Solution for the Operation of Green
LTE Networks with Energy and Environment Considerations
Hakim Ghazzai, Elias
Yaacoub, Mohamed-Slim
Alouini and Adnan Abu-
Dayya
442
16:30-16:45 TA2a3 A Bio Inspired Estimation of Distribution Algorithm for
Global Optimization
Omar S. Soliman and Aliaa
Rassem
613
16:45-17:00 TA2a4 A Bio Inspired Fuzzy K-Modes Clustering Algorithm Omar S. Soliman, Doaa Saleh
and Samaa Rashwan
624
17:00-17:15 TA2a5 DPSO Based on Random Particle Priority Value and
Decomposition Procedure as A Searching Strategy for the
Evacuation Vehicle Routing Problem
Marina Yusoff, Junaidah
Ariffin and Azlinah Mohamed
631
17:15-17:30 TA2a6 Canonical Duality Theory and Algorithm for Solving
Challenging Problems in Network Optimisation
Ning Ruan and David Yang
Gao
649
17:30-17:45 TA2a7 Energy-efficient Virtual Machine Placement in Data Centers
by Genetic Algorithm
Grant Wu, Maolin Tang, Yu-
Chu Tian and Wei Li
246
Tue.,
Nov 13
TA2b Special Session
Applied Soft Computing in Medical Informatics
Room: Al Sidra
Chair: Uvais Qidwai ID
16:00-16:15 TA2b1 Artificial Bees Colony Optimized Neural Network Model for
ECG signals classification
Slami Saadi, Maamar
Bettayeb, Abderrezak
Guessoum and M. K.
Abdelhafidi
302
16:15-16:30 TA2b2 Parallel Support Vector Configuration for Identification of
Fast Independent Components in Morphological Patterns
Derived by Cardiovasographic Analysis on the Radial Pulse
S.H. Karamchandani, P.
Mahadesh, D.G. Khairnar,
G.D. Jindal, S.N. Merchant
and U.B. Desai
487
16:30-16:45 TA2b3 Fuzzy Model for Detection and Estimation the Degree of
Autism Spectrum Disorder
Wafaa Shams, Abdul Wahab
and Uvais Qidwai
323
16:45-17:00 TA2b4 Detection Different Tasks using EEG-Source-Temporal
Features
Wafaa Shams, Abdul Wahab
and Uvais Qidwai
324
17:00-17:15 TA2b5 Performance Evaluation of Securing TCP and UDP healthcare
traffic in IEEE 1451 compliant Healthcare Infrastructure
Junaid Chaudhry and Uvais
Qidwai
355
17:15-17:30 TA2b6 Fuzzy Classification-based Control of Wheelchair Using EEG
Data to Assist People with Disabilities
Uvais Qidwai and Mohamed
Shakir
420
35
ICONIP 2012
Tue.,
Nov 13
TA2c Regular Session
Applications
Room:Al Jazi
Chair: Iqbal Gondal and
Shuichi Kurogi
ID
16:00-16:15 TA2c1 Fusion of Multiple Texture Representations for Palmprint
Recognition Using Neural Networks
Galal M. Binmakhashen and
El-Sayed M. El-Alfy
425
16:15-16:30 TA2c2 Abductive Neural Network Modeling for Hand Recognition
Using Geometric Features
El-Sayed M. El-Alfy, Radwan
Abdel-Aal and Zubair Baig
522
16:30-16:45 TA2c3 Moments of Predictive Deviations as Ensemble Diversity
Measures to Estimate the Performance of Time Series
Prediction
Kohei Ono, Shuichi Kurogi
and Takeshi Nishida
62
16:45-17:00 TA2c4 Tracking Property of UMDA in Dynamic Environment by
Landscape Framework
Ran Long, Liangqi Gong, Bo
Yuan, Ping Ao and Qingsheng
Ren
265
17:00-17:15 TA2c5 Unitary Anomaly Detection for Ubiquitous Safety in Machine
Health Monitoring
Muhammad Amar, Iqbal
Gondal and Campbell Wilson
340
17:15-17:30 TA2c6 Smart phone Based Machine Condition Monitoring System M. Farrukh Yaqub, Iqbal
Gondal and Xueliang Hua
450
17:30-17:45 TA2c7 Robust Stability Analysis of Hybrid BAM Neural Networks
with Time Delays
Ruya Samli, Eylem Yucel
Demirel and Sabri Arik
63
Tue.,
Nov 13
TA2d Regular Session
Mixture Models and Kernel Methods
Room:Al Sidra
Chair: Anam Tariq ID
16:00-16:15 TA2d1 Nonparametric Localized Feature Selection via a Dirichlet
Process Mixture of Generalized Dirichlet Distributions
Wentao Fan and Nizar
Bouguila
35
16:15-16:30 TA2d2 Approximation of Feature Vectors in Nonnegative Matrix
Factorization with Gaussian Radial Basis Functions
Rafal Zdunek 510
16:30-16:45 TA2d3 Maximal Margin Kernel Learning Vector Quantisation for
Binary Classification
Trung Le, Dat Tran, Tuan
Hoang and Dharmendra
Sharma
165
16:45-17:00 TA2d4 Validation Based Sparse Gaussian Processes for Ordinal
Regression
P.K. Srijith, Shirish Shevade
and S. Sundararajan
321
17:00-17:15 TA2d5 On the Objective Function and Learning Algorithm for
Concurrent Open Node Fault
Chi Sing Leung, Pui Fai Sum
and Kai-Tat Ng
177
17:15-17:30 TA2d6 Multi-task Learning using Shared and Task Specific
Information
P.K. Srijith and Shirish
Shevade
114
17:30-17:45 TA2d7 Hierarchical Parallel PSO-SVMbased Subject-independent
Sleep Apnea Classification
Yashar Maali and Adel Al-
Jumaily
468
17:45-18:00 TA2d8 A Gaussian Mixture Model Based System for Detection of
Macula in Fundus Images
Anam Tariq 33
36
ICONIP 2012
16:00-18:00 Tuesday, 13 November Poster Session
Tue.,
Nov 13
TA2P Poster Session Outside Al Areen ball room ID
TA2P01 Bayesian Modeling of Visual Attention Jinhua Xu 71
TA2P02 Optimization of SIRMs Fuzzy Model Using Lukasiewicz
Logic
Takashi Mitsuishi, Takanori
Terashima and Yasunari
Shidama
74
TA2P03 A Human-Simulated Immune Evolutionary Computation
Approach
Gang Xie, Hong-Bo Guo, Yu-
Chu Tian and Maolin Tang
81
TA2P04 A STPHD-Based Multi-sensor Fusion Method Zhenwei Lu, Lingling Zhao,
Xiaohong Su and Peijun Ma
85
TA2P05 Decoding Cognitive States From Neural Activities of
Somatosensory Cortex
Xiaoxu Kang, Marc
Schieberand Nitish Thakor
87
TA2P06 Cognitive Modelling of Dilution Effects in Visual Search Kleanthis Neokleous, Marios
Avraamides, Costas
Neocleous and Christos
Schizas
88
TA2P07 OMP or BP? A Comparison Study of Image Fusion Based on
Joint Sparse Representation
Yao Yao, Xin Xin and Ping
Guo
91
TA2P08 Vehicle License Plate Localization and License Number
Recognition Using Unit-linking Pulse Coupled Neural
Network
Ya Zhao and Xiaodong Gu 103
TA2P09 Off-Line Handwritten Arabic Word Recognition Using SVMs
with Normalized Poly Kernel
Abdulrahman
Alalshekmubarak, Amir
Hussain and Qiu-Feng Wang
70
TA2P10 Does Social Network always Promote Entrepreneurial
Intentions? Part I: Theoretical model
Xiao Lu and Fan Ming 8
TA2P11 Motivating Retail Marketing Efforts under Fairness Concerns
in Small-world networks: A Multi-Agent Simulation Study
Qingfeng Meng, Jianguo Du
and Zhen Li
67
TA2P12 Hybrid Validation of Handwriting Process Modelling Mohamed Aymen Slim,
Maroua El Kastouri, Afef
Abdelkrim and Mohamed
Benrejeb
68
TA2P13 An Iterative Method for a Class of Generalized Global
Dynamical System Involving Fuzzy Mappings in Hilbert
Spaces
Yunzhi Zou, Xinkun Wu,
Wenbin Zhang and Changyin
Sun
73
TA2P14 DBNs-BLR (MCMC) -GAs-KNN: A Novel Framework of
Hybrid System for Thalassemia Expert System
Patcharaporn Paokanta 242
TA2P15 New Intelligent Interactive Automated Systems for Design of
Machine Elements and Assemblies
Wojciech Kacalak and Maciej
Majewski
132
TA2P16 Evolving Flexible Beta Operator Neural Trees (FBONT) for
Time Series Forecasting
Souhir Bouaziz, Habib Dhahri
and Adel M. Alimi
17
TA2P17 Harmony Search with Multi-Parent Crossover for Solving
IEEE-CEC2011 Competition Problems
Iyad Abu Doush 131
37
ICONIP 2012
08:00-10:00 Wednesday, 14 November Oral Sessions
Wed.
Nov 14
WM1a Regular Session
Evolutional Computing
Room: Al Areen 2
Chair: Eduard Petlenkov ID
08:00-08:15 WM1a1 Application of Genetic Neural Networks for Modeling
of Active Devices
Anwar Jarndal 188
08:15-08:30 WM1a2 Evolutionary Extreme Learning Machine for Ordinal
Regression
David Becerra-Alonso, Mariano
Carbonero-Ruz, Francisco José
Martínez-Estudillo and Alfonso
Carlos Martínez-Estudillo
190
08:30-08:45 WM1a3 ICHEA – A Constraint Guided Search for Improving
Evolutionary Algorithms
Anurag Sharma and Dharmendra
Sharma
219
08:45-09:00 WM1a4 Optimization of Fuzzy Systems Using Group-Based
Evolutionary Algorithm
Jyh-Yeong Chang, Ming-Feng Han
and Chin-Teng Lin
236
09:00-09:15 WM1a5 Improved Differential Evolution via Cuckoo Search
Operator
Pakarat Musigawan, Sirapat
Chiewchanwattana and Khamron
Sunat
357
09:15-09:30 WM1a6 A Quantum-inspired Evolutionary Algorithm for
Optimization Numerical Problems
Maurizio Fiasché 639
09:30-09:45 WM1a7 Evolutionary Design of the Closed Loop Control on
the Basis of NN-ANARX Model Using Genetic
Algoritm
Kristina Vassiljeva, Eduard
Petlenkov and Sven Nomm
501
Wed.,
Nov 14
WM1b Special Session
Co-clustering of Large and High Dimensional Data
Room: Al Areen 1
Chair: Gilles Bisson ID
08:00-08:15 WM1b1 A Sequential Data Mining Method for Modelling
Solar Magnetic Cycles
Kassim Mwitondi, Raeed
Said and Adil Yousif
226
08:15-08:30 WM1b2 Iterative Evolutionary Subspace Clustering Lydia Boudjeloud-Assala and
Alexandre Blansché
327
08:30-08:45 WM1b3 Hybrid Online Non-negative Matrix Factorization for
Clustering of Documents
Vinod Jadhao and M Narasimha
Murty
443
08:45-09:00 WM1b4 A knowledge-driven bi-clustering Method for Mining
Noisy Datasets
Karima Mouhoubi, Lucas Létocart
and Céline Rouveirol
500
09:00-09:15 WM1b5 Statistical Analysis of Arabic Phonemes Used in
Arabic Speech Recognition
Khalid Nahar, Mustafa
Elshafei, Wasfi Al-Khatib, Husni
Al-Muhtaseb and Mansour
Alghamdi
454
09:15-09:30 WM1b6 Discrete-time Hopfield Neural Network Based Text
Clustering Algorithm
Zekeriya Uykan, Murat Can
Ganiz and Cagla Sahinli
464
09:30-09:45 WM1b7 Budgeted Knowledge Transfer for State-wise
Heterogeneous RL Agents
Farbod Farshidian, Zeinab
Talebpour and Majid Nili
Ahmadabadi
331
09:45-10:00 WM1b8 An Architecture to Efficiently Learn Co-Similarities
with Multi-View Datasets
Gilles Bisson and Clément Grimal 171
38
ICONIP 2012
Wed.
Nov 14
WM1c Special Session
Computationally Intelligent Techniques in Processing
Neural Information
Room: Al Areen 4
Chair: Mufti Mahmud and
Armando Pelliccioni
ID
08:00-08:15 WM1c1 Analysis of Alertness Status of Subjects Undergoing
The Cortical Auditory Evoked Potential Hearing Test
Ahmed Al-Ani, Bram Van Dun,
Harvey Dillon and Alaleh Rabie
96
08:15-08:30 WM1c2 Fault Diagnosis of a High-speed Automaton Based on
Structure Vibration Response Analysis
Hongxia Pan, Mingzhi Pan,
Runpeng Zhao and Haifeng Ren
481
08:30-08:45 WM1c3 Application of Sampling Theory to Forecast Ozone by
Neural Network
Armando Pelliccioni and Rossana
Cotroneo
184
08:45-09:00 WM1c4 Load Forecasting Accuracy Through Combination of
Trimmed Forecasts
Saima Hassan, Abbas Khosravi,
Jafreezal Jaafar, and Samir B.
Belhaouari
139
09:00-09:15 WM1c5 RAFNI: Robust Analysis of Functional NeuroImages
with Nonnormal-stable Error
Halima Bensmail, Samreen
Anjum, Othmane Bouhali and
Mohammed Elanbari
515
09:15-09:30 WM1c6 FPGA Implementation of A Cortical Network Based
on the Hodgkin-Huxley Neuron Model
Safa Yaghini Bonabi, Hassan
Asgharian, Reyhaneh Bakhtiari,
Saeed Safari and Majid Nili
Ahmadabadi
203
09:30-09:45 WM1c7 Decoding Network Activity from LFPs: A
Computational Approach
Mufti Mahmud, Davide Travalin
and Amir Hussain
492
Wed.,
Nov 14
WM1d Special Session
Soft Computing for Image Processing: Principles and
Applications
Room: Al Areen 5
Chair: Chu-Kiong Loo ID
08:00-08:15 WM1d1 Rasterization System for Mobile Device Xuzhi Wang, Yangyang Jia, Xiang
Feng, Shuai Yu and Hengyong
Jiang
25
08:15-08:30 WM1d2 Reinforcement of Keypoint Matching by Co-
segmentation in Object Retrieval: Face Recognition
Case Study
Andrzej Sluzek, Mariusz
Paradowski and Duanduan Yang
55
08:30-08:45 WM1d3 An Improved Approach to Super Resolution Based on
PET Imaging
Pei Min Yan and Meng Yang 94
08:45-09:00 WM1d4 Local Patch Dissimilarity for Images Radu-Tudor Ionescu, Liviu P.
Dinu and Marius Popescu
107
09:00-09:15 WM1d5 Image Dehazing Algorithm Based on Atmosphere
Scatters Approximation Model
Zhongyi Hu, Liu Qing, Shenghui
Zhou, Mingjing Huang and Fei
Teng
126
09:15-09:30 WM1d6 One-dimensional-array Millimeter-wave Imaging of
Moving Targets for Security Purpose Based on
Complex-valued Self-organizing Map (CSOM)
Shogo Onojima and Akira Hirose 208
09:30-09:45 WM1d7 Human Posture Recognition with the Stochastic
Cognitive RAM Network
Weng Kin Lai, Imran M.
Khanand George G. Coghill
472
09:45-10:00 WM1d8 Object Recognition Using Sparse Representation of
Overcomplete Dictionary
Chu-Kiong Loo and Ali
Memariani
109
39
ICONIP 2012
Wed.
Nov 14
WM1e Regular Session
Bioinformatics and Biomedical Applications
Room: Al Areen 6
Chair: Abdolhossein Sarrafzadeh ID
08:00-08:15 WM1e1 Hybrid Approach for Diagnosing Thyroid, Hepatitis,
and Breast Cancer Based on Correlation Based
Feature Selection and Naïve Bayes
Mohammad Ashraf, Girija Chety,
Dat Tran and Dharmendra Sharma
257
08:15-08:30 WM1e2 Aspect-Oriented Design and Implementation of
Secure Agent Communication System
Ozgur Koray Sahingoz and Emin
Kugu
199
08:30-08:45 WM1e3 FusGP: Bayesian Co-Learning of Gene Regulatory
Networks and Protein Interaction Networks
Nizamul Morshed, Madhu
Chetty and Vinh Nguyen
342
08:45-09:00 WM1e4 Feature Salience for Neural Networks: Comparing
Algorithms
Theodor Heinze, Martin Von
Loewis and Andreas Polze
359
09:00-09:15 WM1e5 RST-DCA: A Dendritic Cell Algorithm Based on
Rough Set Theory
Zeineb Chelly and Zied Elouedi 410
09:15-09:30 WM1e6 Analysis of Genetic Disease Hemophilia B by Using
Support Vector Machine
Kenji Aoki, Kunihito Yamamori,
Makoto Sakamoto and Hiroshi
Furutani
434
09:30-09:45 WM1e7 Immune Algorithm for Bitmap Join Indexes Amina Gacem and Kamel
Boukhalfa
485
Wed.,
Nov 14
WM1f Regular Session
Neural Applications
Room: Al Majida
Chair: Chaojie Li ID
08:00-08:15 WM1f1 Impulsive Synchronization of State Delayed Discrete
Complex Networks with Switching Topology
Chaojie Li, David Gao and Chao
Liu
54
08:15-08:30 WM1f2 Adaptive Neural Networks Control on Ship's Linear-
Path following
Wei Li, Jun Ning, Zhengjiang Liu
and Tieshan Li
427
08:30-08:45 WM1f3 Annotating Words Using WordNet Semantic Glosses Julian Szymanski and Wlodzislaw
Duch
161
08:45-09:00 WM1f4 Cost-Effective Single-Camera Multi-Car Parking
Monitoring and Vacancy Detection towards Real-
world Parking Statistics and Real-time Reporting
Katy Blumer, Hala Halaseh, Mian
Ahsan, Haiwei Dong and Nikolaos
Mavridis
467
09:00-09:15 WM1f5 Air Quality Monitoring and Prediction System using
Machine-to-Machine Platform
Abdullah Kadri, Khaled
Shaban, Elias Yaacoub and Adnan
Abu-Dayya
478
09:15-09:30 WM1f6 Robot Dancing: Adapting Robot Dance to Human
Preferences
Qinggang Meng, Ibrahim Thoelley
and Paul Chung
498
09:30-09:45 WM1f7 SNEOM: A Sanger Network Based Extended Over-
Sampling Method. Application to Imbalanced
Biomedical Datasets
José Manuel Martínez García,
Carmen Paz Suárez Araujo and P.
García Baez
517
09:45-10:00 WM1f8 Automated Segmentation and Tracking of Dynamic
Focal Adhesions in Time-Lapse Fluorescence
Microscopy
Guannan Li and Nasir Rajpoot 565
40
ICONIP 2012
Wed. Nov 14
WM1g Regular Session Pattern Recognition Room: Al Ahood
Chair: Jonathan H. Chan ID
08:00-08:15 WM1g1 Modelling Energy Use and Fuel Consumption in Wheat Production Using Indirect Factors and Artificial Neural Networks
Majeed Safa and Sandhya Samarasinghe
31
08:15-08:30 WM1g2 Obtaining Single Document Summaries Using Latent Dirichlet Allocation
Karthik N and M Narasimha Murty 101
08:30-08:45 WM1g3 A System for Offline Character Recognition Using Auto-encoder Networks
Sagar Dewan and Srinivasa Chakravarthy
115
08:45-09:00 WM1g4 Multistep Speaker Identification Using Gibbs-Distribution-Based Extended Bayesian Inference for Rejecting Unregistered Speaker
Yuta Mizobe, Shuichi Kurogi, Tomohiro Tsukazaki and Takeshi Nishida
228
09:00-09:15 WM1g5 A single Neuron Model for Pattern Classification B. Chandra and K.V. Naresh Babu 615 09:15-09:30 WM1g6 An Improved NN Training Scheme Using a Two-
Stage LDA Features for Face Recognition Behzad Bozorgtabar and Roland Goecke
632
09:30-09:45 WM1g7 Pathway-based Multi-class Classification of Lung Cancer
Worrawat Engchuan and Jonathan H. Chan
669
Wed., Nov 14
WM1h Special Session Computer Systems and Applications I Room: Al Jazi
Chair: Jihad Mohamad Jaam ID
08:00-08:15 WM1h1 The Impact of Accessible Technologies Some Risks Ahead and Issues of Localization
David Banes
08:15-08:30 WM1h2 Multimedia Educational Content for Saudi Deaf Yahya Elhadj 146 08:30-08:45 WM1h3 Neural and Speech Indicators of Cognitive Load for
Sudoku Game Interfaces Deborah Tuček, William M. Mount and Hussein Abbass
181
08:45-09:00 WM1h4 From e-learning to m-learning: Context- aware CBR System
O. C. Henda, Zulal Sevkli Aise and Bousbahi Fatiha
484
09:00-09:15 WM1h5 An Online Signature Verification System for Forgery and Disguise Detection
Abdelaali Hassaine and Somaya Al-Maadeed
506
09:15-09:30 WM1h6 A Modular approach to support the Multidisciplinary Design of Educational Game Experiences
Telmo Zarraonandia, Paloma Díaz and Ignacio Aedo
511
09:30-09:45 WM1h7 Touch-Based Mobile Phone Interface Guidelines and Design Recommendations for Elderly People: A Survey of the Literature
Hend Al-Khalifa 512
09:45-10:00 WM1h8 Generating Educational Multimedia Contents Dynamically
Jihad Mohamad Jaam 341
Wed. Nov 14
WM1i Regular Session Pattern Recognition Room: Al Sidra
Chair: Xiaolin Hu ID
08:00-08:15 WM1i1 Effect of Luminance Gradients in Measurement of Differential Limen
Hiroaki Kudo, Takuya Kume and Noboru Ohnishi
60
08:15-08:30 WM1i2 A Computational Model for Development of Post-Traumatic Stress Disorders by Hebbian Learning
Sebastien Naze and Jan Treur 100
08:30-08:45 WM1i3 Power-Law Scaling of Synchronization Robustly Reproduced in the Hippocampal CA3 Slice Culture Model with Small-World Topology
Toshikazu Samura, Yasuomi Sato, Yuji Ikegaya, Hatsuo Hayashi and Takeshi Aihara
125
08:45-09:00 WM1i4 Variety of Cortical Pathways Formed by Topographic Neural Projection: A Computational Study
Naoyuki Sato 138
09:00-09:15 WM1i5 Frontal Cortex Neural Activities Shift Cognitive Resources Away from Facial Activities in Real-time Problem Solving
Shen Ren, Michael Barlow and Hussein Abbass
141
09:15-09:30 WM1i6 Support Vector Machines for Real Consumer Circuits Vittorio Latorre, Gianni Di Pillo and Angelo Ciccazzo
648
09:30-09:45 WM1i7 An Orientation Detection Model Based on Fitting from Multiple Local Hypotheses
Hui Wei and Yuan Ren 307
09:45-10:00 WM1i8 Hierarchical K-Means Algorithm for Modeling Visual Area V2 Neurons
Xiaolin Hu, Peng Qi and Bo Zhang 284
41
ICONIP 2012
08:00-10:00 Wednesday, 14 November Poster Session
Wed.,
Nov 14
TA2P Poster Session Outside Al Areen ball room ID
WM1P01 Color Image Segmentation Based on Regional Saliency Haifeng Sima, Lixiong Liu and
Ping Guo
119
WM1P02 Self-Organising Maps for Classification with Metropolis-
Hastings Algorithm for Supervision.
Piotr Plonski and Krzysztof
Zaremba
145
WM1P03 Feature Extraction by Nonnegative Tucker Decomposition
from EEG Data Including Testing and Training
Observations
Fengyu Cong, Anh Huy Phan,
Qibin Zhao, Qiang Wu, Tapani
Ristaniemi and Andrzej
Cichocki
148
WM1P04 Self Organizing Maps for Visualization of Categories Julian Szymański, Włodzisław
Duch
157
WM1P05 Improving the Robustness of Single-view-based ear
Recognition when Rotated in Depth
Daishi Watabe, Takanari
Minamidani, Hideyasu Sai,
Katsuhiro Sakai and Osamu
Nakamura
162
WM1P06 Fast Affine Invariant Shape Matching from 3D Images
based on the Distance Association Map and the Genetic
Algorithm
Chi Sing Leung, Peter Peter
Wai-Ming and Kai-Tat Ng
182
WM1P07 Decomposition of the Transfer Entropy: Partial
Conditioning and Informative Clustering
Guorong Wu, Sebastiano
Stramaglia and Daniele
Marinazzo
189
WM1P08 Towards IMACA: Intelligent Multimodal Affective
Conversational Agent
Erik Cambria and Amir Hussain 574
WM1P09 Salient Instance Selection for Multiple-Instance Learning Liming Yuan, Songbo Liu,
Qingcheng Huang, Jiafeng Liu
and Xianglong Tang
59
WM1P10 Application of Variational Granularity Language Sets in
Interactive Genetic Algorithms
Dunwei Gong, Jian Chen,
Xiaoyan Sun and Yong Zhang
79
WM1P11 ROI-HOG and LBP Based Human Detection via Shape
Part-Templates Matching
Shenghui Zhou, Qing Liu,
Jianming Guo and Yuanyuan
Jiang
105
WM1P12 Rough Sets and Neural Networks Based Aerial Images
Segmentation Method
Xiao Fu, Jin Liu, Bin Zhang and
Rui Gao
136
WM1P13 Decoupled 2-D DOA Estimation Algorithm Based on
Cross-correlation Matrix for Coherently Distributed Source
Yinghua Han, Jinkuan Wang,
Qiang Zhao and Peng Han
147
WM1P14 GMM-ClusterForest:A Novel Indexing Approach for
Multi-Features based Similarity Search in High-
Dimensional Spaces
Yuchai Wan, Xiabi Liu, Kunqi
Tong, Xue Wei, Yi Wu, Fei
Guan and Kunpeng Pang
158
WM1P15 Set-Similarity Joins Based Semi-supervised Sentiment
Analysis
Xishuang Dong, Qibo Zou and
Yi Guan
169
WM1P16 An Improved Method to Calculate Phase Locking Value
Based on Hilbert-Huang Transform and Its Application
Jin Zhang 271
WM1P17 A New Approach for a Priori Client Threshold Estimation
in Biometric Signature Recognition Based on Multiple
Linear Regression
Arancha Simon-Hurtado,
Esperanza Manso-Martinez,
Carlos Vivaracho-Pascualand
Juan M. Pascual-Gaspar
160
42
ICONIP 2012
10:30-12:30 Wednesday, 14 November Oral Sessions
Wed.
Nov 14
WM2a Special Session
Artificial Neural Network and Pattern Recognition
Room: Al Areen 2
Chair: Kittichai Lavangnananda ID
10:30-10:45 WM2a1 Estimation of Missing Precipitation Records using
Modular Artificial Neural Networks
J. Kajornrit, K.W. Wong and
Chun Che Fung
82
10:45-11:00 WM2a2 A Self-Organizing Maps Multivariate Spatio-Temporal
Approach for the Classification of Atmospheric
Conditions
Kostas Philippopoulos and
Despina Deligiorgi
497
11:00-11:15 WM2a3 Multi-Threaded Support Vector Machines For Pattern
Recognition
Bernardete Ribeiro and Noel
Lopes
519
11:15-11:30 WM2a4 A Set of Geometrical Features for Writer Identification Abdelaali Hassaine, Somaya Al-
Maadeed and Ahmed Bouridane
520
11:30-11:45 WM2a5 Real-Valued Constraint Optimization with ICHEA Anurag Sharma and Dharmendra
Sharma
335
11:45-12:00 WM2a6 Adaptive Classifier Selection in Large-scale
Hierarchical Classification
Ioannis Partalas, Rohit Babbar,
Eric Gaussier and Cecile Amblard
571
12:00-12:15 WM2a7 Turf Grass Irrigation Using Neuro-Fuzzy System Shuzlina Abdul Rahman, Azlinah
Mohamed, Sofianita Mutalib and
Marina Yusoff
634
12:15-12:30 WM2a8 Utilizing Symbolic Representation in Synergistic
Neural Networks Classifier of Control Chart Patterns
Kittichai Lavangnananda and
Pantharee Sawasdimongkol
287
Wed.
Nov 14
WM2b Special Session
Computer Systems and Applications II
Room: Al Areen 1
Chair: Jihad Mohamad Jaam ID
10:30-10:45 WM2b1 Designing Serious Games for Adult Students with
Cognitive Disabilities
Javier Torrente, Ángel Del
Blanco, Pablo Moreno-Ger
and Baltasar Fernandez-Manjon
572
10:45-11:00 WM2b2 A Novel Traffic Sign Detection and Recognition
Approach by Introducing CCM and LESH
Zakir Usman, Usman Asima,
Hussain Amir
576
11:00-11:15 WM2b3 Global Minimizer of Large Scale Stochastic
Rosenbrock Function: Canonical Duality Approach
Chaojie Li, David Gao and
Chuandong Li
651
11:15-11:30 WM2b4 Audio-Visual Feature Fusion for Person Identification Noor Almaadeed, Abbes Amira
and Amar Aggoun
84
11:30-11:45 WM2b5 An Integrated Problem Solving Steering Framework on
Clash Reconciliation Strategies for University
Examination Timetabling Problem
J. Joshua Thomas, Ahamad
Tajudin Khader, Bahari Belaton
and Choy Chee Ken
278
11:45-12:00 WM2b6 Neural Networks Based System for the Supervision of
Therapeutic Exercises
S. Nomm, A. Kuusik, S.
Ovsjanski, I. Malmberg, M.
Parve and L. Orunurm
320
12:00-12:15 WM2b7 An Extension of the Consensus-Based Bundle
Algorithm for Group Dependant Tasks with Equipment
Dependencies
Simon Hunt, Qinggang Meng and
Chris J Hinde
479
43
ICONIP 2012
Wed.
Nov 14
WM2c Regular Session
Cognitive Science I
Room: Al Areen 4
Chair: Sven Nomm ID
10:30-10:45 WM2c1 PEAQ Compatible Audio Quality Estimation Using
Computational Auditory Model
Jia Zheng, Mengyao Zhu, Junwei
He and Xiaoqing Yu
112
10:45-11:00 WM2c2 A Memetic Approach for the Knowledge Extraction Sadjia Benkhider, Oualid
Dahmri and Habiba Drias
128
11:00-11:15 WM2c3 Future Prediction with Hierarchical Episodic Memories
under Deterministic and Stochastic Environments
Yoshito Aota and Yoshihiro
Miyake
207
11:15-11:30 WM2c4 A Contextual-bandit Algorithm for Mobile Context-
Aware Recommender System
Djallel Bouneffouf, Amel
Bouzeghoub and Alda Lopes
Gançarski
250
11:30-11:45 WM2c5 Measuring Stress-Reducing Effects of Virtual Training
Based on Subjective Response
Tibor Bosse, Charlotte Gerritsen,
Jeroen de Man and Jan Treur
251
11:45-12:00 WM2c6 Machine Learning Approach to Enhance the Design of
Automated Theorem Provers
Mahdi Khalifa, Hazem Raafat and
Mohammed Almulla
619
12:00-12:15 WM2c7 Managing Qualitative Preferences with Constraints Eisa Alanazi and Malek Mouhoub 622
12:15-12:30 WM2c8 Aimbot Detection in Online FPS Games Using A
Heuristic Method Based on Distribution Comparison
Matrix
Su-Yang Yu, Nils Hammerla, Jeff
Yan and Peter Andras
623
Wed.
Nov 14
WM2d Regular Session
Computer and Internet Applications
Room: Al Areen 5
Chair: William Mount ID
10:30-10:45 WM2d1 Low Complexity Classification System for Glove-
based Arabic Sign Language Recognition
Khaled Assaleh, Tamer
Shanableh and Mohammed
Zourob1
216
10:45-11:00 WM2d2 Computer Aided Writing - A Framework Supporting
Research Tasks, Topic Recommendations and Text
Readability
Klahold André, Mareike
Dornhöfer and Madjid Fathi
194
11:00-11:15 WM2d3 Mobile Web Browsing Techniques Zahirrudin Ahmad and Jer Lang
Hong
263
11:15-11:30 WM2d4 Discriminative Feature Analysis and Selection for
Document Classification
Punya Murthy Chinta and M.
Narasimha Murty
291
11:30-11:45 WM2d5 Attach Topic Sense to Social Tags Junpeng Chen, Juan Liu and Bo
Guo
352
11:45-12:00 WM2d6 ANN for Multi-Lingual Regional Web Communication Kolla Bhanu Prakash, M.A. Dorai
Ranga Swamy and Arun
Rajaraman
446
12:00-12:15 WM2d7 A framework of a Route Optimization Scheme for
Nested Mobile Network
S. Senan, A. Hashim, Akram
Zeki, Rashid Saeed, Shihab
Hameed and Jamal Daoud
645
12:15-12:30 WM2d8 A Psycho-physiological Analysis of Weak Annoyances
in Human Computer Interfaces
William Mount, Deborah Tuček
and Hussein Abbass
180
44
ICONIP 2012
Wed.
Nov 14
WM2e
Regular Session
Signal Processing and Image Processing II
Room: Al Areen 6
Chair: Baoliang Lu ID
10:30-10:45 WM2e1 Design of Distribution Independent Noise Filters with
Online PDF Estimation
Vipul Arora and Laxmidhar
Behera
53
10:45-11:00 WM2e2 Implement Real-time Polyphonic Pitch Detection and
Feedback System for the Melodic Instrument Player
Geon-Min Kim, Chang-Hyun
Kim and Soo-Young Lee
142
11:00-11:15 WM2e3 Integration of Face Detection and User Identification
with Visual Speech Recognition
Alaa Sagheer and Saleh Aly 448
11:15-11:30 WM2e4 Effect of Facial Feature Points Selection on 3D Face
Shape Reconstruction using Regularization
Ashraf Y.A. Maghari, Iman Y.
Liao and Bahari Belaton
471
11:30-11:45 WM2e5 A Multi-Modal Face and Signature Biometric
Authentication System Using a Max-of-Scores Based
Fusion
Youssef Elmir, Somaya Al-
Maadeed, Abbes Amira and
Abdelaali Hassaine
516
11:45-12:00 WM2e6 Subspace Echo State Network for Multivariate Time
Series Prediction
Min Han and Meiling Xu 643
12:00-12:15 WM2e7 Online Vigilance Analysis Combining Video and
Electrooculography Features
Ruofei Du, Renjie Liu,Tianxiang
Wu and Baoliang Lu
433
Wed.
Nov 14
WM2f
Regular Session
Data Analysis
Room: Al Majida
Chair: Irwin King ID
10:30-10:45 WM2f1 Robust and Optimum Features for Persian Accent
Classification Using Artificial Neural Network
Azam Rabiee and Saeed
Setayeshi
416
10:45-11:00 WM2f2 Dual-Feature Bayesian MAP Classification: Exploiting
Temporal Information for Video-based Face
Recognition
John See, Chikkannan Eswaran
and Mohammad Faizal Ahmad
Fauzi
490
11:00-11:15 WM2f3 Linked PARAFAC/CP Tensor Decomposition and its
Fast Implementation for Group Tensor Analysis
Tatsuya Yokota, Andrzej
Cichocki and Yukihiko
Yamashita
80
11:15-11:30 WM2f4 Adaptive Multiplicative Updates for Projective
Nonnegative Matrix Factorization
He Zhang, Zhirong Yang and
Erkki Oja
231
11:30-11:45 WM2f5 Online Projective Nonnegative Matrix Factorization for
Large Datasets
Zhirong Yang, He Zhang and
Erkki Oja
232
11:45-12:00 WM2f6 A New Probabilistic Approach to Independent
Component Analysis Suitable for On-Line Learning in
Artificial Neural Networks
Marko V. Jankovic and Neil
Rubens
480
12:00-12:15 WM2f7 Self-Organized Three Dimensional Feature Extraction
of MRI
Satoru Morita 76
12:15-12:30 WM2f8 TaskRec: Probabilistic Matrix Factorization in Task
Recommendation in Crowdsourcing Systems
Connie Yuen, Irwin King and
Kwong-Sak Leung
455
45
ICONIP 2012
Wed. Nov 14
WM2g
Regular Session Learning Algorthms and Neural Models I Room: Al Ahood
Chair: Nistor Grozavu ID
10:30-10:45 WM2g1 Bandit-based Structure Learning for Bayesian Network Classifiers
S. Eghbali, M.H.Z. Ashtiani, Majid Nili Ahmadabadi and Babak Nadjar Araabi
288
10:45-11:00 WM2g2 Feature Selection for Unsupervised Learning Jyoti Ranjan Adhikary and M. Narasimha Murty
290
11:00-11:15 WM2g3 A Unified Framework of Binary Classifiers Ensemble for Multi-Class Classification
Takashi Takenouchi and Shin Ishii
298
11:15-11:30 WM2g4 Recursive Similarity-Based Algorithm for Deep Learning
Tomasz Maszczyk and Wlodzislaw Duch
310
11:30-11:45 WM2g5 Manifold Regularized Multi-task Learning Peipei Yang, Xu-Yao Zhang, Kaizhu Huang and Cheng-Lin Liu
463
11:45-12:00 WM2g6 Energy-Based Temporal Neural Networks for Imputing Missing Values
Philemon Brakel and Benjamin Schrauwen
489
12:00-12:15 WM2g7 Robust Active Learning for Linear Regression via Density Power Divergence
Yasuhiro Sogawa, Tsuyoshi Ueno, Yoshinobu Kawahara and Takashi Washio
505
12:15-12:30 WM2g8 Collaborative Generative Topographic Mapping Mohamad Ghassany, Nistor Grozavu and Younès Bennani
495
Wed. Nov 14
WM2h
Regular Session Computational Advances in Bioinformatics Room: Al Jazi
Chair: Madhu Chetty ID
10:30-10:45 WM2h1 Association of Anti-Histamine Drugs with Brain tumor Nisar Ahmed Shar, Samreen Feroz and Ali Raza Jafri
40
10:45-11:00 WM2h2 Dynamic Health Level 7 Packetizer for on-the-fly Integrated Healthcare Enterprises (IHE) in Disaster Zones
Junaid Chaudhry, Uvais Qidwai and Malrey Lee
328
11:00-11:15 WM2h3 Adaptive Modeling of HRTFs Based on Reinforcement Learning
Shuhei Morioka, Isao Nambu, Shohei Yano, Haruhide Hokari and Yasuhiro Wada
405
11:15-11:30 WM2h4 Using Hybrid Neural Networks for Identifying the Brain Abnormalities from MRI Structural Images
Lavneet Singh, Girija Chetty and Dharmendra Sharma
444
11:30-11:45 WM2h5 A Novel Approach to Protein Structure Prediction Using PCA or LDA Based Extreme Learning Machines
Lavneet Singh, Girija Chetty and Dharmendra Sharma
445
11:45-12:00 WM2h6 Towards Applying Associative Classifier for Genetic Variants
Sofianita Mutalib, Shuzlina Abdul Rahman and Azlinah Mohamed
628
12:00-12:15 WM2h7 On the Reconstruction of Genetic Network from Partial Microarray Data
A.R.Chowdhury, M. Chetty and X.N. Vinh
640
12:15-12:30 WM2h8 Data Discretization for Dynamic Bayesian Network based Modeling of Genetic Networks
Vinh Nguyen, Madhu Chetty, Ross Coppel and Pramod P. Wangikar
254
Wed. Nov 14
WM2i
Regular Session Image Processing I Room: Al Sidra
Chair: Muhammad Usman Akram ID
10:30-10:45 WM2i1 From Image Annotation to Image Description Ankush Gupta 185 10:45-11:00 WM2i2 Multiple Sections Extraction using Visual Cue Derren Wong and Jer Lang Hong 264 11:00-11:15 WM2i3 A Novel Hierarchical Statistical Model for Count Data
Modeling and its Application in Image Classification. Ali Shojaee Bakhtiari and Nizar Bouguila
275
11:15-11:30 WM2i4 Early-vision-inspired Method to Distinguish between Handwritten and Machine-Printed Character Images Using Hough Transform
Yuuya Konno and Akira Hirose 325
11:30-11:45 WM2i5 An Image Representation Method Based on Retina Mechanism for the Promotion of SIFT and Segmentation
Hui Wei, Bo Lang and Qing-Song Zuo
344
11:45-12:00 WM2i6 Medical Image Thresholding Using Online Trained Neural Networks
Ahmed Othman 635
12:00-12:15 WM2i7 An Automated System for the Grading of Diabetic Maculopathy in Fundus Images
Muhammad Usman Akram 45
46
ICONIP 2012
10:30-12:30 Wednesday, 14 November Poster Session
Wed.,
Nov 14
WM2P Poster Session Outside Al Areen ball room ID
WM2P01 Global Optimal Selection of Web Composite Services Based
on UMDA
Shuping Cheng, Xiaoming Lu
and Xianzhong Zhou
209
WM2P02 Adaptive Dynamic Control of Quadrupedal Robotic Gaits
with Artificial Reaction Networks
Claire E. Gerrard, George
Coghill, Christopher Macleod
and John Mccall
220
WM2P03 Bifurcation Analysis of A Two-dimensional Simplified
Hodgkin-Huxley Model Exposed to External Electric Fields
Hu Wang and Yongguang Yu 225
WM2P04 Steady-state Visually Evoked Potential (SSVEP)-Based
Brain-Computer Interface (BCI): A Low-Delayed
Asynchronous Wheelchair Control System
Zhuo Xu, Jie Li, Rong Gu
and Bin Xia
244
WM2P05 Multi-source Transfer Learning with Multi-view Adaboost Zhijie Xu and Shiliang Sun 261
WM2P06 Semi-supervised Multitask Learning via Self-training and
Maximum Entropy Discrimination
Guoqing Chao and Shiliang
Sun
262
WM2P07 Multitask Twin Support Vector Machines Xijiong Xie and Shiliang Sun 282
WM2P08 Characterisation of Information Flow in an Izhikevich
Network
Li Guo, Zhijun Yang, Bruce
Graham and Daqiang Zhang
306
WM2P09 Feature and Signal Enhancement for Robust Speaker
Identification of G.729 Decoded Speech
Kalpesh Raval, Ravi
Ramachandran, Sachin Shetty
and Brett Smolenski
319
WM2P10 Suppression and Stabilization of Functional System with
Markovian Switching
Lizhu Feng, Yi Shen and
Zhuguo Li
371
WM2P11 Approaches for the Detection of the Key Words in Spoken
Documents : Application for the Field of E-libraries
Bendib Issam and Laouar
Mohamed Ridda
176
WM2P12 Survey on Simplified Olfactory Bionic Model to Generate
Texture Images
Jin Zhang 270
WM2P13 Learning Visual Saliency based on Object's Relative
Relationship
Senlin Wang, Qi Zhao,
Mingli Song, Jiajun Bu, Chun
Chen and Dacheng Tao
305
WM2P14 Template Matching Based Video Tracking System Using A
Novel N-Step Search Algorithm and Hog Features
Tudor Barbu 311
WM2P15 Damage Pattern Recognition of Refractory Based on BP
Neural Network
C. Liu, Z.Wang, Yourong Li,
Xi Li, Gangbing Song and
Jianyi Kong
412
WM2P16 Emotion Recognition Using KNN Classification for User
Modeling and Sharing of Affect States
Imen Tayari Meftah, Nhan Le
Thanh and Chokri Ben Amar
192
WM2P17 Effective Handwriting Recognition System Using
Geometrical Character Analysis Algorithms
Wojciech Kacalak and Maciej
Majewski
212
47
ICONIP 2012
13:40-15:40 Wednesday, 14 November Invited Session and Oral Sessions
Wed.,
Nov 14
I3 Invited Session
Room: Al Areen 3
Chair: Ganesh Kumar
Venayagamoorthy
ID
13:40-14:10 I301 Adaptive Learning and Control for Machine Intelligence Haibo He
14:10-14:40 I302 Noise Attenuation and Robustness in Cell Signaling and
Patterning
Qing Nie
14:40-15:10 I303 About the Optimality of Mutual Information for Feature
Selection
Michel Verleysen
15:10-15:40 I304 Dynamic Scalable Monitoring and Control Technologies for
Smart Grids
Ganesh Kumar
Venayagamoorthy
Wed.
Nov 14
WA1a Regular Session
Fuzzy and Soft Computing
Room: Al Areen 2
Chair: Laszlo T. Koczy ID
13:40-13:55 WA1a1 Structures of Surround Modulation for the Border-
Ownership Selectivity of V2 Cells
Yusuke Nakata and Ko Sakai 297
13:55-14:10 WA1a2 A Novel Node Splitting Criteria for Decision Trees Based on
Theil Index
Shina Sheen and R Anitha 351
14:10-14:25 WA1a3 Power and Task Management in Wireless Body Area
Network Based Medical Monitoring Systems
Robert Rittenhouse, Malrey
Lee, Junaid Chaudhry and
Uvais Qidwai
356
14:25-14:40 WA1a4 Global Reweighting and Weight Vector Based Strategy for
Multiclass Boosting
Awais Mian and M Baig 369
14:40-14:55 WA1a5 Echo State Networks and Extreme Learning Machines: a
Comparative Study on Seasonal Streamflow Series
Prediction
Hugo Siqueira, Levy Boccato,
Romis Attux and Christiano
Lyra Filho
417
14:55-15:10 WA1a6 GARF: Towards Self-optimised Random Forests Mohamed Bader-El-Den and
Mohamed Gaber
424
15:10-15:25 WA1a7 Interval-Valued Fuzzy Extension of Formal Concept
Analysis for Information Retrieval
Loutfi Zerarga and Yassine
Djouadi
508
15:25-15:40 WA1a8 Hamacher t-norm Applied in Fuzzy Rule Extraction Laszlo Gal, Rita Lovassy,
Laszlo T. Koczy and Imre J.
Rudas
299
Wed.
Nov 14
WA1b Regular Session
Knowledge Discovery
Room: Al Areen 1
Chair: Istvan Elek ID
13:40-13:55 WA1b1 Price Forecasting using Dynamic Assessment of Market
Conditions and Agent’s Bidding Behavior
Preetinder Kaur, Madhu
Goyal and Jie Lu
99
13:55-14:10 WA1b2 Development of a Novel Conversational Calculator based on
Remote Online Computation
Xiaohua Liu, Haoran Liang,
Haiwei Dong and Nikolaos
Mavridis
129
14:10-14:25 WA1b3 A Novel Ontological Technique for Sentiment Analysis Kye Lok Tan, Jer Lang
Hong and Ee Xion Tan
277
14:25-14:40 WA1b4 Novelty Detection using a New Group Outlier Factor Amine Chaibi, Mustapha
Lebbah and Hanane Azzag
281
14:40-14:55 WA1b5 Are You A Social Conformer? Priyanka Garg, Irwin King
and Michael R. Lyu
644
14:55-15:10 WA1b6 Semantic Levels of Domain-Independent Commonsense
Knowledgebase for Visual Indexing and Retrieval
Applications
Amjad Altadmri, Amr Ahmed
and Haytham Mohtasseb
562
15:10-15:25 WA1b7 Spontaneous Emergence of the Intelligence in an Artificial
World
Istvan Elek, Janos Roden and
Binh Nguyen
86
48
ICONIP 2012
Wed. Nov 14
WA1c Regular Session Image Processing II Room: Al Areen 4
Chair: David Yang Gao ID
13:40-13:55 WA1c1 Grasping Region Identification in Novel Objects Using Microsoft Kinect
L. Behera, A. Rai, P.K. Patchaikani, M. Agarwal and Rohit Gupta
153
13:55-14:10 WA1c2 Implementation of Face Selective Attention Model on An Embedded System
B. Kim, H.M. Son, Yun-Jung Lee andMinho Lee
170
14:10-14:25 WA1c3 A Hybrid KNN-Ant Colony Optimization Algorithm for Prototype Selection
A. Miloud-Aouidate and Ahmed Riadh Baba-Ali
245
14:25-14:40 WA1c4 Avoiding Catastrophic Forgetting by a Biologically Inspired Dual-Network Memory Model
Motonobu Hattori 313
14:40-14:55 WA1c5 Self-Correcting Symmetry Detection Network W. Chang, H.A. Song, S.H. Oh and S.Y. Lee
473
14:55-15:10 WA1c6 Canonical Duality for Radial Basis Neural Networks Vittorio Latorre and David Yang Gao
647
Wed. Nov 14
WA1d Regular Session Learning Algorithms Room: Al Areen 5
Chair: Nataliya Sokolovska ID
13:40-13:55 WA1d1 Construction of Decision Trees by using Feature Importance Value for Improved Learning Performance
Md. Ridwan Al Iqbal, Mohammad Saiedur Rahaman and Syed Irfan Nabil
191
13:55-14:10 WA1d2 Using Agent Based Modeling and Simulation for Data Mining
Emin Kugu, Levent Altay and Ozgur Koray Sahingoz
197
14:10-14:25 WA1d3 A Distributed Q-Learning Approach for Variable Attention to Multiple Critics
Maryam Tavakol, Majid Nili Ahmadabadi, Maryam Mirian and Masoud Asadpour
201
14:25-14:40 WA1d4 A Meta-Learning Approach to Select Meta-Heuristics for the Traveling Salesman Problem Using MLP-Based Label Ranking
Jorge Kanda, Carlos Soares,Eduardo Hruschka and Andre Carvalho
423
14:40-14:55 WA1d5 Manifold Analysis of Spectral Munsell Colors Hongyu Li, Chen Lin, Junyu Niu, Lin Zhang and Jussi Parkkinen
457
14:55-15:10 WA1d6 Spatio-Temporal LTSA and its Application to Motion Decomposition
Hongyu Li, Junyu Niu, Lin Zhang and Bo Hu
465
15:10-15:25 WA1d7 Sparse Gradient-Based Direct Policy Search Nataliya Sokolovska 183 Wed. Nov 14
WA1e
Regular Session Clustering Algorithms and SOM Room: Al Areen 6
Chair: Andrew Paplinski ID
13:40-13:55 WA1e1 Understanding Individual Play Sequences Using Growing Self Organizing Maps
Manjusri Wickramasinghe, Jayantha Rajapakse and Damminda Alahakoon
58
13:55-14:10 WA1e2 Classification of Interview Sheets Using Self-Organizing Maps for Determination of Ophthalmic Examinations
Naotake Kamiura, Ayumu Saitoh, Teijiro Isokawa, Nobuyuki Matsui and Hitoshi Tabuchi
143
14:10-14:25 WA1e3 A Hybrid Visualization-induced Self-Organizing Map for Multi Dimensional Reduction and Data Visualization
Chee Siong Teh and Chwen Jen Chen
238
14:25-14:40 WA1e4 Learning from Positive and Unlabelled Examples using Maximum Margin Clustering
Sneha Chaudhari and Shirish Shevade
373
14:40-14:55 WA1e5 Clustering with Uncertainties: An Affinity Propagation-Based Approach
Wenye Li 431
14:55-15:10 WA1e6 Modified Particle Swarm Optimization For Pattern Clustering
K.P. Swetha, Devi V. Susheela
437
15:10-15:25 WA1e7 A Possibilistic Density Based Clustering for Discovering Clusters of Arbitrary Shapes and Densities in High Dimensional Data
Noha A. Yousri, Mohamed S. Kamel and Mohamed A. Ismail
496
15:25-15:40 WA1e8 Incremental Self-Organizing Map (iSOM) in Categorization of Visual Objects
Andrew Paplinski 92
49
ICONIP 2012
Wed.
Nov 14
WA1f
Regular Session
Neural Dynamics and Dynamic Systems
Room: Al Majida
Chair: Gangbing Song ID
13:40-13:55 WA1f1 NARX Recurrent Neural Network Model of Ultra-Thin
Shape Memory Alloy Wire
Han Wang and Gangbing
Song
330
13:55-14:10 WA1f2 Temporal Finite-State Machines: A Novel Framework for
the General Class of Dynamic Networks
Karim El-Laithy and Martin
Bogdan
332
14:10-14:25 WA1f3 Solving Dynamic Constraint Optimization Problems using
ICHEA
Anurag Sharma and
Dharmendra Sharma
346
14:25-14:40 WA1f4 Sensorless Speed Control of Hystersis Motor based on
Model Reference Adaptive System and Luenberger Observer
Techniques
Abolfazl Halvaei Niasar,
Hassan Mogheblli and
Mojtaba Yavari
438
14:40-14:55 WA1f5 Emergence of Multi-Step Discrete State Transition through
Reinforcement Learning with a Recurrent Neural Network
Mohamad Faizal Samsudin
and Katsunari Shibata
494
14:55-15:10 WA1f6 Markovian Models for Electrical Load Prediction in Smart
Buildings
Muhammad Kumail Haider,
Asad Khalid Ismail and Ihsan
Ayyub Qazi
568
15:10-15:25 WA1f7 Extension of Incremental Linear Discriminant Analysis to
Online Feature Extraction under Nonstationary
Environments
Annie Anak Joseph, Young-
Min Jang, Seiichi Ozawa and
Minho Lee
573
15:25-15:40 WA1f8 Learning Anticipation through Priming in Spatio-Temporal
Neural Networks
Nooraini Yusoff and Andre
Gruning
168
Wed.
Nov 14
WA1g
Regular Session
Spiking Systems and Dynamic Systems
Room: Al Ahood
Chair: Yiran Chen ID
13:40-13:55 WA1g1 Identification of Neural Network Structure from Multiple
Spike Sequences
Kaori Kuroda, Kantaro
Fujiwara and Tohru Ikeguchi
149
13:55-14:10 WA1g2 A Data Gathering Scheme in Wireless Sensor Networks
Using a Spiking Neural Network with Simple Local
Information
Ikki Fujita, Hidehiro Nakano
and Arata Miyauchi
283
14:10-14:25 WA1g3 A Target-Reaching Controller for Mobile Robots Using
Spiking Neural Networks
Xiuqing Wang Wang and
Zeng-Guang Hou
637
14:25-14:40 WA1g4 The Optimal Control of Discrete-time Delay Nonlinear
System with Dual Heuristic Dynamic Programming
Bin Wang and Dongbin Zhao 609
14:40-14:55 WA1g5 Full Body Balance Modeling Based on Neural Network R. Trevino, M. Frye, and
Chunjiang Qian
14:55-15:10 WA1g6 A Maximum Priciple for Systems Governed by Self-
Adjoint-Nonlinear Operator Equations in Hilbert Spaces
Mohamed El-Gebeily
15:10-15:25 WA1g7 The Circuit Realization of a Neuromorphic Computing
System with Memristor-based Synapse Design
Beiye Liu, Yiran Chen,
Bryant Wysocki and Tingwen
Huang
286
50
ICONIP 2012
Wed.
Nov 14
WA1h
Regular Session
Dynamic Systems
Room: Al Jazi
Chair: Takafumi Kanamori ID
13:40-13:55 WA1h1 Estimating Principal Point and Nonlinear Parameters of
Camera from a Planar Calibration Image
Qiuyu Zhu 46
13:55-14:10 WA1h2 Robust Controller for Flexible Specifications Using
Difference Signals and Competitive Associative Nets
Weicheng Huang, Shuichi
Kurogi and Takeshi Nishida
61
14:10-14:25 WA1h3 Design of a Data-Oriented PID Controller for Nonlinear
Systems
Shin Wakitani, Takuya
Nawachi and Toru Yamamoto
140
14:25-14:40 WA1h4 A Basic Study on Particle Swarm Optimization Based on
Chaotic Spike Oscillator Dynamics
Yoshikazu Yamanaka and
Tadashi Tsubone
173
14:40-14:55 WA1h5 An Incremental Approach to Solving Dynamic Constraint
Satisfaction Problems
Anurag Sharma and
Dharmendra Sharma
349
14:55-15:10 WA1h6 Transient-Time Fractional-Space Trigonometry and
Application
Ahmed S. Elwakil 57
15:10-15:25 WA1h7 Non-Convex Optimization on Stiefel Manifold and
Applications to Machine Learning
Takafumi Kanamori and
Akiko Takeda
104
15:25-15:40 WA1h8 Estimating Brain Activity of Motor Learning by Using
Fnirs-GLM Analysis
Takahiro Imai, Takanori Sato,
Isao Nambu and Yasuhiro
Wada
312
Wed.
Nov 14
WA1i
Regular Session
Computational Neuroscience
Room: Al Sidra
Chair: Jiangguo Liu ID
13:40-13:55 WA1i1 Bayesian Variable Selection in Neural Networks for Short-
Term Meteorological Prediction
Pierrick Bruneau and
Laurence Boudet
274
13:55-14:10 WA1i2 Modeling Post-Training Memory Transfer in Cerebellar
Motor Learning
Tadashi Yamazaki and Soichi
Nagao
339
14:10-14:25 WA1i3 Surface-Based Construction of Curvature Selectivity from
the Integration of Local Orientations
Yasuhiro Hatori and Ko Sakai 345
14:25-14:40 WA1i4 Modeling of Polycaprolactone Production from Ε-
Caprolactone Using Neural Network
Senthil Kumar Arumugasamy,
Mohamad Hekarl Uzir and
Zainal Ahmad
353
14:40-14:55 WA1i5 An Estimation of Cell Forces with Hierarchical Bayes
Approach Considering Cell Morphology
Satoshi Kozawa, Yuichi
Sakumura, Michinori
Toriyama, Naoyuki Inagaki
and Kazushi Ikeda
435
14:55-15:10 WA1i6 A Novel Paradigm for Mining Cell Phenotypes in Multi-Tag
Bioimages using a Locality Preserving Nonlinear
Embedding
Adnan Mujahid Khan, Ahmad
Humayun, Shan-E-Ahmed
Raza, Michael Khan and Nasir
Rajpoot
514
15:10-15:25 WA1i7 Continuous Classification of Spatio-Temporal Data Streams
Using Liquid State Machines
Stefan Schliebs and Doug
Hunt
617
15:25-15:40 WA1i8 Viral Assembly: Dynamical Systems and Group Theory Jiangguo Liu
51
ICONIP 2012
13:40-15:40 Wednesday, 14 November Poster Session
Wed.,
Nov 14
WA1P Poster Session Outside Al Areen ball room ID
WA1P01 P-order Normal Cloud Model: Walking on the Way between
Gaussian and Power Law Distributions
Yu Liu and Tianwei Zhang 404
WA1P02 Identification of Factors Characterising Volatility and Firm-
Specific Risk Using Ensemble Classifiers
Pascal Khoury and Denise
Gorse
418
WA1P03 Sampling Normal Distribution Restricted on Multiple Regions Jun Li and Dacheng Tao 428
WA1P04 Robust Hypersurface Fitting Based on Random Sampling
Approximations
Jun Fujiki, Shotaro Akaho,
Hideitsu Hino and Noboru
Murata
447
WA1P05 Trust and Equity Theory in Prisoner's Dilemma Eun-Soo Jung, Bo-Kyeong
Kim and Soo-Young Lee
475
WA1P06 Comparative Analysis of Clustering Algorithms applied to the
Classification of Bugs
Anderson Santana, Jackson
Silva, Patricia Muniz,
Fabrício Araújo and Renata
Souza
546
WA1P07 Authorship Attribution of Electronic Documents Walter Ribeiro de Oliveira
Jr., Edson Justino and Luiz
Oliveira
551
WA1P08 Mass Classification in Digitized Mammograms Using Texture
Features and Artificial Neural Network
M.Wong, X. He, H. Nguyen
and W. Yeh
120
WA1P09 Retrieval of Semantic Concepts Based on Analysis of Texts
for Automatic Construction of Ontology
Reshmy Krishnan, Amir
Hussain and Sherimon P.C
453
WA1P10 The Use of ASM Feature Extraction and Machine Learning
for the Discrimination of Members of the Fish Ectoparasite
Genus Gyrodactylus
R. Ali, A. Hussain, J.E.
Bron and A.P. Shinn
215
WA1P11 A Hybrid Approach for Adaptive Car Navigation Siamak Barzegar, Maryam
Davoudpour and Alireza
Sadeghian
202
WA1P12 Novel Robust Stability Criteria for Stochastic Hopfield
Neural Network with Time-Varying Delays
Xiaolin Li and Minrui Wang 407
WA1P13 Delay-dependent Stabilization of Uncertain Distributed
Systems with Interval Time-varying Delay
Lizhu Feng, Yi Shen and
Cheng Wang
422
WA1P14 Direct Robust Adaptive NN Tracking Control for Double
Inverted Pendulums
Wenlian Yang, Ye Tao and
Tieshan Li
430
WA1P15 A Weighted Learning Vector Quantization Approach for
Interval Data
Telmo M. Silva Filho and
Renata M.C.R. Souza
440
WA1P16 Harnessing Chaotic Activation Functions in Training Neural
Network
Md. Asaduzzaman, N.
Uddin, Md. Shahjahan and K.
Murase
466
WA1P17 MOTIF-RE: Motif-based Hypernym/hyponym Relation
Extraction from Wikipedia Links
Bifan Wei and Jun Liu 567
52
ICONIP 2012
16:10-17:40 Wednesday, 14 November Invited Session and Oral Sessions
Wed.,
Nov 14
I4 Invited Session
Room: Al Areen 3
Chair: Zidong Wang ID
16:10-16:40 I401 Action and Rule of Neuronal Energy in Signal Processing
of the Cerebral Cortex
Rubin Wang
16:40-17:10 I402 A Sampled-Data Approach to Analysing Complex
Networks
Zidong Wang
17:10-17:40 I403 Advantage of Discrete Neural Networks: Co-Existence of
Chaos and Stable Periodic Orbits in Discrete Neural
Networks with Delay
Xingfu Zou
Wed.
Nov 14
WA2a Speical Session
Intelligent Intrusion Detection And Security Systems
Room: Al Areen 2
Chair: El-Sayed Mohamed El-
Alfy
ID
16:10-16:25 WA2a1 Office Employees Authentication Based on E-exam
Techniques
Ameer Morad 90
16:25-16:40 WA2a2 Pedestrian Analysis and Counting System with Videos Zhi-Bin Wang, Hong-Wei Hao,
Yan Li, Xu-Cheng Yin and Shu
Tian
95
16:40-16:55 WA2a3 Analysis of Intrusion Detection in Control System
Communication based on Outlier Detection with One-class
Classifiers
Takashi Onoda and Mai Kiuchi 259
16:55-17:10 WA2a4 Fuzzy Particle Swarm Optimization for Intrusion
Detection
Dalila Boughaci, Mohamed
Djamel Eddine Kadi and
Meriem Kada
477
17:10-17:25 WA2a5 Extreme Learning Machines for Intrusion Detection
Systems
Gilles Paiva, Adriano Oliveira
and George Cabral
486
17:25-17:40 WA2a6 Neuro-Cryptanalysis of DES and Triple-DES Mohammed Alani 612
Wed.
Nov 14
WA2b Special Session
Non-stationary Time Series Processing in Computational
Neuroscience
Room: Al Areen 1
Chair: Emili Balaguer-Ballester ID
16:10-16:25 WA2b1 Time Domain Parameters for Online Feedback fNIRS-
based Brain-Computer Interface Systems
Tuan Hoang, Dat Tran, Khoa
Truong, Trung Le, Xu Huang,
Dharmendra Sharma and Toi
Vo
150
16:25-16:40 WA2b2 Embedding Relevance Vector Machine in Fuzzy Inference
System for Energy Consumption Forecasting
Hamid Aghaie Moghanjooghi,
Babak Nadjar Araabi and Majid
Nili Ahmadabadi
155
16:40-16:55 WA2b3 Data Discretization using the Extreme Learning Machine
Neural Network
Juan Jesús Carneros, Jose M.
Jerez, Ivan Gomez and
Leonardo Franco
272
16:55-17:10 WA2b4 Single-Trial Multi-Channel N170 Estimation using Linear
Discriminant Analysis (LDA)
Wee Lih Lee, Tele Tan,
Torbjorn Falkmer and Yee
Hong Leung
308
17:10-17:25 WA2b5 Complexity Analysis of EEG Data During Rest State and
Visual Stimulus
Wajid Mumtaz, Likun Xia and
Aamir Saeed Malik
93
17:25-17:40 WA2b6 Neurodynamical Top-Down Processing during Auditory
Attention
Emili Balaguer-
Ballester,Abdelhamid
Bouchachia, Beibei Jiang and
Susan L Denham
198
53
ICONIP 2012
Wed. Nov 14
WA2c Special Session Neural Cognitive Architectures and Systems Room: Al Areen 4
Chair: Jacek Mańdziuk ID
16:10-16:25 WA2c1 Synchronization of Hopfield like Chaotic Neural Networks with Structure Based Learning
Nariman Mahdavi and Juergen Kurths
89
16:25-16:40 WA2c2 A Dynamic Bio-Inspired Model of Categorization Hamidreza Jamalabadi, Hossein Nasrollahi, Majid Nili Ahmadabadi, Babak Nadjar Araabi, Abdolhossein Vahabie and Mohammadreza Abolghasemi
127
16:40-16:55 WA2c3 A Real-Time, Event Driven Neuromorphic System for Goal-Directed Attentional Selection
Francesco Galluppi, Kevin Brohan, Simon Davidson, Teresa Serrano-Gotarredona, José-Antonio Pérez Carrasco, Bernabé Linares-Barranco and Steve Furber
178
16:55-17:10 WA2c4 Generation of Environmental Representation of a Large Indoor Parking Lot
Jung-Ming Wang, Sei-Wang Chen, Chiou-Shann Fuh and Chih-Fan Hsu
266
17:10-17:25 WA2c5 Stabilizing Relaxed Nonlinear FMA Yields a (Combinatorial) Optimizer
Zekeriya Uykan 322
17:25-17:40 WA2c6 Human-like Intuitive Playing in Board Games Jacek Mańdziuk 240
Wed. Nov 14
WA2d Regular Session Learning Algorthms and Neural Models II Room: Al Areen 5
Chair: Mohamad Saada ID
16:10-16:25 WA2d1 Learning Temporal Coherent Features through Life-Time Sparsity
Jost Tobias Springenberg and Martin Riedmiller
280
16:25-16:40 WA2d2 Over-Sampling from an Auxiliary Domain Samir Al-Stouhi and Abhilash Pandya
491
16:40-16:55 WA2d3 A Novel Method of Sparse Least Squares Support Vector Machines in Class Empirical Feature Space
Takuya Kitamura and Takamasa Sekine
413
16:55-17:10 WA2d4 Rule Extraction from Ensemble Methods Using Aggregated Decision Trees
Md. Ridwan Al Iqbal 503
17:10-17:25 WA2d5 Adaptive Probabilistic Policy Reuse
Yann Chevaleyre and Aydano Machado Pamponet
563
17:25-17:40 WA2d6 An efficient Algorithm for Anomaly Detection in a Flight System using Dynamic Bayesian Networks
Mohamad Saada and Qinggang Meng
575
Wed. Nov 14
WA2e Regular Session Computational Intelligence Methods and Applications in Smart Grid Room: Al Areen 6
Chair: Armando Pelliccioni ID
16:10-16:25 WA2e1 Office-Space-Allocation Problem using Harmony Search Algorithm
Ahamad Tajudin Khader, Mohammed Azmi Al-Betar, Phuah Chea Woon and Mohammed Awadallah
294
16:25-16:40 WA2e2 Feature Selection for Electricity Load Prediction Mashud Rana, Irena Koprinska and Vassilios Agelidis
458
16:40-16:55 WA2e3 Statistical and Machine Learning Methods for Electricity Demand Prediction
Alexandra Kotillova, Irena Koprinska and Mashud Rana
459
16:55-17:10 WA2e4 A Regularized Linear Classifier for Effective Text Classification
Sharad Nandanwar and M. Narasimha Murty
163
17:10-17:25 WA2e5 EnerPlan: Smart Energy Management Planning for Home Users
Usman Ali, Zeeshan Rana, Fahad Javed and Awais Mian
461
17:25-17:40 WA2e6 Classification of Power Quality Disturbances Using Artificial Neural Networks and a Logarithmically Compressed S–transform
Emir Turajlic and Dzenan Softic 518
54
ICONIP 2012
Wed.
Nov 14
WA2f
Regular Session
Cognitive Science ll
Room: Al Majida
Chair: Ahmed Izzidien ID
16:10-16:25 WA2f1 Cross-subject Classification of Speaking Modes Using
fNIRS
Christian Herff, Dominic Heger,
Felix Putze, Cuntai Guan and
Tanja Schultz
329
16:25-16:40 WA2f2 Artificial Neural Network Classification Models for Stress
in Reading
Nandita Sharma and Tom
Gedeon
333
16:40-16:55 WA2f3 Emotion Recognition Using The Emotiv EPOC Device Trung Pham and Dat Tran 375
16:55-17:10 WA2f4 Semantic De-biased Associations (SDA) Model to
Improve Ill-structured Decision Support
Tasneem Memon, Jie Lu and
Farookh Hussain
415
17:10-17:25 WA2f5 Cooperative Behavior Acquisition in Multi-agent
Reinforcement Learning System Using Attention Degree
Kunikazu Kobayashi, Tadashi
Kurano, Takashi Kuremoto and
Masanao Obayashi
469
17:25-17:40 WA2f6 Brain Computer Interfacing Using Humour and Memory
Recall
Ahmed Izzidien, Mohammed
Ali Roula, Sony Mallipudi, Sri
Krishna Chaitanya Ogirala and
Srikanth Bantupalli
629
Wed.
Nov 14
WA2g
Regular Session
EEG signal
Room: Al Ahood
Chair: Shaoning Pang ID
16:10-16:25 WA2g1 Modeling the Mental Differentiation Task with EEG Tan Vo, Tom Gedeon and Dat
Tran
292
16:25-16:40 WA2g2 Emotion Understanding in Movie Clips Based on EEG
Signal Analysis
Mingu Kwon and Minho Lee 334
16:40-16:55 WA2g3 EEG-Based Emotion Recognition in Listening Music by
Using Support Vector Machine and Linear Dynamic
System
Ruo-Nan Duan, Xiao-Wei
Wang and Bao-Liang Lu
432
16:55-17:10 WA2g4 EEG-based Fatigue Classification by Using Parallel
Hidden Markov Model and Pattern Classifier Combination
Hui Sun and Bao-Liang Lu 441
17:10-17:25 WA2g5 Calibration of Low Density EEG Sensor Arrays for Brain
Source Localization
Tahereh Zarghami, Hasan Mir
and Hasan Al-Nashash
258
Wed.
Nov 14
WA2h
Regular Session
Optimization and Control
Room: Al Jazi
Chair: Ping Guo ID
16:10-16:25 WA2h1 Group Sparse Inverse Covariance Selection with a Dual
Augmented Lagrangian Method
Satoshi Hara and Takashi
Washio
102
16:25-16:40 WA2h2 Matrix Pseudoinversion for Image Neural Processing Rossella Cancelliere, Mario Gai,
Thierry Artières and Patrick
Gallinari
110
16:40-16:55 WA2h3 Simultaneous Feature Selection and Clustering Using
Particle Swarm Optimization
K.P. Swetha, Devi V. Susheela 439
16:55-17:10 WA2h4 Basic Study on Particle Swarm Optimization with
Hierarchical Structure for Constrained Optimization
Problems
Kazuki Komori, Kazuhiro
Homma and Tadashi Tsubone
474
17:10-17:25 WA2h5 Data Driven System Identification Using Evolutionary
Algorithms
Awhan Patnaik, Samrat Dutta
and Laxmidhar Behera
493
17:25-17:40 WA2h6 Texture Segmentation Based on Neuronal Activation
Degree of Visual Model
Jin Ma, Ping Guo and Fuqing
Duan
204
55
ICONIP 2012
Wed.
Nov 14
WA2i
Regular Session
Learning Algorthms and Neural Models III
Room: Al Sidra
Chair: Yoshifusa Ito ID
16:10-16:25 WA2i1 Learning Attentive Fusion of Multiple Bayesian Network
Classifiers
Sepehr Eghbali, Majid Nili
Ahmadabadi, Babak Nadjar
Araabi and Maryam Mirian
123
16:25-16:40 WA2i2 Multiclass Penalized Likelihood Pattern Classification
Algorithm
Amira Talaat, Amir Atiya,
Sahar Mokhtar, Ahmed Al-Ani
and Magda Fayek
130
16:40-16:55 WA2i3 Identification of Moving Vehicle Trajectory using
Manifold Learning
Giyoung Lee, Rammohan
Mallipeddi and Minho Lee
166
16:55-17:10 WA2i4 Transductive Cartoon Retrieval by Multiple Hypergraph
Learning
Jun Yu, Jun Cheng, Jianmin
Wang, and Dacheng Tao
227
17:10-17:25 WA2i5 Iterative Appearance Learning with Online Multiple
Instance Boosting
Bo Guo, Juan Liu and Junpeng
Chen
268
17:25-17:40 WA2i6 Simultaneous Learning of Several Bayesian and
Mahalanobis Discriminant Functions by a Neural Network
with Memory Nodes
Yoshifusa Ito, Hiroyuki Izumi
and Cidambi Srinivasan
32
56
ICONIP 2012
16:10-17:40 Wednesday, 14 November Poster Session
Wed.,
Nov 14
WA2P Poster Session Outside Al Areen ball room ID
WA2P01 Multivariate Isotonic Regression Under tree Semi-order
Restrictions and Test in Multivariate Normal Distribution
Yuzhen Lu 577
WA2P02 On the Application of Bio-Inspired Algorithms in
Timetabling Problem
Daniela Oliveira Francisco
and Ivan Nunes da Silva
591
WA2P03 Neural Network Based Approach for Automotive Brake Light
Parameter Estimation
Antonio Vanderlei Ortega,
Ivan Nunes da Silva
610
WA2P04 Clock Synchronization Protocol using Resonate-and-Fire
Type of Pulse-coupled Oscillators for Wireless Sensor
Networks
Kazuki Nakada and Keiji
Miura
611
WA2P05 Orthogonalized Partial Directed Coherence for Functional
Connectivity Analysis of Newborn EEG
Amir Omidvarnia, Ghasem
Azemi, Boualem Boashash,
John M. O' Toole, Paul
Colditz and Sampsa
Vanhatalo
625
WA2P06 Evaluating SPAN Incremental Learning for Handwritten Digit
Recognition
Ammar Mohemmed, Guoyu
Lu, and Nikola Kasabov
627
WA2P07 On the Selection of Time-frequency Features for Improving
the Detection and Classification of Newborn EEG Seizure
Signals and other Abnormalities
Boualem Boashash and Larbi
Boubchir
633
WA2P08 Assessing Reliability of Substation Spare Current
Transformer System
Cristiano Melo, Renata Souza
and Liliane Salgado
638
WA2P09 Classification of Working Memory Load using Wavelet
Complexity Features of EEG Signals
Pega Zarjam, Julien Epps,
Fang Chen and Nigel Lovell
650
WA2P10 Vehicle Image Classification Based on Edge: Features and
Distances Comparison
Fabrízia Matos and Renata
Souza
661
WA2P11 Study on Supply Disruption Management of Supply Chain
Based on Case-based Reasoning
Daohai Zhang 641
WA2P12 Adaptive Backstepping Neural Control for Switched
Nonlinear Stochastic System with Time-delay Based on
Extreme Learning Machine
Yang Xiao, Fei Long,
Zhigang Zeng
671
WA2P13 Learn to Swing up and Balance a Real Pole Based on Raw
Visual Input Data
Jan Mattner, Sascha Lange
and Martin Riedmiller
111
WA2P14 A Fast Edge-Directed Interpolation Algorithm Qichong Tian, Hao Wen,
Chenhui Zhou and Wei Chen
317
WA2P15 EEG based Foot Movement Onset Detection with the
Probabilistic Classification Vector Machine
Raheleh Mohammadi, Ali
Mahloojifar, Huanhuan Chen
and Damien Coyle
318
WA2P16 Chinese How Net-based multi-factor word similarity
algorithm integrated of result modification
Benbin Wu, Jing Yang and
Liang He
237
57
ICONIP 2012
The 5th International Workshop on Data Mining and Cybersecurity
08:00-12:30 Wednesday, 14 November Oral Session
Wed.
Nov 14
Workshop 1 Room: Al Areen 1 Chair: Abdolhossein
Sarrafzadeh
ID
08:00-08:30 High Dimensional Data Analysis for Botnet Detection Jun'ichi Takeuchi
08:30-08:45 WS01 SDE-Driven Service Provision Control Gang Chen, Shaoning
Pang, Abdolhossein
Sarrafzadeh, Tao Ban and
Daisuke Inoue
211
08:45-09:00 WS02 Training Minimum Enclosing Balls for Cross Tasks
Knowledge Transfer
Shaoning Pang, Fan Liu,
Youki Kadobayashi, Tao
Ban and Daisuke Inoue
293
09:00-09:15 WS03 Classifier Ensemble Using a Heuristic Learning with
Sparsity and Diversity
Xu-Cheng Yin, Kaizhu
Huang, Hong-Wei Hao,
Khalid Iqbal and Zhi-Bin
Wang
72
09:15-09:30 WS04 TrafficS: a behavior-based network Traffic classification
benchmark system with traffic Sampling functionality
Xiaoyan Yan, Bo Liang,
Tao Ban, Shanqing Guo
and Liming Wang
116
09:30-09:45 WS05 Semantic Analysis of FBI News Reports Sarwat Nizamani and
Nasrullah Memon
289
Wed.,
Nov 14
Workshop 2 Room: Al Areen 1 Chair: Shaoning Pang ID
10:30-11:00 The First English-Persian Statistical Machine Translation Abdolhossein Sarrafzadeh
11:00-11:15 WS06 Exploring Crude Oil Impacts to Oil Stocks through
Graphical Computational Correlation Analysis
Anthony Lai, Lei Song,
Yiming Peng, Peter
Zhang, Qili Wang
and Shaoning Pang
296
11:15-11:30 WS07 Botnet Detection Based on Non-negative Matrix
Factorization and the MDL Principle
Sayaka Yamauchi,
Masanori Kawakita and
Jun’ichi Takeuchi
402
11:30-11:45 WS08 Secure Distributed Storage for Bulk Data Tadashi Minowa and
Takeshi Takahashi
513
11:45-12:00 WS09 DNS-based Defense Against IP Spoofing Attacks Eimatsu Moriyama,
Takeshi Takahashi and
Daisuke Miyamoto
564
12:00-12:15 WS10 A Malware Collection and Analysis Framework Based on
Darknet Traffic
Jungsuk Song, Jang-Won
Choi and Sang-Soo Choi
566
12:15-12:30 WS11 Behavior Analysis of Long-term Cyber Attacks in the
Darknet
Tao Ban, Lei Zhu, Junpei
Shimamura, Shaoning
Pang, Daisuke Inoue and
Kouji Nakao
570
58
ICONIP 2012
Conference Venue (Renaissance Hotel First Floor) Floor Map
Map in City Center Mall Area
59
ICONIP 2012
Discover Qatar
While in Qatar, take some time and visit some of the many beautiful and fascinating wonders of the Arab
World.
Desert Safari
For those visitors looking for a little
excitement, you need to experience
desert safari. Just an hour south of Doha
is the start of the Empty Quarter and our
enormous sand dunes! Expert local
drivers will take you dune bashing for
some fast paced thrills and stop to see
the beautiful Inland Sea.
Inland Sea
Locally called Khor al-Daid, this
massive inland sea is connected to the
Arabian Gulf by a narrow inlet that
shares the southern border with Saudi
Arabia. Located over an hour's drive
south of Qatar, an additional half-hour
dune bashing through the entrance of the
Empty Quarter is required to reach the
shallow blue sea. Filled with hammour,
small sharks, and porpoises, it is one of
the most popular weekend getaways in
Qatar.
The Pearl
Over 32 new kilometers of coastline was
created when Qatar began building its
first artificial island residential area. The
Pearl features a large range of luxury
villas, apartments, five-star hotels and
over two million square meters of
international retail, restaurants, cafes and
entertainment. Eight other private
islands will be for sale to private owners.
The Pearl is home to the finest shopping
and dining in all of Qatar.
60
ICONIP 2012
The Corniche
The waterfront promenade encircling
Doha Bay, the Doha Corniche is a
major thoroughfare and entertainment
area of Qatar. Every morning joggers
get their exercise, and every evening
the Corniche and its connecting park fill
with families enjoying the magical
downtown lights. Cafes and coffee
shops can be found alongside the
traditional fishing Dhows along the
seven kilometer stretch.
Museum of Islamic Art
Nestled on a man-made island in the
middle of Doha harbor, this stunning
I.M. Pei designed museum is a unique
storehouse dedicated to all facets of
Islamic art. The finest examples of
manuscripts, ceramics, and textiles
from every Muslim country in the
world fill the galleries. Included in the
free admission is access to the extensive
libraries, along with the best view of the
West Bay and the Corniche.
Souq Waqif
Recently restored to its former glory,
this major outdoor market is the place
to go for tourists and locals alike for
spices, handicrafts, and souvenirs.
Along the narrow alleys filled with
varied shops and art galleries are a
collection of restaurants representing
cuisines from all over the world. The
nearby Fanir Islamic Center and its
piercing spiral mosque is a great place
to learn about Islam and the Arabic
people.
61
ICONIP 2012
Cultural Village
Doha Cultural Village is a mini-
township of sorts. Situated in the scenic
West Bay area of Doha, this massive
complex is the focal point of culture
and entertainment in the city. Sprawled
across 99 acres, it comprises multiple
theaters, halls, stages, children's
playgrounds and food parks. Concerts,
plays, dance shows, band performances,
movie screenings and plethora of
festivals galore at Cultural Village. The
hugely popular Doha Tribeca Film
Festival is held here. Teeming millions
grace the venue to attend this gala
event. You, too, shouldn't miss it!
Education City
Education City is an initiative of Qatar
Foundation for Education, Science and
Community Development. Located on
the outskirts of Doha, the capital of
Qatar, Education City covers 14 square
kilometers and houses educational
facilities from school age to research
level and branch campuses of some of
the world's leading universities.
Education City aims to be the center of
educational excellence in the region,
instructing students in fields of critical
importance to the Gulf Cooperation
Council region. It is also conceived of as a forum where universities share research and forge
relationships with businesses and institutions in public and private sectors. Six US universities
have branch campuses at Education City. They are: Virginia Commonwealth University in Qatar,
Weill Cornell Medical College in Qatar, Texas A&M University at Qatar, Carnegie Mellon
University in Qatar, Georgetown University School of Foreign Service in Qatar, Northwestern
University in Qatar and one branch campus of UK university: University College London in
Qatar. Several centers based at Education City focus on science and research. These include
Qatar Science & Technology Park (QSTP), a state-of-the-art facility comprising 45,000 square
meters of office and laboratory space. QSTP aims to fuel Qatar’s knowledge economy by
encouraging companies from around the world to develop and commercialize their technology in
Qatar, and by helping entrepreneurs to launch start-up technology businesses. Education City
also hosts the Qatar Foundation for Education, Science and Community Development, a private,
chartered, non-profit organization in the state of Qatar, founded in 1995 by decree of His
Highness Sheikh Hamad Bin Khalifa Al Thani, Emir of Qatar.
62