1. technology and computing

UPCOMING CONFERENCES
Guilin, China, February 28-March 2, 2015
Conference Name
2015 2nd International Conference on
Electronics Engineering and Power
Engineering
(CEEPE-II 2015)
2015 International Conference on Smart
Manufacturing
(ICOSM 2015)
2015 International Conference on Information
Management
(ICIM 2015)
Conference Website
Submission Deadline & Email
www.ceepe.net
December 15, 2014
ceepe@saise.org
www.icosm.org
December 15, 2014
icosm@saise.org
www.icim.org
December 20, 2014
icim@saise.org
Conference Website
Submission Deadline & Email
www.ceeit.net
January 5, 2015
ceeit@saise.org
www.icbcb.org
January 5, 2015
www.icmai.org
January 5, 2015
icmai@saise.org
Conference Website
Submission Deadline & Email
www.icsis.org
February 15, 2015
icsis@saise.org
www.icoee.org
February 15, 2015
www.icrai.org
February 28, 2015
icrai@saise.org
Hong Kong, China, March 12-13, 2015
Conference Name
2015 2nd International Conference on
Electrical Engineering and Information
Technology
(CEEIT 2015)
2015 3rd International Conference on
Bioinformatics and Computational Biology
(ICBCB 2015)
2015 International Conference on
Measurement, Automation and Instrumentation
(ICMAI 2015)
icbcb@saise.org
Las Vegas, USA, May 09-10, 2015
Conference Name
2015 International Conference on Software and
Information Systems
(ICSIS 2015)
2015 International Conference on Electronics
Engineering
(ICOEE 2015)
2015 International Conference on Robotics and
Artificial Intelligence
(ICRAI 2015)
icoee@saise.org
2014 International Conference on Computer Engineering (ICOCE 2014)
Contents
Contents ············································································································1
Welcome Page ·····································································································2
Conference Venue·································································································3
Simple Version of Conference Schedule ······································································4
Introduction to Keynote Speakers ··············································································5
Schedule of Sessions ·····························································································7
Poster Session ····································································································20
Call for Papers····································································································26
1
2014 International Conference on Computer Engineering (ICOCE 2014)
Welcome to ICOCE 2014 in Shenzhen, China
Welcome to 2014 International Conference on Computer Engineering (ICOCE 2014). ICOCE 2014 has 2
workshops, they are ICNT 2014 (2014 International Conference on Network Technologies) and ICAAI 2014
(2014 International Conference on Advances in Artificial Intelligence). The aim of ICOCE 2014 and its
workshops is to present the latest research and results of scientists related to computer engineering, network
technologies, and artificial intelligence. This conference provides opportunities for delegates from different
areas to exchange new ideas and application experiences face to face, to establish business or research
relations and to find global partners for future collaboration. We hope that the conference can make
significant contribution to these up-to-date scientific fields. And wish all respected authors and listeners a
nice trip in Shenzhen, China.
Warm Tips:
All papers of ICOCE 2014 and ICNT 2014, both invited and contributed, have been reviewed by two or three experts
from the PC. After a careful reviewing process, all registered and presented paper will be published in WIT
Transactions on Information and Communication Technologies (ISSN: 1743-3517), which will be indexed by EI
Compendex, Scopus and ISI.
All accepted and registered papers of ICAAI 2014 will be published together with ISCBI, and will be submitted to be
reviewed by the IEEE Xplore and Computer Society Digital Library (CSDL).
 Get your presentation PPT prepared and print out the notification letter before you leave for Shenzhen,
China.
 Pick up the conference materials at the reception desk of ICOCE 2014 in the lobby of Lushan Hotel on
November 09, 2014.
 Please attend the conference and arrive the Conference Room before 9:00 a.m. in formal attire on
November 10, 2014
 There will be a group photo and coffee break between 10:45-11:00, November 10; every attendee will
be invited to come to the platform to take group photo.
 Copy your PPT to the conference computer before your session begins. One best presentation will be
selected from each session, and the best one of each session will be announced and awarded the
certificate at the end of each session.
 If you didn’t put a formal photo in your registration from, please bring a one-inch formal photo to the
venue.
2
2014 International Conference on Computer Engineering (ICOCE 2014)
Conference Venue(会议地点)
Lushan Hotel, Shenzhen
Shenzhen, China
（深圳庐山酒店，深圳，中国）
Website（网址）: www.shenzhenlushanhotel.com
Address: No. 3019, Chunfeng Road, Luohu District, Shenzhen, China
地址：中国广东省深圳市罗湖区春风路 3019 号
电话(TEL)：（86）0755-82338888 80308031
3
2014 International Conference on Computer Engineering (ICOCE 2014)
Simple Version of Conference Schedule
Dates
November 09, 2014(Sunday )
Venue
Items
In the lobby of Lushan hotel
Participants Registration and Conference kits
(庐山酒店大堂)
Collection
10:00AM-12:00AM
13:30PM-16:00PM
th
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
(9:00AM-10:45AM)
(5 楼九江厅)
Opening Ceremony and Keynote Speeches
Keynote Speech I: Prof. Dr. Thomas Fang Zheng
Keynote Speech II: Prof. Chin-Chen Chang
th
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
(10:45AM-11:00AM)
(5 楼九江厅)
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
Paper Presentation Session I (6 papers)
(11:00AM-12:15AM)
(5 楼九江厅)
Session Chair: Prof. Wenyu Zhang
November 10, 2014 (Monday)
Fangting Restaurant, 2nd floor of Lushan
(12:15AM-13:30PM)
Hotel(2 楼芳庭餐厅)
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
Paper Presentation Session II (9 papers)
(13:30PM -15:20PM)
(5 楼九江厅)
Session Chair: Prof. Vania Joloboff
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
(15:20PM -15:35PM)
(5 楼九江厅)
November 10, 2014 (Monday)
Jiujiang Conference Room, 5 floor
Paper Presentation Session III (9 Papers)
(15:35PM -17:25PM)
(5 楼九江厅)
Session Chair: TBA
November 10, 2014 (Monday)
Fangting Restaurant, 2nd floor of Lushan
(17:30PM -19:00PM)
Hotel(2 楼芳庭餐厅)
Coffee Break and Group Photo
th
Lunch
th
th
Coffee Break
th
4
Dinner Banquet
2014 International Conference on Computer Engineering (ICOCE 2014)
Introduction to Keynote Speakers
Prof. Chin-Chen Chang (张真诚教授）
Feng Chia University, Taiwan （逢甲大学）
Biography: Professor Chin-Chen Chang obtained his Ph.D. degree in computer engineering from National
Chiao Tung University. His first degree is Bachelor of Science in Applied Mathematics and master degree is
Master of Science in computer and decision sciences. Both were awarded in National Tsing Hua University. Dr.
Chang served in National Chung Cheng University from 1989 to 2005. His current title is Chair Professor in
Department of Information Engineering and Computer Science, Feng Chia University, from Feb. 2005.
Prior to joining Feng Chia University, Professor Chang was an associate professor in Chiao Tung University,
professor in National Chung Hsing University, chair professor in National Chung Cheng University. He had also
been Visiting Researcher and Visiting Scientist to Tokyo University and Kyoto University, Japan. During his
service in Chung Cheng, Professor Chang served as Chairman of the Institute of Computer Science and
Information Engineering, Dean of College of Engineering, Provost and then Acting President of Chung Cheng
University and Director of Advisory Office in Ministry of Education, Taiwan.
Professor Chang's specialties include, but not limited to, data engineering, database systems, computer
cryptography and information security. A researcher of acclaimed and distinguished services and contributions to
his country and advancing human knowledge in the field of information science, Professor Chang has won many
research awards and honorary positions by and in prestigious organizations both nationally and internationally.
He is currently a Fellow of IEEE and a Fellow of IEE, UK. And since his early years of career development, he
consecutively won Institute of Information & Computing Machinery Medal of Honor, Outstanding Youth Award of
Taiwan, Outstanding Talent in Information Sciences of Taiwan, AceR Dragon Award of the Ten Most Outstanding
Talents, Outstanding Scholar Award of Taiwan, Outstanding Engineering Professor Award of Taiwan, Chung-Shan
Academic Publication Awards, Distinguished Research Awards of National Science Council of Taiwan,
Outstanding Scholarly Contribution Award of the International Institute for Advanced Studies in Systems
Research and Cybernetics, Top Fifteen Scholars in Systems and Software Engineering of the Journal of Systems
and Software, Top Cited Paper Award of Pattern Recognition Letters, and so on. On numerous occasions, he was
invited to serve as Visiting Professor, Chair Professor, Honorary Professor, Honorary Director, Honorary
Chairman, Distinguished Alumnus, Distinguished Researcher, Research Fellow by universities and research
institutes. He also published over serval hundred papers in Information Sciences. In the meantime, he
participates actively in international academic organizations and performs advisory work to government agencies
and academic organizations.
Prof. Dr. Thomas Fang Zheng (郑方教授）
Tsinghua University, China (清华大学）
Biography: Dr. Thomas Fang Zheng is a full research professor and Vice Dean of the Research Institute of
Information Technology (RIIT), Tsinghua University (THU), and Director of the Center for Speech and Language
Technologies (CSLT), RIIT, THU.
Since 1988, he has been working on speech and language processing. He has been in charge of, or undertaking
as a key participant, the R&D of more than 30 national key projects and international cooperation projects, and
received awards for more than 10 times from the State Ministry (Commission) of Education, the State Ministry
(Commission) of Science and Technology, the Beijing City, and others. So far, he has published over 200 journal
and conference papers, 11 (3 for first author) of which were titled the Excellent Papers, and 11 books (refer to
http://cslt.riit.tsinghua.edu.cn/~fzheng for details).
5
2014 International Conference on Computer Engineering (ICOCE 2014)
He has been serving in many conferences, journals, and organizations. He is an IEEE Senior member, a CCF
(China Computer Federation) Senior Member, an Oriental COCOSDA (Committee for the international
Coordination and Standardization of speech Databases and input/output Assessment methods) key member, an
ISCA member, an APSIPA (Asia-Pacific Signal and Information Processing Association) member, a council
member of Chinese Information Processing Society of China, a council member of the Acoustical Society of
China, a member of the Phonetic Association of China, and so on.
He serves as Council Chair of Chinese Corpus Consortium (CCC), a Steering Committee member and a BoG
(Board of Governors) member of APSIPA, Vice President – Institutional Relations and Education Program (Term
2013-2014) of APSIPA, Chair and Secretary General of the Steering Committee of the National Conference on
Man-Machine Speech Communication (NCMMSC) of China, head of the Voiceprint Recognition (VPR) special
topic group of the Chinese Speech Interactive Technology Standard Group, Vice Director of Subcommittee 2 on
Human Biometrics Application of Technical Committee 100 on Security Protection Alarm Systems of
Standardization Administration of China (SAC/TC100/SC2), a member of the Artificial Intelligence and Pattern
Recognition Committee of CCF.
He is an associate editor of IEEE Transactions on Audio, Speech, and Language Processing, a member of
editorial board of Speech Communication, a member of editorial board of APSIPA Transactions on Signal and
Information Processing, an associate editor of International Journal of Asian Language Processing, a series editor
of SpringerBriefs in Signal Processing, and a member of editorial committee of the Journal of Chinese Information
Processing.
He ever served as co-chair of Program Committee of International Symposium on Chinese Spoken Language
Processing (ISCSLP) 2000, member of Technical Committee of ISCSLP 2000, member of Organization
Committee of Oriental COCOSDA 2000, member of Program Committee of NCMMSC 2001, member of Scientific
Committee of ISCA Tutorial and Research Workshop on Pronunciation Modeling and Lexicon Adaptation for
Spoken Language Technology 2002, member of Organization Committee and international advisor of Joint
International Conference of SNLP-O-COCOSDA 2002, General Chair of Oriental COCOSDA 2003, member of
Scientific Committee of International Symposium on Tonal Aspects of Languages (TAL) 2004, member of
Scientific Committee and Session Chair of ISCSLP 2004, chair of Special Session on Speaker Recognition in
ISCSLP 2006, Program Committee Chair of NCMMSC 2007, Program Committee Chair of NCMMSC 2009,
Tutorial Co-Chair of APSIPA ASC 2009, Program Committee Chair of NCMMSC 2011, general co-chair of APSIPA
ASC 2011, and APSIPA Distinguished Lecturer (2012-2013).
He has been also working on the construction of "Study-Research-Product" channel, devoted himself in
transferring speech and language technologies into industries, including language learning, embedded speech
recognition, speaker recognition for public security and telephone banking, location-centered intelligent
information retrieval service, and so on. Now he holds over 10 patents in various aspects of speech and language
technologies.
He has been supervising tens of doctoral and master students, several of who were awarded, and therefore he
was entitled Excellent Graduate Supervisor. Recently, he received 1997 Beijing City Patriotic and Contributing
Model Certificate, 1999 National College Young Teacher (Teaching) Award issued by the Fok Ying Tung
Education Foundation of the Ministry of Education (MOE), 2000 1st Prize of Beijing City College Teaching
Achievement Award, 2001 2nd Prize Beijing City Scientific and Technical Progress Award, 2007 3rd Prize of
Science and Technology Award of the Ministry of Public Security, and 2009 China "Industry-University-Research
Institute" Collaboration Innovation Award.
6
2014 International Conference on Computer Engineering (ICOCE 2014)
Schedule of Sessions
November 10, Morning
Venue: Jiujiang Conference Room, 5th floor（5 楼九江厅）
Time: 9:00 a.m.-12:15 a.m.
9:00a.m.-9:05a.m.
9:05a.m.-9:55a.m.
Opening Remarks
Prof. Chin-Chen Chang
Keynote Speech I
Prof. Dr. Thomas Fang Zheng (郑方教授）
Tsinghua University, China (清华大学）
Topic of Keynote Speech: Time-Varying Robustness for Speaker Recognition
Abstract: Speaker recognition applications are becoming more and more popular.
However, in practical applications many factors may affect the performance of
systems.
In this talk, a general introduction to speaker recognition will be presented, including
definition, applications, category, and key issues in terms of research and
application. Robust speaker recognition technologies that are useful to speaker
recognition applications will be briefed, including cross channel, multiple speaker,
background noise, emotions, short utterance, and time-varying (or aging). Recent
research on time-varying robust speaker recognition will be detailed.
Performance degradation with time varying is a generally acknowledged
phenomenon in speaker recognition and it is widely assumed that speaker models
should be updated from time to time to maintain representativeness. However, it is
costly, user-unfriendly, and sometimes, perhaps unrealistic, which hinders the
technology from practical applications. From a pattern recognition point of view, the
time-varying issue in speaker recognition requires such features that are
speaker-specific, and as stable as possible across time-varying sessions. Therefore,
after searching and analyzing the most stable parts of feature space, a
Discrimination-emphasized Mel-frequency-warping method is proposed. In
implementation, each frequency band is assigned with a discrimination score, which
takes into account both speaker and session information, and Melfrequency-warping is done in feature extraction to emphasize bands with higher
scores.
Experimental results show that in the time-varying voiceprint database, this method
can not only improve speaker recognition performance with an EER reduction of
19.1%, but also alleviate performance degradation brought by time varying with a
reduction of 8.9%. This conclusion applies to some other databases where no
recording time information is transcribed.
Keynote Speech II
9:55a.m.-10:45a.m
Prof. Chin-Chen Chang (张真诚教授）
Feng Chia University, Taiwan （逢甲大学）
Topic of Keynote Speech: Hiding Information in a Digital Image
Abstract: Information Hiding is the science of secret message delivery using cover
7
2014 International Conference on Computer Engineering (ICOCE 2014)
media. A digital image is a flexible medium used to carry a secret message because
the slight modification of a cover image is hard to distinguish by human eyes.
In this talk, I will introduce three methods: Kim et al.'s method, Zhang and Wang’s
method and Sudoku solutions. A selected Sudoku solution is used to guide cover
pixels’ modification in order to imply secret data. Because the number of possible
Sudoku solutions is very large, the proposed method is more secure than Kim et al.'s
method and Zhang and Wang’s method. From the experimental results, the visual
quality of stego images produced by the Sudoku method is higher than 44 dB in
average, which is slightly less than that of related works; however, the embedding
capacity of the proposed method is 1.5 bit per pixel, which is greater than that of the
related works.
Coffee Break and Group Photo
10:45a.m.-11:00a.m.
Session I- Pattern Recognition and Multimedia Technology
(6 papers, 12 minutes for each paper, including Q&A)
Venue: Jiujiang Conference Room, 5th floor（5 楼九江厅）
Time: 11:00a.m.-12:15a.m.
Session Chair: Prof. Wenyu Zhang
Presenter: Jie ZHANG
From: Nagoya University, Japan
E-118E
11:00-11:12
Title: Detecting Reused Elements in Presentation Slides
Authors: Jie ZHANG and Chuan XIAO
Abstract: Slide presentations have become a ubiquitous tool for business and
educational purposes. Instead of starting from scratch, slide composers tend to make
new presentation slides by browsing existing slides and reusing materials from them.
In this paper, we investigate the problem of reused element detection in presentation
slides. We develop respective techniques to identify both textual and visual elements
that have been reused across multiple presentation files. Experiments are performed
to evaluate the effectiveness of the proposed methods.
8
2014 International Conference on Computer Engineering (ICOCE 2014)
Presenter: Ran Shao
From: Queen’s University Belfast, Northern Ireland
E-212E
11:12-11:24
Title: Optimizations of the GPU-based Three-Dimensional FDTD Program with
CPML boundary condition on Kepler Architecture GPU
Authors: Ran Shao, David Linton, Ivor Spence, Ning Zheng
Abstract: An effective way to accelerate the Finite-difference time-domain (FDTD)
method is the use of a Graphic Processing Unit (GPU). This paper describes an
implementation of the three dimensional FDTD method with CPML boundary
condition on a Kepler (GK110) architecture GPU. We optimize the FDTD domain
decomposition method on Kepler GPU. And then, several Kepler-based optimizations
are studied and applied to the FDTD program. The optimized program achieved up to
270.9 times speedup compared to the CPU sequential version. The experiments show
that 22.2% of the simulation time is saved compared to the GPU version without
optimizations. The solution is also faster than previous works.
Presenter: Haoting Zhang
From: Guanghua International School of Shanghai, China
Title: Predicting the Treatment Effect in Diabetes Patients Using Classification
Models
Authors: Haoting Zhang, Lingyun Shao, Chengyu Xi
E-213E
11:24-11:36
E-216E
11:36-11:48
Abstract: The objective of this study is to explore the prediction of treatment effect
in diabetes patients using classification models, especially Decision Tree. The data of
the diabetic patients are from the Health Facts database of the United States. Models
(mainly Decision Tree, and also Rule Induction and Naïve Bayes) are constructed
using RapidMiner 5.3, so that the predictors will be searched and used to predict
whether the diabetic patients will be readmitted within 30 days. In this way, every
individual patient can be assessed according to their different characteristics, and
their treatment can be personalized accordingly to decrease the chances of
readmitting within 30 days. Another finding is that, medical management, which isn’t
directly related to the disease itself, can actually make a big difference in therapeutic
effect. In conclusion, using classification models such as Decision Tree is an effective
way to predict and personalize treatment effect of patients.
Presenter: Sang-Min Song
From: Tongmyong University,Korea
Title: GPU-based Parallel Processing for Real-time Skinning for Massive Crowd
Animation
Authors: Sang-Min Song and Soo-Yol Ok
9
2014 International Conference on Computer Engineering (ICOCE 2014)
Abstract: In this paper, we propose a keyframe animation for 3-D characters based
on skeleton data. GPU shader has been generally employed for efficient character
skinning [1]. The most expensive computation for animating characters with
skeletons is required for bone update and skinning. The previous shader-based
approaches exploited the GPU parallelism only for skinning. However, the
computation for updating the bone structure has not been efficiently optimized with
the GPU parallelism. The method proposed in this paper, however, utilized
general-purpose parallel programming technologies with GPU to optimize both the
skinning and bone computation.
Presenter: Alice J. Lin
From: Marshall University, USA
Title: Automatic Placement/Arrangement of Underneath Bone Structures for 3D
Facial Expressions and Animations
E-326E
11:48-12:00
Authors: Alice J. Lin and Fuhua (Frank) Cheng
Abstract: This paper presents a new method for automatically setting the bones in a
facial/head model to speed up the rigging process of a human face. To accomplish
this, vertices of the face/head are grouped. The average distance between pairs of
vertices is used to place the head bones. To set the bones for a face with
multi-density, the mean value of the vertices in a group is measured. The method
works on any particular person’s face/head model quickly and effectively, and
provides a powerful means for generating facial expressions and animations. The
time saved with the method is significant. Although we focus on human faces in this
work, the concepts presented here are flexible enough to be used on non-human
characters as well.
Presenter: Chattrakul Sombattheera
From: Mahasarakham University, Thailand
Title: A Load Balancing in Task Allocation of a Multiagent System
Authors: Chattrakul Sombattheera
ICA2014-1-005
12:00-12:12
Abstract: Task allocation is an important area of research in multiagent systems
because it can efficiently solve complexity in real world problem, such as power grid
systems, where a power plant (source) can be considered as an agent. Agents’ task is
to provide consistent supply to consumers, whose needs vary over the time. They
need to jointly plan in order to find appropriate schedules which associate each agent
to customers over the course of time such that consistent supplies are provided to
customers. This research formulates a new task allocation problem which can be
solved with two phases: i) find a (near) optimal plan, and i) verify whether the plan is
stable. These provide extra benefit to the solution that a stable plan is also (near)
optimal in terms of efficiency.
10
2014 International Conference on Computer Engineering (ICOCE 2014)
Lunch Time
12:15 a.m.-13:30 p.m.
Fangting Restaurant, 2nd floor of Lushan Hotel (2 楼芳庭餐厅)
Schedule of the Sessions
November 10, Afternoon
Session Chair
Session II (13:30 p.m.-15:20 p.m.)
Prof. Vania Joloboff
Coffee Break (15:20 p.m.-15:35 p.m.)
TBA
Session III (15:35 p.m.-17:25 p.m.)
Session II- Pattern Recognition and Distributed Systems
(9 Papers, 12 minutes for each paper, including Q&A)
Venue: Jiujiang Conference Room, 5th floor（5 楼九江厅）
Time: 13:30 p.m.-15:20 p.m.
Session Chair: Prof. Vania Joloboff
E-117E
13:30-13:42
Presenter: Payungsak Kasemsumran
From: Chiang Mai University, Chiang Mai, Thailand
Title: Face Recognition Using String Grammar Nearest Neighbor Technique
Authors: Payungsak Kasemsumran, Sansanee Auephanwiriyakul, and Nipon
Theera-Umpon
Abstract: Face recognition has become one of the important biometrics in many
applications. However, there is a problem of collecting more than one image per
person in the training data set, the so-called “one sample per person problem”.
11
2014 International Conference on Computer Engineering (ICOCE 2014)
Hence in this paper, we develop a face recognition system with a string grammar
nearest neighbor (sgNN) to cope with the problem. We implement our system in
three data sets, i.e., ORL, MIT-CBCL, and Georgia Tech databases. The recognition
rates of the test data set from three databases are 88.25%, 87.50%, and 70.71%,
respectively..
Presenter: Vania Joloboff
From: East China Normal University, China and INRIA, France
Title: Automated Generation of Instruction Set Simulator from Specification
E-209E
13:42-13:54
Authors: Shenpeng Liu, Vania Joloboff, Fei He
Abstract: We present here an architecture compiler, namely a software that takes as
input the description of a processor architecture as it is available from the vendors
on their web site, and generates an instruction set simulator for that processor,
which can be readily integrated into a simulation framework. This architecture
compiler extracts relevant information from the .pdf file, translated into an XML
specification. After further XML transformations, the C++ code of the simulator is
finally generated. The paper details the approach and the results for the ARM
Version 7 processor, that is suitable for other architectures as well.
Presenter: Semin Kang
From: Tongmyong University, Korea
Title: An Improved Sequential Constructive Crossover for Evolutionary Approach
to Travelling Salesman Problem
E-215E
13:54-14:06
E-217E
14:06-14:18
Authors: Semin Kang, Sung-Soo Kim, Young-Min Kang
Abstract: In this paper, we proposed an improved crossover method for genetic
approach to travelling salesman problem (TSP). Since the valid solution of TSP is
an ordered permutation, traditional crossover methods do not guarantee the valid
off-springs and fast convergence. Therefore, researchers have proposed special
crossover, and it is known that SCX is superior to other methods in the aspect of
convergence speed and fitness of the genes. In this paper, we extend the SCX to
have bidirectional and circular search properties in the off-spring construction. The
proposed BCSCX shows the better convergence speed and even better solution that
those of SCX in the empirical experiments.
Presenter: Tae-Hyeong Kim
From: Tongmyoung University, Korea
Title: An Efficient Simulation of Massive Crowd with Navigation and Affordance
Fields
Authors: Tae-Hyeong Kim, Young-Min Kang, Soo-Yol Ok
12
2014 International Conference on Computer Engineering (ICOCE 2014)
Abstract: In this paper, we propose a simulation method for massive crowd
behavior. The movement of each agent is determined by scalar energy fields, and the
fields are expressed as images in order to improve the computational efficiency. The
energy fields in our method are composed of navigation fields and affordance fields.
The navigation fields are applied to all agents, and each agent has its own
affordance field. The image-based approach can exploit the GPU functionalities to
manipulate the fields, and the affordance field model makes it possible to transform
the collision handling problem into a simple navigation field generation. The
image-based navigation field can resolve the collision without globally considering
the relations between agents. The efficient collision handling enables the proposed
method to simulate massively large amount of agents in real-time
Presenter: Dong-Min Woo
From: Myongji University, Korea
Title: Clustering of Optical Flow Using Centroid Neural Network for Motion
Tracking of Moving Vehicles
E-310E
14:18-14:30
Authors: Dong-Min Woo, Seung Soo Ha, and Wonha Kim
Abstract: Motion tracking is one of the most practical applications of computer
vision in real life. In this paper, we highlight a new application for tracking motion
and estimating the velocity of the moving vehicle in terms of clustering of optical
flows. A centroid neural network with a metric utilizing optical flow is employed to
group pixels of moving vehicles from traffic images, and to generate blobs of
moving vehicles. To verify the best optical flow, we utilize RANSAC (RANdom
SAample Consensus) by determining the best model that optimally fits the flows.
Experiments are performed with various traffic images. The results show that the
proposed method can efficiently segment moving vehicles out of background and
accurately estimate the velocity of moving vehicle.
Presenter: Yanbo J. Wang
From: China Minsheng Bank, China
Title: Application of Text Mining for Customer Evaluations in Commercial
Banking
E-312E
14:30-14:42
Authors: Jing Tan,Xiaojiang Du, Pengpeng Hao,and Yanbo J. Wang
Abstract: Nowadays customer attrition is increasingly serious in commercial banks.
To combat this problem roundly, mining customer evaluation texts is as important as
mining customer structured data. In order to extract hidden information from
customer evaluations, Textual Feature Selection, Classification and Association Rule
Mining are necessary techniques. This paper presents all three techniques by using
Chinese Word Segmentation, C5.0 and Apriori, and a set of experiments were run
based on a collection of real textual data that includes 823 customer evaluations
taken from a Chinese commercial bank. Results, consequent solutions, some advice
for the commercial bank are given in this paper.
13
2014 International Conference on Computer Engineering (ICOCE 2014)
Presenter: Najla Sassi
From: SOIE Laboratory, Tunisia
Title: Using Multi-Agent System to solve Distributed Constraint Optimization
Problems
ICA2014-1-002
14:42-14:54
Authors: Najla Sassi;Khaled Ghédira; Kais Ben Salah
Abstract: Many problems in multi-agent systems can be described as Distributed
Constraint Satisfaction Problems (D CSPs), where the goal is to find a set of
assignments to variables that satisfies all constraints among agents. However, when
real-life application problems are formalized as DCSPs, they are often
over-constrained and have no solution that satisfies all constraints. Moreover, the
globalization of the economy and democratization of the Internet, boosted by the
huge growth in information and communication technologies, have largely
contributed to the expansion of numerous distributed architectures. Thus this paper
provides a new distributed management and decision support system suitable to
these interdependencies and these complex environments. We present a Distributed
Optimization under Constraints Basic Relax (DOC-BRelax) as a new framework for
dealing with over-constrained situations. We also present a version of this
framework called DOC-MaxRelax and a new algorithm for solving Distributed
Maximal Constraint Satisfaction Problems (DMCSPs).
Presenter: Qingzhuang Zhao
From: Shenzhen Graduate School, Peking University, China
Title: IPTV Video Surveillance Based on Network Coding Distributed File System
ICNT2014-2-211
14:54-15:06
Authors: Qingzhuang Zhao, Kun Li, Hui Li, Yunmin Wang and Haipeng You
Abstract: Video Surveillance is taking an important role in daily life and the social
development,as the popular and application of high definition video the storge
problem of video with so large scale is more and more serious.We proposed an
approach of video surveillance NCIVS based on Network Coding Distributed File
System(NCDFS),a system that Self-repair Code Redundancy Theory, the most
advanced theory of cloud storge area , is applied.And Converged Network Video
Broadcast and Control System for IPTV is used in the system ,as a result ,video
would be played via Internet on different operating system .The experimental result
demonstrate that NCIVS greatly saved storge space and improved the user
experience.
E-313E
15:06-15:18
Presenter: Yanbo J. Wang
From: China Minsheng Bank, China
Title: Research on Micro-blog Character Analysis based on Naïve Bayes
14
2014 International Conference on Computer Engineering (ICOCE 2014)
Authors: Yun Liu,Tong Liu,and Yanbo J. Wang
Abstract: With the development of Information Technology, people have entered
the era of Big Data, and the demand for intelligent information is more intense. How
to make computer provide more personalized and efficient service for all walks of
life, is something worth exploring. In this paper, we aim to predict user’s character
by analyzing the textual content of his/her micro-blog, which is the foundation of
Personalized Service. Our study describes the method of creating a prediction model
about user’s character by using Bayesian algorithms. Experimental results show that
the Naïve Bayes approach is a valid and promoted analytic method in micro-blog
character analysis.
Coffee Break
15:20 p.m.-15:35 p.m.
Session III- Computer Networking and Communications
(9 papers, 12 minutes for each paper, including Q&A)
Venue: Jiujiang Conference Room, 5th floor（5 楼九江厅）
Time: 15:35 p.m.-17:25 p.m.
Session Chair: TBA
Presenter: Yan Gao
From: Zhengzhou Information Science and Technology Institution, China
Title: A Security Routing Model Based on Trust for Medical Sensor Networks
E-106E
15:35-15:47
Authors: Yan Gao and Wenfen Liu
Abstract: With the development of medical sensor networks, the security has
becomes an important issue. In this paper, a security routing model based on trust is
proposed for medical sensor networks. To measure the credibility of each path from
the source master node to the base station, a calculation method with Tsallis entropy
is put forward on the basis of trust values of intermediate master nodes in the path.
With the properties of Tsallis entropy, path Tsallis entropy can comprehensively
reflect the uncertainty of all the intermediate nodes in each path. Based on this, the
trust value of each path is obtained. Therefore the path with the maximum trust
value is selected to transfer the data from the multiple paths. Simulation
experiments show that the proposed model enables the transfer to effectively avoid
15
2014 International Conference on Computer Engineering (ICOCE 2014)
such paths containing the low-trust nodes, so that the packet successful delivery rate
has a great improvement and the ability against malicious attacks is also enhanced.
Presenter: Supeng Huang
From: Beijing University of Posts and Telecommunications(BUPT),China
Title: A Novel Resource Allocation Scheme based on Resource Efficiency for
LTE-A System
Authors: Supeng Huang, Xibo Wang, Chaowei Wang,Weidong Wang, Yinghai
Zhang
E-301E
15:47-15:59
Abstract: Resource allocation in Orthogonal Frequency Division Multiple (OFDM)
system is implemented by assigning subcarriers and power to all users in order to
achieve large throughput and high energy efficiency. The base station acts as
scheduler, which aims at scheduling active users as many as possible and
maximizes the system throughput. Conventional schemes allocate resource to user
mainly based on Quality of Service (QoS), spectral efficiency or maximum
throughput without considering the resource efficiency. These schemes achieve
compromise between maximized throughput and user fairness. However, there is
excessive resource occupied. In this paper, a novel resource allocation algorithm
based on proportional fairness (PF) algorithm is proposed. This novel algorithm
mainly promotes the resource efficiency for LTE or LTE-A system during resource
allocation. Meanwhile, the scheme takes user fairness and QoS into consideration
and approaches the global optimal solution. According to simulation, the proposed
algorithm achieves higher resource utilities efficiency and schedule more active
users with the limit resource.
Presenter: Pengfei Shi
From: Beijing Institute of Technology, China
E-302D
15:59-16:11
Title: Robustness of fractional order for FRFT-OFDM systems
Authors: Pengfei Shi, Dongjie Qi, Miao Li and Hao Huan
Abstract: Fractional Fourier transform (FRFT) has been widely used in orthogonal
frequency division (OFDM) systems to combat the doubly dispersive channels. The
sensitivity of the fractional order is a serious problem. In this paper, we derive
closed form of the variable order and its optimal value based on the mathematical
expression in the FRFT-OFDM systems. The theoretical results show that the
optimal fractional order for the FRFT-OFDM system is 0.5. Simulation results
verify the robustness of fractional order 0.5 in the FRFT-OFDM systems.
E-309E
16:11-16:23
Presenter: Min Xiao
From: Xiamen University of Technology, China
Title: Design of Finite-Length Rate-Compatible LDPC Codes
16
2014 International Conference on Computer Engineering (ICOCE 2014)
Authors: Min Xiao
Abstract: This paper considers rate-compatible puncturing for finite-length low-density
parity-check (LDPC) codes. Among the existing systematic puncturing methods, the
grouping and sorting algorithm (GSA) stands out for its good performance and easy
implementation, but as is proven in this paper, there exists a limit on the amount of
puncturing that can be done, which restricts the range of the achievable code rates as well
as the choice of the mother code. A new puncturing algorithm with better flexibility is
developed. The new algorithm can be generally applied to an arbitrary irregular or regular
LDPC code to obtain a code rate arbitrarily close to 1, and at the same time to achieve
performance that is superior to the GSA.
Presenter: Di Liu
From: Beijing University Of Posts and Telecommunications（BUPT）, China
Title: Adaptive Power Allocation Scheme for Land Mobile Satellite Cooperative
Communication Systems Under a SNR Threshold Constraint
E-316
16:23-16:35
Authors: Di Liu, Lixi Fu, Yizhou He, Gaofeng Cui, Weidong Wang
Abstract: Power resource is one of the extremely limited resources of user
terminals. This paper proposes an adaptive power allocation scheme aiming at
minimizing total transmit power consumption for land mobile satellite (LMS)
cooperative communication systems through amplify-and-forward (AF) protocol. In
LMS uplink, the cooperative opportunity, which is defined as the selection between
direct transmission and the cooperative transmission, is introduced into this scheme.
With the variation values of the fading degree, the transmit power of user terminals
can be allocated adaptively subject to a signal to noise ratio (SNR) threshold
constraint. Numerical results are given in order to illustrate a significant advantage
of total transmit power consumption based on adaptive power allocation scheme
over conventional cooperative power allocation scheme and direct transmission.
Presenter: Nattawut Wichit
From: Prince of Songkla University, Thailand
Title: Multi-sensor Data Fusion Model Based Kalman filter Using Fuzzy Logic For
Human Activity Detection
E-323E
16:35-16:47
Authors: Nattawut Wichit and Anant Choksuriwong
Abstract: The performances of the systems that fuse multiple data coming from
different sources are deemed to benefit from the heterogeneity and the diversity of
the information involved. In this work a novel Multi-Sensor Data Fusion (MSDF)
architecture is presented. The estimation accuracy of the system states is reduced
dramatically. Therefore, applying Kalman filter to generate the importance density
function has been introduced to improve the performance with slightly increasing
the computational complexity. In this paper we propose a new Multisensor based
activity recognition approach which fuzzy logic fusion sensors to recognize Human
Behaviour. This approach aims to provide accuracy and robustness to the activity
recognition system. In the proposed approach, we choose to perform fusion at the
Feature-level.
17
2014 International Conference on Computer Engineering (ICOCE 2014)
Presenter: Abdullah Adnan
From: Kuwait University, Kuwait
Title: An Election Algorithm for Improved Leader Longevity in Heterogeneous
Mobile Ad-hoc Networks
Authors: Mohammad H. Al Shayeji, Abdullah Adnan and M.D. Samrajesh
ICNT2014-1-103
16:47-16:59
Abstract: Mobile Ad-hoc networks (MANET) differ from traditional distributed
systems, due to their dynamic and self-organizing characteristics. MANET requires
a leader to organize and manage various tasks such as key distribution, routing
coordination, sensor coordination and much more. One of the challenges in
MANET is having the right election algorithm that chooses the best leader based on
the various dynamic factors. In this paper, we propose a new leader election
algorithm for heterogeneous mobile Ad-hoc network considering specific factors of
MANET. The algorithm selects a leader from a list of candidates based on a number
of factors such as node’s residual energy, signal strength and crash history. The
proposed algorithm considers network partitions and network merging. Our
evaluation and discussions shows that the proposed algorithm is effective in
selecting a leader with the best longevity, thus reducing the number of elections and
reducing the fraction of time without a leader.
Presenter: Somayya Madakam
From: IT Applications Group, NITIE, Mumbai (India)
Title: Internet of Things: Smart Things
Authors: Somayya Madakam
ICNT2014-2-203
16:59-17:11
ICNT2014-2-212
17:11-17:23
Abstract: Research study on the Internet of Things and Smart Things has been
going on for more than a decade and reaches back to Mark Weiser’s original dream
of ubiquitous computing. Bruce Sterling recently popularized the idea of Smart
Objects and the IoT. Smart Things is another paradigm shift in IT world. Smart
Things are the things that are having embedding smartness or intelligence,
identification, automation, monitoring and controlling calibre. Smart Things are
assisting human life a lot, nowadays without their applications life is becoming
cumbersome. This paper exhibits systematically on Internet, Things, and then
explores on Internet of Things and finally Smart Things from researchers’, and
corporate’s perspective. Moreover, this article focuses on the state of Smart Things
and its applications. This in turn would help the new researchers, who want to do
research in this IoT domain.
Presenter: Ali Abbas Alsabbagh
From: Florida Institute of Technology, Florida, USA
Title: A Survey of Routing Protocols for Ad Hoc Networks Based on Update
Mechanism
Authors: Ruaa A.S.Alsabah , Ali Abbas Alsabbagh and Hisham Alzorghani
18
2014 International Conference on Computer Engineering (ICOCE 2014)
Abstract: An essential matter for ad hoc networks is routing protocol design which
is a major technical challenge due to the mobility of the nodes. Routing problem
becomes more complex and challengeable, and it probably is the most addressed
and studied problem in ad hoc networks. There are several classifications of
Routing protocols are used to perform routing the information from source to
destination. Classification methods help researchers and designers to understand
distinct characteristics of a routing protocol and find its relationship with others.
The main aim of this paper is to explore and to compare the concept of all routing
protocol based on update mechanism. This classification divided into Table-Driven
(Proactive), On-demand (Reactive), Hybrid routing protocols. Also, the comparison
is provided based on the routing mechanism and information used to make routing
decisions. Also this paper presents an overview of routing issues in different cases
as well as a detailed discussion of and their relative performance. To compare and
analyze an ad hoc network routing protocols, appropriate classification methods are
important.
19
2014 International Conference on Computer Engineering (ICOCE 2014)
Poster Session (21 Papers)
Venue: Jiujiang Conference Room, 5th floor（5 楼九江厅）
Time: 9:00 a.m.-17:30 p.m.
Title: Continuous Speech Recognition based on Convolutional Neural Network
Authors: Qing-qing Zhang, Yong Liu, Jie-lin Pan, Yong-hong Yan
E-104E
Abstract: Convolutional Neural Networks (CNNs), which showed success in
achieving translation invariance for many image processing tasks, are investigated
for continuous speech recognitions in the paper. Compared to Deep Neural Networks
(DNNs), which have been proven to be successful in many speech recognition tasks
nowadays, CNNs can reduce the NN model sizes significantly, and at the same time
achieve even better recognition accuracies. Experiments on standard speech corpus
TIMIT showed that CNNs outperformed DNNs in the term of the accuracy when
CNNs had even smaller model size.
Title: Video Copy Detection Based on Improved Affinity Propagation
Authors: Peng Li, Shengxiang Gao, Chengqiu Xiao, Zhe Xu, and Junguang Zhu
E-110E
Abstract: To solve the problems in the traditional BoVW (bag of visual words)
method based on the K-means clustering algorithm such as bad searching precision
and low time efficiency. An improved BoVW making method based on Affinity
Propagation (AP) and applying for large scale dataset is proposed. E2LSH is used to
match the similar video frame and vote to completing the video copy detection, and
an LAP method is introduced to make the BoVW scalable. Experimental results
show that the accuracy of the proposed method is substantially improved compared
to the traditional methods. Besides, it also adapts large scale datasets well.
Title: Research on Garment Wrinkle Synthetic Method Based on Mass-Spring
Model
Authors: Yuanwei Chen, Bing He, and Xuefu Yu
E-111E
Abstract: The manifestation and details of garments are mainly represented by
wrinkles. Through physical simulation of garment model, generated folding and
wrinkles can be seen, The more mass points of garment mesh model are, the more
realistic the effect are, but the longer the time will spend. On the contrary, the less
mass points of garment mesh model are, the faster the calculation is, but the rougher
the effect is. In order to give a balance to both simulation time and effect, this paper
will show a enhanced wrinkle algorithm to conduct local-regional mesh refinement
and simulation again providing a more detailed and realistic result for the
simulation result of rough mesh.
Title: Improving Ontology Matching with Propagation Strategy and User Feedback
Authors: Chunhua Li, Zhiming Cui, Pengpeng Zhao, Jian Wu, Jie xin, Tianxu He
E-113E
Abstract: Markov logic networks which unify probabilistic graphical model and
first-order logic provide an excellent framework for ontology matching. The
existing approach requires a threshold to produce matching candidates and use a
small set of constraints acting as filter to select the final alignments. We introduce
novel match propagation strategy to model the influences between potential entity
mappings across ontologies, which can help to identify the correct correspondences
and produce missed correspondences. The estimation of appropriate threshold is a
difficult task. We propose an interactive method for threshold selection through
which we obtain an additional measurable improvement. Running experiments on a
public dataset has demonstrated the effectiveness of proposed approach in terms of
the quality of result alignment.
20
2014 International Conference on Computer Engineering (ICOCE 2014)
Title: Construct the Cloud Services Platform of Educational Resources to Achieve
Regional Sharing of Educational Resources
Authors: Zhijun Liu, Pengxi Li, Ling Lu, Lie Han, and Guili Zhang
E-115E
Abstract: In recent years, with the rapid development and popularity of the
Internet, some emerging network technologies bring a profound impact to
information construction in higher education. The traditional teacher-centred
instructional mode has been unable to meet the needs of modern education.
Through construction of excellent course and open course, many colleges and
universities have accumulated a large number of high-quality online educational
resources, to build the cloud platform of educational resources that can support
regional sharing. If using of appropriate sharing mode, it can improve the utilization
of educational resources and accelerate the pace of universities education
information.
Title: Vertical Handover in Optical Wireless Heterogeneous Networks
Authors: Huanmin Han, Lei He,Qiang Li,Shuangyin Ren
E-202E
Abstract: Heterogeneous networks are now widely deployed to improve the
coverage rate for large area and increase the communication capacity in small area
coverage. Indoor optical wireless or Li-Fi satisfies high capacity demand in density
scenario, without any interference to existing radio frequency communication. It
brought new challenges to deal with handover for heterogeneous networks when
optical wireless access attachment points existed. In this article, we introduced
vertical handover and designed a vertical handover algorithm for a typical optical
wireless scenario.
Title: The Trigonometric Interpolation Spline Surface and Its Application in Image
Zooming
Authors: Juncheng Li and Lian Yang
E-210E
Abstract: The trigonometric polynomial spline surface generated over the space {1,
sint, cost, sin2t, cos2t} is presented in this work. The proposed surface can
automatically interpolate all the given data points and satisfy C2 continuous without
solving equation systems. Then, image zooming making use of the proposed surface
is investigated. Experimental results show that the proposed surface is effective for
dealing with image zooming problems.
Title: Factors influencing Adoption of Knowledge Management Systems in India
from a Micro, Small and Medium Enterprise’s Perspective
Authors: G. P. Girish, Dennis Joseph, Souvik Roy, and G. Amar Raju
E-211E
Abstract: In this study we investigate factors influencing successful adoption of
Knowledge Management Systems (KMS) in India from a Micro, Small and
Medium Enterprise’s (MSME’s) Perspective. MSME sector in India contributes
approximately 8% of India’s GDP accounting for nearly 45% of the manufacturing
output and 40% of the exports of India. In our study we review MSME sector in
India, literature pertaining to developing Knowledge Management Systems and
propose a conceptual model having traits of Technology Acceptance Model, Theory
of Reasoned Action and Social Cognitive Theory. The preliminary findings of the
study based on literature aids us in laying out factors influencing successful
adoption of KMS in a developing country like India from a MSME’s Perspective.
Empirical investigation of the developed model would have practical implication
and will help MSMEs (which are major contributors to development of the
economy) in successful adoption of Knowledge Management Systems and reap the
potential benefits.
21
2014 International Conference on Computer Engineering (ICOCE 2014)
Title: Behavior-based Mamdani Fuzzy Controller for Mobile Robot Wall-following
Authors: Xiao Li and Dan Wang
E-307E
Abstract: In literatures, most of the researches on mobile robot wall-following
problem are focused on straight or continuous smooth wall-following cases. This
paper proposes a behavior-based fuzzy controller for multi-type-wall following. The
fuzzy controller provides an information fusion mechanism for combining sensor
data from all laser range finder sensors. The behavior-based approach is
implemented as a coordinator to manage the switching among various behaviors to
solve the multi-type-wall following problem. The simulation results demonstrate
that the mobile robot can follow the wall with convex corner and concave corner.
Title: Weighted Bilateral Filtering Using Relative Difference Between Pixels
Authors: Li Ma, Yu-qi Zhang, Bin-bin Hu, Ming-yang Zheng
E-308E
Abstract: The similarity measurement of the bilateral filtering can’t indicate the
difference between pixels accurately in the dense texture region. It causes the
smoothing effect seriously, thereby reducing the edge preserving properties of the
bilateral filtering. This paper presents a new weighted function of the bilateral
filtering. It involves an additional range kernel using the relative difference between
pixels. The range kernel operates differently by acting on the pixel gray intensities
or colors. And it uses the reciprocal kernel for the approximation of the standard
Gaussian weight value. Experimental results suggest that it significantly preserves
more details than the classical bilateral filtering on edge or dense texture regions.
Title: Power Consumption Based Cloud Scheduler
Authors: Wu Li
E-311E
Abstract: After years of development and trial usage, cloud computing has finally
entered into mainstream and wide spread commercial use. Among the various cost
elements in operating a cloud computing infrastructure, power usage stands out
prominently. In fact, how to reduce the power consumption of cloud computing
platforms has received considerable attention of the cloud service provider as well
as academic researchers. This paper proposes a Power Awareness Scheduler (PAS)
system to manage the resource scheduling based on power usage patterns in the
cloud. By obtaining and analyzing the power consumption-load curve, PAS is able
to make power-efficient virtual machine deployment for the cloud. Our
implementation of the proposed PAS on OpenStack [1] shows that PAS can reduce
total power consumption by up to 17%.
Title: Multiple Confusion Network Application in MT System Combination
Authors: Yupeng Liu, Chunguang ma, Lemao Liu, Shui Liu, Shilei Zhao
E-314
E-317E
Abstract: System combination has emerged as a powerful method for machine
translation (MT).In the construction of word level confusion network (CN), the
alignment and skeleton selection are two key issues of system combination. The
paper introduces multi-CN for solving skeleton selection. We fail to yield the better
performance through using simple prior score as CN-based feature, so we introduce
more sophisticated CN-based and consensus-decoding-based features into
combination framework to test multi-CN’s validity. The approaches of multi-CN
are shown to be superior to single-CN in the setting of the Chinese-to-English track
of the 2008 NIST Open MT evaluation.
Title: Rethink Scalable M:N Threading on Modern Operating Systems
22
2014 International Conference on Computer Engineering (ICOCE 2014)
Authors: Lu Gong, Zhanqiang Li, Tao Dong, Youkai Sun
Abstract: We propose a highly scalable user-level threading library, μThread,
which enables programmer to write threaded code in a heavily concurrent
environment without losing performance. Our library achieves an M:N threading
model, which schedules M user-level threads on top of N kernel-level threads. The
user-level threads are directly scheduled by the asynchronous I/O and the library
can be adapted to modern operating systems without kernel modification.
We also provide a proof-of-concept implementation of a web server application.
According to our experiments, μThread provides good performance and great
scalability. The web server based on μThread becomes the best performance
user-mode web server under Windows.
Title: Random Neighbour-based Fault Localization
E-318E
Authors: Xinyu Zhu and XuePing He
Abstract: In the large-scale network, the router acts an increasingly important role
but the malicious behaviours including packets dropping and corruption of the
malicious routers harm the performance of the network. Actually, many work has
been proposed to locate the potential failure nodes but they all suffer from some
issues of performance and scalability, which are not practical for the network
environment. To deal with these problems, we introduce random neighbour-based
fault localization (RNFL). It utilizes neighbourhood nodes and message
authentication code (MAC) to check the integrity of packets so that RNFL can
detect the malicious nodes. Besides, it supports dynamic routing and the experiment
shows that it only puts small extra computing burden (less than 10%) on the
network routers.
Title: BMA: Bandwidth Allocation Management for Distributed Systems under
Cloud Gaming
E-319E
Authors: Runze Wang, Mochi Xue, Kai Chen, Zhanqiang Li, Tao Dong, Youkai
Sun
Abstract: Cloud gaming is becoming a popular IT business among cloud services.
In order to host a variety of network services, modern clouds provide great
computing power by equipping with multi-core CPUs and parallel-core GPUs. In
our previous work, we propose VGASA [1], a virtualized GPU resource adaptive
scheduling policy in cloud gaming, solving the poor default mechanisms of GPU
resource sharing. However, with the number of game player for cloud gaming
rising, the user experience is inevitably limited by the network bandwidth and
communication quality, due to the poor default mechanism of network resources
management. To address this network limitation, we propose BAM, which
combines distributed architecture and virtualized GPU resource adaptive policy in
cloud gaming based on our prior work. The key module of BAM maintains a
real-time monitoring of the virtual machine (VM) running status to manage the
allocation of network resources, guaranteeing the better running of VMs.
Title: UIIM: A User-Item Interest Model based on Bipartite Network for Top-N
Recommender System
E-320E
Authors: Zhixiong Jiang, Chunyang Lu, Siyuan Zheng, and Juan Yang
Abstract: Recently, a sparse linear method (SLIM) is developed for top-N
recommender systems, which can produce high-quality recommendations for sparse
data sets. SLIM provides a better performance than other existing methods. In this
paper, we provide a novel user-item interest method (UIIM) based on bipartite
network to improve the performance of SLIM. UIIM generates top-N
recommendations by building the user-item interest matrix R with the bipartite
23
2014 International Conference on Computer Engineering (ICOCE 2014)
network of users and items, calculating the item-item similarity matrix W with
SLIM and predicting users’ ratings on items as a dot product of matrix R and W.
And we also provide a parallel algorithm based on Spark to learn W. Our results
indicate that UIIM provides better performance and recommendation quality than
other existing methods and parallel algorithm of learning W outperforms serial
algorithm on large-scale data sets
Title: Classification of oilfield and nuclear power plants’ equipment states applying
methods of linear algebra
E-321E
Authors: A.I. Kalyaev, V.V. Korobkin, I.S. Korovin, M.V. Khisamutdinov, V.I.
Shmoylov, and Povarov V.P.
Abstract: A possible approach to solve the problem of the oilfield and nuclear
power plants’ equipment states classification is proposed in the paper. This
approach is based on the building of large dimension linear algebraic equations
systems. A fundamentally new algorithm for solving linear algebraic equations
systems (SLAE) using the so-called corresponding continued fractions, which are
often referred to as proper C-fractions. The proposed algorithm for SLAE solution,
although based on classical iterative algorithms of Jacobi and Seidel belongs to the
category of exact algorithms, providing systems solution by discrete number of
operations. It is shown that the developed algorithm allows to solve ill-conditioned
systems, and systems with random matrices. A comparison of SLAE solving
algorithm with the simple iteration, Seidel and Gauss algorithms has been carried
out.
Title: A Method of Generating Test Task Based on Analyzing Code Change
E-322E
Authors: CHENG Gao-Fei and ZHANG Mao-Lin
Abstract: The change of software code has a great effect on software function and
its test. When a new version of software is developed, the software need regression
test to ensure that the new version also meets the requirements designed. This paper
proposes a method that insert special format mark which is actually comment in
code to instruct the function of the code block. We also develop a tool for
automatically analyzing the change in code and software functions related to the
changed code between two different versions of code, then the tool could select test
cases related to the function difference to generate test tasks.
Title: An Approach of Conformance Verification between Design Models and Code
Based on Abstract Syntax Tree
E-324E
ICNT2014-1-102
Authors: Liu Zhao, Tian Yang, and Yan Haihua
Abstract: Design models and code are products of different stages in the software
development process. The conformance of design models and code plays an
important role in software development process, also is a key principle to improve
the maintainability of the software. Currently, the conformance on different level of
abstraction is verified mostly by manual inspection. In order to avoid the errors and
omissions, we propose a conformance verification approach between design models
and code based on abstract syntax tree. The approach verifies the conformance by
comparing the class diagram, sequence diagram with the code from the aspects of
static structure information and dynamic behaviour information. Firstly, we discuss
how to extract and recover model information from the abstract syntax tree, then
give the conformance verification approach between class diagram, sequence
diagram and code, finally implement a semi-automatic verification tool based on the
approach.
Title: Topology Control for Free-space Optical Networks
Authors: Tong Ning, Hun JieXu, Zhang Xue and Wang Chunshuang
24
2014 International Conference on Computer Engineering (ICOCE 2014)
Abstract: We consider the problem of designing a topology control algorithm for
free-space optical networks. The problem is to create a topology with strong
connectivity. A hierarchical topology control approach is present, named VTC. The
approach
applies
three-level
management
architecture
(Manager-Clusterhead-Member) and constructs a backbone network by Voronoi
diagram and Delaunay triangulation. VTC autonomously deploys Clusterheads and
enables the network to reconfigure itself; hence, the area covered by the network
can be enlarged. To avoid a mass of control messages being disseminated
periodically, we use a maintenance algorithm based on level. Through an example
using this algorithm, we show that the performance of the topology control
algorithm we derive works well.
Title: Hierarchical ZRP’s Performance vs ZRP’s Performance in MANET
Authors: Zhang Xijie, Xu Chunxiu and Xu Jiaqi
ICNT2014-1-104
Abstract: The mobile ad hoc network ( MANET ) has a dynamic nature that makes
the network topology change frequently. As a consequence, routing protocol plays
an important role in MANET. Zone Routing Protocol (ZRP) is a typical hybrid
routing protocol in MANET. It combines proactive with reactive techniques. It
applies a proactive technique in the zone and a reactive technique out of the zone. In
this paper we propose a hierarchical routing protocol H-ZRP based on ZRP to
avoid redundant or duplicate route requests. We demonstrate the performance of
H-ZRP with various performance metrics. We compare the performance of
H-ZRP and ZRP in End-to-End Delay , overhead, route discovery time and packet
delivery ratio.
Dinner Banquet
17:30 p.m.-19:00 p.m.
Fangting Restaurant, 2nd floor of Lushan Hotel(2 楼芳庭餐厅)
25
2014 International Conference on Computer Engineering (ICOCE 2014)
Call for Papers
www.ceepe.net
All papers, both invited and contributed, will be reviewed by two or three experts from the PC. After a careful reviewing
process, all accepted paper will be published in international journal “Applied Mechanics and Materials”
[ISSN:1660-9336, Trans Tech Publications] “Applied Mechanics and Materials” is indexed by Elsevier. Scopus and Ei
Compendex (CPX), Cambridge Scientific Abstracts (CSA) , Chemical Abstracts (CA) , Google and Google Scholar, ISI
(ISTP) , Institution of Electrical Engineers(IEE), etc.(For index information, please refer to AMM official website:
http://www.ttp.net/1660-9336.html). The full text is online available via platform www.scientific.net. Trans Tech
Publications will provide online camera-ready paper submission system.
Submission Methods: (Deadline: December 15, 2014)
1. Easy Chair System (pdf)
2. Email: ceepe@saise.org
www.ceeit.net
The topics of CEEIT 2015 will cover all areas encompassing Electrical Engineering and Information Technology. All papers
will be reviewed by two or three experts from the IPC. After a careful reviewing process, all accepted papers after proper
registration and presentation, will be published in WIT Transactions on Information and Communication Technologies
(ISSN: 1743-3517), which will be indexed by EI Compendex, Scopus and ISI.
Submission Methods: (Deadline: January 5, 2015)
1. Easy Chair System (pdf)
2. Email: ceeit@saise.org
www.icsis.org
This conference will feature world-class plenary speakers, major technical symposia, industry and academic panels, tutorials
and workshops. The technical program chairs invite the submission of original papers to following symposia for
presentation and publication in the conference proceedings. Accepted and presented papers will be submitted to WIT
Transactions on Information and Communication Technologies (ISSN: 1743-3517), which will be indexed by EI
Compendex, Scopus and ISI.
Submission Methods: (Deadline: February 15, 2015)
3. Easy Chair System (pdf)
4. Email: icsis@saise.org
26
2014 International Conference on Computer Engineering (ICOCE 2014)
Note
27
2014 International Conference on Computer Engineering (ICOCE 2014)
Note
28