1. No category

2015 DUBAI, UAE CONFERENCES
May 4-5, 2015
 ICRV 2015
2015 International Conference on Robotics and Vision
 ICSIE 2015
2015 4th International Conference on Software and Information Engineering
 ICOPR 2015
2015 International Workshop on Pattern Recognition
Flora Grand Hotel
http://www.florahospitality.com/dubai/deira/dubai-flora-grand-hotel.aspx
P.O. Box: 120328, Near Al Rigga Metro Station, Deira, Dubai, U.A.E.
Tel: + 971 4 2943660, Mobile: + 971 50 2562275, Fax: + 971 4 2943150
Program
2015 DUBAI CONFERENCES
WELCOME LETTER
3
OVERVIEW
4
KEYNOTES
6
DETAILED SCHEDULE
12
SESSION 1: Communications and Information Technology
14
SESSION 2: Computer and Information Sciences
17
CALL FOR PAPERS
21
FEEDBACK
25
2
2015 DUBAI CONFERENCES
Dear Participants,
Welcome to IACT 2015 Conferences in Dubai! We are confident that over the two days you will get the
theoretical grounding, practical knowledge, and personal contacts that will help you build a long-term,
profitable and sustainable communication among researchers and practitioners in a wide variety of scientific
areas with a common interest in Robotics and Vision topics, software and information engineering topics and
Pattern Recognition topics.
For the conferences of ICRV 2015, ICSIE 2015, and ICOPR 2015, we had received more than 70
submissions, and around 25 excellent papers were accepted for presentation. Congratulations for these
papers.
We wish to thank our outstanding keynote speakers Prof. Houssain Kettaniand, Prof. Magne Jørgensen, Prof.
Siva Yellampalli, Prof. Christopher Nwosisi, Dr. Carsten Mueller and other distinguished professors for
sharing their deep insights on future challenges and trends in Robotics and Vision, software and information
engineering and Pattern Recognition topics.
Special thanks to all the researchers and students who with their work and participate in the conference.
Hope you enjoy the conference, the food, the hospitality, and the beautiful and charming environment of
Dubai, UAE!
IACT Committee
3
2015 DUBAI CONFERENCES
Conference Agenda Overview
Monday, May. 4th, 2015
10 :00 am to 5:00 pm
Arrival and Registration
Lobby
Tuesday, May. 5th, 2015
Opening Ceremony
8:45am to 9:00am
Prof. Houssain Kettani
Fort Hays State University, USA
Keynote Address-1:
9:00am to 9:40am
Prof. Houssain Kettani
Fort Hays State University, USA
9:40am to 10:00am
Group Photo & Coffee Break
Keynote Address-2:
10:00am to 10:40am
Prof. Magne Jørgensen
Informatics at University of Oslo, Norway
Flora Grand Hall
Keynote Address-3:
10:40am to 11:20am
Prof. Siva Yellampalli
VTU Extension Centre, UTL Technologies Ltd., India
Plenary Speech-1:
11:20am to 12:00am
12:00am to 1:00pm
Prof. Christopher Nwosisi
The College of Westchester & Pace University New York,
USA
Lunch
Monsoon Restaurant
Plenary Speech-2:
1:00pm to 1:40pm
1:40pm to 3:25pm
3:25pm to 3:45pm
Dr. Carsten Mueller
Informatics Department, University of Economics, Czech
Republic
Flora Grand Hall
Session 1: Communications and Information Technology——7
presentations
Coffee Break
Foyer
4
2015 DUBAI CONFERENCES
3:45pm to 6:30pm
6: 30pm to 8:30pm
Session 2: Computer and Information Sciences —— 10
Flora Grand Hall
presentations
Dinner
Monsoon Restaurant
Instructions for Oral Presentations
Devices Provided by the Conference Organizer:
 Laptops (with MS-Office & Adobe Reader)
 Projectors & Screen
 Laser Sticks
Materials Provided by the Presenters:
 PowerPoint or PDF files
 Duration of each Presentation (Tentatively):
 Regular Oral Session: about 15 Minutes of Presentation including 2-3
Minutes of Q&A

Plenary Speech: 35 Minutes of Presentation, 5 Minutes of Q&A
NOTICE:
 *Certificate of Participation can be collected in front of the registration counter.
 *The organizer will not provide accommodation, so we suggest you make an early reservation.
 *One best presentation will be selected from each session. The best one will be announced when each
session ends, and will be awarded by the session chair after each session in the meeting room.
 *The attendee should provide the author’s authorization or attendee’s passport ID when the attendee is
none of the authors.
Conference Secretariat Contact:
ICRV 2015: Ms. Heleny Yi ([email protected])
ICSIE 2015: Ms. Dorothy Zhang ([email protected] )
ICOPR 2015: Ms. Alice Kuo ([email protected])
Tel: +1-661-888-4278; +86-28-86528298
5
2015 DUBAI CONFERENCES
The United States' Challenges in Science and Engineering
Education
Prof. Houssain Kettani
Fort Hays State University, USA
Abstract:
Numerous statistical data indicate that science and engineering workforce in the United States is aging and nearing
retirement. Moreover, various studies show that it has become increasingly difficult to attract American students to
science and engineering fields. We present supporting data for different ethnic groups and international students for
various degrees in these fields. The situation is particularly grim for Hispanics, who are the fastest growing segment in
the population. They remain an untapped in resource, which could either present the solution needed to overcome this
challenge, or further deteriorate the situation. The objective of this talk is to shed some light on the situation and
suggest some solutions to this predicament that the nation is facing.
Biography:
Dr. Houssain Kettani was born in 1978 in Khobar, Saudi Arabia. He then moved with his parents in 1981 to Jeddah,
Saudi Arabia where he received his K to 6th grade education. He then moved with his parents again to Rabat, Morocco
in 1989, where he is originally from and where he received his 7th to 12th grade education. He then moved to
Famagusta, North Cyprus in 1995, where he received the Bachelor's degree in Electrical and Electronic Engineering
from Eastern Mediterranean University, Famagusta, North Cyprus, in 1998, and moved in the same year to the United
States to continue his higher education. In 2000 and 2002 respectively, he received his Master’s and Doctorate degrees
both in Electrical Engineering from the University of Wisconsin, Madison, Wisconsin, USA.
He served as Assistant Professor of Electrical and Computer Engineering at the University of South Alabama, Mobile,
Alabama, USA in 2002-2003, Assistant Professor of Computer Science at Jackson State University, Jackson,
Mississippi, USA in 2003-2007, Full Professor of Electrical and Computer Engineering and Computer Science and
Director of the Partnership Development Office at Polytechnic University, San Juan, Puerto Rico, USA in 2007-2012,
and Professor and Director of Information Systems Engineering at Fort Hays State University, Hays, Kansas, USA
since 2012.
Dr. Kettani has served as Staff Research Assistant at Los Alamos National Laboratory, Los Alamos, New Mexico,
USA in summer of 2000, Visiting Research Professor at Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
6
2015 DUBAI CONFERENCES
in summers of 2005 to 2011, Visiting Research Professor at the Arctic Region Supercomputing Center at the
University of Alaska, Fairbanks, Alaska, USA in summer of 2008, and Visiting Professor at the Joint Institute for
Computational Sciences at the University of Tennessee, Knoxville, Tennessee, USA in summer of 2010.
Dr. Kettani’s research interests include computational science and engineering, high performance computing
algorithms, information retrieval, network traffic characterization, number theory, robust control and optimization, and
Muslim population studies. He presented his research in over sixty refereed conference and journal publications and his
work received over four hundred citations by researchers all over the world. He chaired over hundred international
conferences throughout the world and successfully secured external funding in millions of dollars for research and
education from US federal agencies such as NSF, DOE, DOD, and NRC.
7
2015 DUBAI CONFERENCES
The Use and Misuse of Statistics in Studies on Software
Development. Things You Should Know About Statistics That
You didn’t Learn in School.
Prof. Magne Jørgensen
Informatics at University of Oslo, Norway
Abstract:
The keynote addresses a selection of questionable statistical practices commonly observed in software engineering
research. This includes a discussion of the topics: finding pattern in randomness, do you know what p-values means,
publication bias, how much can we trust the outcome of statistical tests in software engineering studies?, the
consequences of violation of the fixed variables assumption in regression analysis. The topics will be illustrated with
observations on how questionable statistical practices have produced misleading and incorrect results in software
engineering research. It is important to never use a statistical method without understanding it thoroughly and to never
violate statistical assumptions without understanding the likely consequences of doing so. Several changes in statistical
practice in software engineering research are suggested.
Biography:
Magne Jørgensen received the Diplom Ingeneur degree in Wirtschaftswissenschaften from the University of Karlsruhe,
Germany, in 1988 and the Dr. Scient. degree in informatics from the University of Oslo, Norway, in 1994. He is a
professor of software engineering at the University of Oslo and a member of the software engineering research group at
the Simula Research Laboratory. He has 10 years industry experience as a consultant and manager. His research
interests include software estimation, uncertainty assessments in software projects, expert judgment processes, and
learning from experience.
Magne Jørgensen works as a researcher at Simula Research Laboratory and a professor at the University of Oslo.
Previously, he worked with software development, estimation, and process improvement in the telecom and insurance
industry. He is one of the founders of evidence-based software engineering and teaches this to students and software
professionals.
His current main research interest is effort estimation, bidding processes, outsourcing, and software development skill
assessments.
8
2015 DUBAI CONFERENCES
Image Processing for the Next Generation Networks
Prof. Siva Yellampalli
VTU Extension Centre, UTL Technologies Ltd., India
Abstract:
The tremendous and continuously accelerated growth in the amount of images and videos distribution over the internet,
together with the widespread availability of a wide range of non-PC end-user connected devices (ranging from
smartphones and tablets to internet-enabled TV sets), is changing the ways in which people consume visual content. In
this environment image processing has to evolve to meet the new requirements such as low bit rate for data storage and
transmission, while maintaining acceptable distortion along with minimizing the power consumption.
With the increased commercial interest in video communication the need for new international image and video coding
techniques are increasing. New video coding techniques and standardization holds the promise of large markets for
video communication equipment. In this talk key internet trends along with market growth analysis and new internet
trends where image processing is playing a major role are discussed. Then we will briefly look into the history of VLSI
implementation of image/video coding techniques such as JPEG, MPEG-1, H.261, MPEG-2, H.263, MPEG-4, and
H.264/AVC, and the related coding principles and their effectiveness in the new environment. Participants will gain an
understanding of image processing requirements and novel techniques in the next generation video coding standards,
along with some perspectives for the future applications and research opportunities.
Biography:
Dr. Siva Yellampalli is currently working as a Professor with VTU Extension Centre, UTL Technologies Ltd. He
obtained his MS & Ph.D from Louisiana State University. His area of research is system level design for power
optimization. His area of research encompasses different research fields such as Very Large Scale Integration (VLSI),
mixed signal circuits/systems development, micro-electromechanical systems (MEMS), and integrated carbon
nanotube based sensors. He has published a book in the area of mixed signal design, and edited two books on carbon
nano tubes. He also published multiple International Journal papers & IEEE Conference papers in these areas of
research. In addition he has delivered keynote speeches at International conferences held in Canada & Spain including
tutorials at various IEEE International Conferences. He has given many professional presentations including invited
talks. He has been a consultant to a variety of industries and acts as a reviewer for technical journals and book
publishers. Currently he is the Student Activities Chair, Executive Committee IEEE Bangalore Section. He is also a life
member of Indian Society for Technical Education (ISTE), senior member, International Association of Computer
Science and Information Technology (IACSIT), VLSI Society of India (VSI) and National Society of Collegiate
Scholars (NSCS).
9
2015 DUBAI CONFERENCES
A Novel Definition of an Efficient Binary Decision Tree
Prof. Christopher Nwosisi
The College of Westchester & Pace University New York, USA
Abstract:
Decision trees have been well studied, widely used in knowledge discovery and decision support systems. They are
simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible.
In this study, a genetic algorithm is used to construct decision trees of increased accuracy and efficiency compared to
those constructed by the conventional ID3 or C4.5 decision tree building algorithms. An improved definition of an
efficient binary decision tree is proposed and evaluated – instead of simply using the number of nodes in a tree, the
average number of questions asked in the tree for all the database entries is proposed.
Biography:
DPS, Pace University MS, Polytechnic University BA, Hunter College Certifications: CNA, CNE, Network+, A+,
MCSA, CCNA, CCAI
Research Interests: Data Mining, Network Architecture, Database Management, Teaching Methodology & Pattern
Recognition.
"Our classes are comprised of students with diverse work experiences. For those of them with "zero" IT knowledge and
those of them who want to change career, our department will give them the hands-on experience that they need. Our
small class size encourages team work and one-on-one interaction. Project development is an integral part of our
program, and real life projects are used to stimulate and inspire our students."
"Tell me and I'll forget; show me and I may remember; involve me and I'll understand." - Chinese Proverb
10
2015 DUBAI CONFERENCES
Dynamic Collaboration Structures in an object-oriented IT
Governance
Dr. Carsten Mueller
Informatics Department, University of Economics, Czech Republic
Abstract:
IT Governance (ITG) is the degree to which the authority for making IT decisions is defined and shared among
management, and the processes managers in both IT and business organisations apply in setting IT priorities and the
allocation of IT Resources. ITG in a global context has to cater for intensive competition, cultural diversity, and various
fluctuating economic conditions. It is viewed as a mixture of various structures, processes, relational mechanisms.
The main reason for using object-oriented modelling in the context of ITG is the natural mapping paradigm which
allows a one-to-one mapping between objects in the ITG domain being modelled and their abstractions in the object
model. Based on this object-oriented ITG model four dynamic and interacting collaboration structures i) Service
Component Architecture ii) Service Composition iii) SPSPR Model and iv) Team- and Target Formation are
implemented.
The dynamic collaboration structures are supported by design patterns/principles (e.g. watchdog), clustering,
recommender and metaheuristics for optimization. The relationships and collaborations in ITG and BITA are
configured using a query language, analysed and optimized – at runtime.
This component-based software architecture with minimum coupling and maximum cohesion provides a flexible ITG
platform for the main activities direct, align, monitor and analyse. Based on (business-) requirements/optimizations it is
possible to substitute and extend existing components on demand and at runtime. This leads to well-adapted ITG and
improves a) information flow,b) workflow, c) management-/decision support d) resource allocation and e) value
creation from the IT investment in the context of ITG including Business-IT Alignment (BITA).
This plenary speech provides a general overview about this intelligent and fascinating solution. The practical
demonstration is focussing on Change Management (COBIT, BAI06) and BITA.
Biography:
Carsten Mueller holds a M.Sc. degree from the University of Liechtenstein in Vaduz and a Ph.D. degree from the
University of Economics (Department Informatics and Statistics) in Prague. He works over 15years as an independent
consultant and trainer in the areas of IT process optimization, object-oriented modelling and IT governance. He is
currently the technical head of processes and IT management at a large airport in Germany and a senior lecturer for
software engineering, UML and algorithms at the Baden-Wuerttemberg Cooperative State University.
11
2015 DUBAI CONFERENCES
Detailed Schedule
Monday, May 4th
Location
Lobby
10：00 – 12：00
13：00 — 17：00
Arrival and Registration
Tips:
After sign, you will collect your conference package, including:
Original Receipt
Journal (Only for Author Attendee)
Representative / Pass Card with Tie
Printed Program
Lunch Coupon
Dinner Coupon
*Certificate (collected from Session Chair after the presentation)
Conference Souvenir
Computer Bag
Notice:

Please check on all these materials as soon as you get the package; if any of them is not included in the
package, please let us know at once; If any of them gets lost after the registration, no additional one
would be provided. Your understanding will be appreciated!

Each regular registration covers only one package. Additional package will be charged.

Some attendees may arrive on May 5, kindly be noted that you can register at the registration desk from
9 am onwards.
12
2015 DUBAI CONFERENCES
Tuesday Morning, May 5th
Opening Ceremony
Location
Flora Grand Hall
Opening Ceremony
8:45am to 9:00am
Prof. Houssain Kettaniand
Fort Hays State University, USA
9:00am to 09:40am
Keynote Address -1:
The United States' Challenges in Science and Engineering Education
Prof. Houssain Kettaniand
Fort Hays State University, USA
9:40am to 10:00am
10:00am to 10:40 am
Group Photo & Coffee Break
Keynote Address-2:
The Use and Misuse of Statistics in Studies on Software Development.
Things You Should Know About Statistics That You didn’t Learn in
School.
Prof. Magne Jørgensen
Informatics at University of Oslo, Norway
10:40am to 11:20 am
Keynote Address-3:
Image Processing for the Next Generation Networks
Prof. Siva Yellampalli
VTU Extension Centre, UTL Technologies Ltd., India
11:20 am to 12:00am
Plenary Speech-1:
A Novel Definition of an Efficient Binary Decision Tree
Prof. Christopher Nwosisi
The College of Westchester & Pace University New York, USA
13
2015 DUBAI CONFERENCES
12:00am——1:00pm Lunch Time
Location
Monsoon Restaurant
Tips:
 Please be noted that lunch coupon is necessary for entering the Monsoon Restaurant.
 Please arrive on time to the Flora Grand Hall by 12:55 pm. Thank you!
Tuesday Afternoon, May 5th
Plenary Speech-2:
1:00 pm to 1:40am
Dr. Carsten Mueller
Informatics Department, University of Economics, Czech Republic
-PAPER SESSIONSSession 1: Communications and Information Technology
Chair: Prof. Christopher Nwosisi
7 presentations
Time: 1:40pm to 3:25pm
Venue: Flora Grand Hall
A Novel Definition of an Efficient Binary Decision Tree
Christopher Nwosisi
College of the City University of New York, US
E3003
Abstract — Decision trees have been well studied, widely used in knowledge discovery and decision support systems. They are
simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible. In this study,
a genetic algorithm is used to construct decision trees of increased accuracy and efficiency compared to those constructed by the
conventional ID3 or C4.5 decision tree building algorithms. An improved definition of an efficient binary decision tree is proposed
and evaluated – instead of simply using the number of nodes in a tree, the average number of questions asked in the tree for all the
database entries is proposed.
14
2015 DUBAI CONFERENCES
On a New Competence Measure Applied to the Combining Multiclassifier System
Marek Kurzynski
Wroclaw University of Technology, Poland
Abstract — In this paper a new method for calculating competence of a classifier in the feature space is presented. The idea of
method is based on relating the response of the classifier with the decision profile of a test object which is evaluated using K nearest
R010
objects from the validation set. The measure of competence reflects this relation and rates the classifier with respect to the similarity
nting
the dynamic classifier selection (DCS) and dynamic ensemble selection (DES) strategies are developed using proposed measure of
competence.
The performance of proposed MCS’s was compared against seven multiple classification systems using six benchmark datasets
taken from the UCI Machine Learning Repository and Ludmila Kuncheva Collection. The experimental investigations clearly show
the effectiveness of the combining multiclassifier system in dynamic fashion using proposed measure of competence regardless of
the ensemble type used (homogeneous or heterogeneous).
Performance Enhancement in 5G Mobile Network Processing
Eba' Almousa and Feda Alshahwan
Public Authority for Applied Education and Training, Kuwait
E006
Abstract — Networks are developing to increase the data speed and channels bandwidth. Many attempts have been carried out to
achieve the main demands of faster connectivity and download. This study presents most of the attempts and researches to deploy
5G. However, the new 5G network technology is still in its infancy stage and lacks standardization.
Component-Based Model for Heterogeneous Nodes in Wireless Sensor Networks
Atif Naseer, Basem Alkazemi and Hossam Aldoobi
Umm al Qura University, Saudi Arabia
Abstract — Data exchange between heterogeneous motes in a network requires careful understanding of the data model adopted by
E012
every mote type. This can be a very challenging concern, especially when dealing with a wide variety of motes at runtime where
new nodes can join a network to provide certain services. This paper identifies the key architectural characteristics of two
commonly recognized operating systems, namely TinyOS and Contiki, which behave differently when dealing with data exchange
and state control. The aim is to map the architecture of TinyOS and Contiki on to a component-based software engineering model.
This discussion leads to describing abstractly the design of a generic component-based middleware model to address
interoperability issues when dealing with these two types of motes.
Integral Architecture For Organizational Systems -ARQUETIPOSAna Milena Paez Quintero, Ricardo Llamosa Villalba and Edgar Sneyder Garcí
a Morantes
CIDLIS-UIS, Colombia
E019
Abstract — ARQUETIPOS is a meta-model that combines structural elements given by TOGAF, Enterprise Architecture, agile
methods and ZACHMAN frameworks, with prototyping and simulation techniques. There are advantages to this model such as its
iterative approach, which grants real-time results to stakeholders. Also, when using this model, requirements and solutions evolve
through the collaboration of high performance teams. From an ontological approach ARQUETIPOS is composed of five
components: The Framework for Capability, the Content of the Architecture, the Implementation Method, the Maturity Assessment
Model of Organizational Systems and the Meta-model Repository. This paper aims to test the implementation of ARQUETIPOS in
15
2015 DUBAI CONFERENCES
the education and productive sector through the use of agile principles and prototyping and simulation techniques. The techniques
or strategies used to implement this meta-model are varied, in this case the training service was used. This strategy allowed the
main actors in this paper (Academia and companies) to model their organizational processes through the creation of prototypes with
Lego. In consequence, that let them to get better services and products aligned with their business strategy.
Location based and contextual services using Bluetooth Beacons: New way to Enhance Customer Experience
Nilima Dudhane and Sanjeevkumar Pitambare
TechMahindra Ltd., India
Abstract — Location based services and context facilitates innovative ways to enhance customers “in-location” experience. Indoor
spaces often block cell signals and make it difficult to track customer’s indoor activities via existing technologies like GPS, RFID
E0023
and Cellular tower triangulation etc. These limitations can be addressed using Bluetooth Beacons. Using beacons, retailers can
optimize customer experiences, improve business processes and generate more revenue. Retailers and telecommunication service
providers can do the partnerships with each other to enhance in-store shopping experience of customer and provide personalize
offers.
In this paper, authors have proposed, how Bluetooth beacons can be beneficial to retailers in terms of customer analytics,
operational analytics and revenue improvement along with partnering with service providers to enhance customer experience and
loyalty.
Developing Abuse Cases Based on Threat Modeling and Attack Patterns
Xiaohong Yuan
North Carolina A & T State University, US
Abstract — Developing abuse cases help software engineers to think from the perspective of attackers, and therefore allow them to
E024
decide and document how the software should react to illegitimate use. This paper describes a method for developing abuse cases
based on threat modeling and attack patterns. First potential threats are analyzed by following Microsoft’s threat modeling process.
Based on the identified threats, initial abuse cases are generated. Attack pattern library is searched and attack patterns relevant to the
abuse cases are retrieved. The information retrieved from the attack patterns are used to extend the initial abuse cases and suggest
mitigation method. Such a method has the potential to assist software engineers without high expertise in computer security to
develop meaningful and useful abuse cases, and therefore reduce the security vulnerabilities in the software systems they develop.
Tuesday Afternoon, May 5th
3:25pm to 3:45pm
Location
Foyer
-PAPER SESSIONS-
16
2015 DUBAI CONFERENCES
Session 2: Computer and Information Sciences
Chair: Dr. Carsten Mueller and Asst. Prof. Alaa Halawani
10 presentations
Time: 3:45pm to 6:30pm
Venue: Flora Grand Hall
A Supervised Learning Approach for the Fusion of Multiple Classifier Outputs
Cagdas Ulas, Bilge Koroglu, Can Bekar, Okan Burcak and Onur Agin
Yapi Kredi Bank/R&D and Special Projects Department, Kocaeli, Turkey
Abstract — In this paper, we propose an alternative method for the fusion of multiple classifier outputs to obtain a potential
R006
idual
classifiers, which are trained on different data sets, share common classes and some of them also individually deal with classifying
different class labels. For this reason, we first aim to define a common space to represent all the class labels and then propose a
supervised learning approach to effectively recognize patterns of the tuples that are formed by concatenating classifiers outputs
based on top-N rankings. To evaluate the performance of our method, we utilize Random Forest (RF) classifier for this multiclass
classification problem and the results demonstrate that our method can achieve promising performance improvement in true positive
rate of classification compared to that of the best performing individual classifier yields.
Image Quality Improvement in Kidney Stone Detection on Computed Tomography Images
Saman Ebrahimi and Vladimir Mariano
Institute of Computer Science, University of the Philippines Los Baños, Philippines
Abstract — Kidney-urine-belly computed tomography (KUB CT) analysis is an imaging modality that has the potential to enhance
R009
kidney stone screening and diagnosis. This study explored the development of a semi-automated program that used image
processing techniques and geometry principles to define the boundary, and segmentation of the kidney area, and to enhance kidney
stone detection. It marked detected kidney stones and provided an output that identifies the size and location of the kidney based on
pixel count. The program was tested on standard KUB CT scan slides from 39 patients at Imam Reza Hospital in Iran who were
divided into two groups based on the presence and absence of kidney stones in their hospi-tal records. Of these, the program
generated six in-consistent results which were attributed to the poor quality of the original CT scans. Results showed that the
program has 84.61 per cent accuracy, which sug-gests the program’s potential in diagnostic efficiency for kidney stone detection.
Human Ear Localization: A Template-based Approach
Alaa Halawani and Haibo Li
Department of Applied Physics and Electronics (TFE), UmeåUniversity, Umeå, Sweden
R012
Abstract — We propose a simple and yet effective technique for shape-based ear localization. The idea is based on using a
predefined binary ear template that is matched to ear contours in a given edge image. To cope with changes in ear shapes and sizes,
the template is allowed to deform. Deformation is achieved by dividing the template into segments. The dynamic programming
search algorithm is used to accomplish the matching process, achieving very robust localization results in various cluttered and
RV1000
Parallel Computed Tomography Technique
Akram Boukhamla, Hayet Farida Merouani, and Hocine Sissaoui
Badji Mokhtar University-Annaba, Algeria
17
2015 DUBAI CONFERENCES
Abstract — Since the Filtered Back-projection algorithm (FBP) requires significantly long computational time when the amount of
data becomes increasingly large; which is the case of Computed Tomography (CT), parallel computing technique is used in MatLab,
as it enables the implementation of multi-tasking. Exploiting this advantage by partitioning the input data and allowing each core of
cluster to work on its own sub-image (2, 4, 8, 16). Therefore, Filtered Back-projection algorithm was applied simultaneously on all
cores. All the reconstructed sub-images will be sent to the Client in order to be gathered. The comparison results between a
sequential FBP algorithm and the parallel algorithm, show that the parallel computing process is up to seven times more efficient
than the sequential algorithm on the voluminous images size, otherwise the small images results were poor because of the workers
intercommunications that require times comparing with the sequential algorithm that takes a short computational time.
Team formation based on nature-inspired swarm intelligence
Carsten Mueller and Christian Eichmann, Germany
University of Economics, Faculty of Informatics and Statistics, PragueBaden Wuerttemberg Cooperative State
University Mosbach
E009
Abstract — This paper describes an application to form teams from a given set of employees. The teams are assigned to perform
task. To accomplish a task a team has to fulfill specific requirements which have to been minded while assigning teams to task. The
goal is the forming of a chain of task meeting specific requirements and assigning a team to each task able to solve it. These chains
have to be optimized for a synergy value representing how well employees work together. There is one synergy value for each
possible pair of employees.
Plugin for Visual Paradigm for generating and intelligent optimization of a Component Diagram based on
attributes in the Class Diagram
Carsten Mueller and Anton Pohl
University of Economics, Faculty of Informatics and Statistics, PragueBaden Wuerttemberg Cooperative State
University Mosbach, Germany
E010
Abstract — In today’s software development process (SDP) it is necessary to do much preparatory work to achieve a good quality of
the software. Besides the requirements engineering the design process is very important. The designer can describe all aspects of the
software to be built. Excellent designing skills and the question “What makes a ‘good’ software?” are essential to create a competent
“cookbook”. The plugin presented in this paper shall support designer using Visual Paradigm (VP) as a modeling-tool during their
modeling process. Based on given attributes in the Class Diagram the plugin can generate and optimize intelligently a Component
Diagram.
Recognition of Modern Arabic Poems
Abdulrahman Almuhareb, Waleed Almutairi, Haya Altuwaijri, Abdulelah Almubarak and Marwa Khan
King Abdulaziz City for Science and Technology (KACST), Saudi Arabia
E0020
Abstract — We propose a machine learning method for recognizing modern Arabic poems based on the common poetic features of
modern Arabic poetry. The poetic features include: rhyming, repetition, use of diacritics and punctuations, and text alignment. The
method can classify text documents as poem or non-poem documents with a very high accuracy of 99.81%.
Application and Assessment of Classification Techniques on Programmers’ Performance in Software Industry
Sangita Gupta and Suma V.
Jain University, Bangalore
E3001
Abstract — Software companies seek to develop and maintain high quality products along with increasing reliability and
maintainability. Therefore, companies look into every aspect for project success. Software companies try to improve efficiency in
process by using different techniques. With best hardware, operating system and methodologies, still there have been disastrous
18
2015 DUBAI CONFERENCES
software failures. It is found that most software failures are due to lack of focus on people working on the process. Human aspect of
software engineering has thus become an emerging stream and it is identified as core factor for project success. Therefore, human
aspect needs deep investigation in this ever changing field of software development. One of the strategies is to process and analyze
previous data of software companies to predict future failures. Data mining techniques have the ability to uncover hidden patterns in
large databases. Software companies can build models that predict with a high degree of accuracy the attributes required in human
aspect for success. Through these predictive data mining models, companies can effectively address issues ranging from selection,
retention to development and effectively manage the team members.
The purpose of this paper is to use different data mining algorithms on project personnel data and compare the accuracy of these
algorithms.
Kinematics Modeling of a 4-DOF Robotic Arm
Amin A. Mohammed and M. Sunar
King Fahd University of Petroleum & Minerals, Saudi Arabia
Abstract — This work presents the kinematics model of an RA-02 (a 4 DOF) robotic arm. The direct kinematic problem is
RV0008
addressed using both the Denavit-Hartenberg (DH) convention and the product of exponential formula, which is based on the screw
theory. By comparing the results of both approaches, it turns out that they provide identical solutions for the manipulator kinematics.
Furthermore, an algebraic solution of the inverse kinematics problem based on trigonometric formulas is also provided. Finally,
simulation results for the kinematics model using the Matlab program based on the DH convention are presented. Since the two
approaches are identical, the product of exponential formula is supposed to produce same simulation results on the robotic arm
studied.
A Proposed Model for Code Quality Maturity Model
Fariha Motherudin and Noor Ezleen Moksen
MIMOS Bhd, Malaysia
Abstract — The information technology (IT) industry is characterized by rapid innovation and intense competition. A key issue is
the ability of the development team to leverage emerging software development best practices. It is a critical enabler for the overall
health and sustainability of an organization's ability to build software solutions. In this paper, we are proposing an evolutionary
E004
model that could be a reference for others in the area of utilizing best practices in the area of code and build management. The best
practices studied in this paper are included static code analysis, automated unit testing, continuous integration, release gate checking
and technical debt. The proposed model is expected to help appraising the maturity level of the produced codes, build and release
management practices. It aims to satisfy the characteristics defined at five levels and estimate the target level that one try to achieve.
The proposed model is based on several years of real world experience with a big number of teams from the software engineering
field. The classification level is based on practices that practitioners observed during the software development life cycle. The
processes have evolved from an independent process using an independent tool to prediction process using technical debt ideas
which hope this proposed model would be beneficial not only to the software engineers but also to the organization as a whole
19
2015 DUBAI CONFERENCES
 Tips:
The best paper will be chosen after each session and the certificate will be awarded by the chair. Good
Luck!
Tuesday Evening, May 5th
6:30 pm to 8:30 pm--Dinner
Location
Monsoon Restaurant
Tips: The Dinner will start at 6:30pm. Please kindly attend on time with bringing the Dinner Coupon.
20
2015 DUBAI CONFERENCES
21
2015 DUBAI CONFERENCES
22
2015 DUBAI CONFERENCES
23
2015 DUBAI CONFERENCES
24
2015 DUBAI CONFERENCES
Please take a few moments to provide us some important feedback about your professional development
of Dubai conferences.
-------------------------------------------------------------------------------------------------------------------------
Conference Feedback
Use the key below
Very Good□
Good□
Poor□
Use the ranking key above as appropriate to answer the questions below on the blank spaces provided at
the end of each questions
How was the overall organization of the conference
How do you rate the registration area
How do you rate the presenter(s)
Did you gain any helpful skills
How was the format of the meeting in terms of
lunch, coffee breaks?
Overall, how were the conference facilities
How was the reception you received at the
conference
How was the venue
List other locations where you think future meeting
should be held
Why did you choose that venue?
Generally, how was the whole experience at the
meeting, and given another chance would you attend
or recommend next year's conference?
Comments and Suggestions
25