Abstract: Learning through creation of contextual games is a
very promising approach when undertaking interdisciplinary and
international group projects. During 2013 and 2014 the authors
organized two intensive student projects. The two projects were in
different countries and different conditions. Between them, the two
projects involved 68 students and 12 mentors from five EU countries
and from various academic disciplines. In this paper we share our
experience of these two projects and we suggest approaches that can
be utilized to strengthen the chances of succeeding in short (12-15
days long) intensive student projects.
Abstract: Real time image and video processing is a demand in
many computer vision applications, e.g. video surveillance, traffic
management and medical imaging. The processing of those video
applications requires high computational power. Thus, the optimal
solution is the collaboration of CPU and hardware accelerators. In
this paper, a Canny edge detection hardware accelerator is proposed.
Edge detection is one of the basic building blocks of video and image
processing applications. It is a common block in the pre-processing
phase of image and video processing pipeline. Our presented
approach targets offloading the Canny edge detection algorithm from
processing system (PS) to programmable logic (PL) taking the
advantage of High Level Synthesis (HLS) tool flow to accelerate the
implementation on Zynq platform. The resulting implementation
enables up to a 100x performance improvement through hardware
acceleration. The CPU utilization drops down and the frame rate
jumps to 60 fps of 1080p full HD input video stream.
Abstract: Securing the confidential data transferred via wireless
network remains a challenging problem. It is paramount to ensure
that data are accessible only by the legitimate users rather than by the
attackers. One of the most serious threats to organization is jamming,
which disrupts the communication between any two pairs of nodes.
Therefore, designing an attack-defending scheme without any packet
loss in data transmission is an important challenge. In this paper,
Dependence based Malicious Route Defending DMRD Scheme has
been proposed in multi path routing environment to prevent jamming
attack. The key idea is to defend the malicious route to ensure
perspicuous transmission. This scheme develops a two layered
architecture and it operates in two different steps. In the first step,
possible routes are captured and their agent dependence values are
marked using triple agents. In the second step, the dependence values
are compared by performing comparator filtering to detect malicious
route as well as to identify a reliable route for secured data
transmission. By simulation studies, it is observed that the proposed
scheme significantly identifies malicious route by attaining lower
delay time and route discovery time; it also achieves higher
throughput.
Abstract: The use of eXtensible Markup Language (XML) in
web, business and scientific databases lead to the development of
methods, techniques and systems to manage and analyze XML data.
Semi-structured documents suffer due to its heterogeneity and
dimensionality. XML structure and content mining represent
convergence for research in semi-structured data and text mining. As
the information available on the internet grows drastically, extracting
knowledge from XML documents becomes a harder task. Certainly,
documents are often so large that the data set returned as answer to a
query may also be very big to convey the required information. To
improve the query answering, a Semantic Tree Based Association
Rule (STAR) mining method is proposed. This method provides
intentional information by considering the structure, content and the
semantics of the content. The method is applied on Reuter’s dataset
and the results show that the proposed method outperforms well.
Abstract: In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation,
style, illumination, and can suffer from perspective distortion.
Pre-processing is performed to make the characters scale and
rotation invariant. Since text degradations can not be appropriately
defined using well-known geometric transformations such
as translation, rotation, affine transformation and shearing, we
use the whole character black pixels as our feature vector.
Classification is performed with minimum distance classifier
using the maximum likelihood criterion, which delivers very
promising Character Recognition Rate (CRR) of 89%. We
achieve considerably higher Word Recognition Rate (WRR) of
99% when using lower level linguistic knowledge about product
words during the recognition process.
Abstract: Container handling problems at container terminals
are NP-hard problems. This paper presents an approach using
discrete-event simulation modeling to optimize solution for storage
space allocation problem, taking into account all various interrelated
container terminal handling activities. The proposed approach is
applied on a real case study data of container terminal at Alexandria
port. The computational results show the effectiveness of the
proposed model for optimization of storage space allocation in
container terminal where 54% reduction in containers handling time
in port is achieved.
Abstract: In this work, neural networks methods MLP type were
applied to a database from an array of six sensors for the detection of
three toxic gases. The choice of the number of hidden layers and the
weight values are influential on the convergence of the learning
algorithm. We proposed, in this article, a mathematical formula to
determine the optimal number of hidden layers and good weight
values based on the method of back propagation of errors. The results
of this modeling have improved discrimination of these gases and
optimized the computation time. The model presented here has
proven to be an effective application for the fast identification of
toxic gases.
Abstract: The recommended limit for cadmium concentration in
potable water is less than 0.005 mg/L. A continuous biosorption
process using indigenous red seaweed, Gracilaria corticata, was
performed to remove cadmium from the potable water. The process
was conducted under fixed conditions and the breakthrough curves
were achieved for three consecutive sorption-desorption cycles. A
modeling based on Artificial Neural Network (ANN) was employed
to fit the experimental breakthrough data. In addition, a simplified
semi empirical model, Thomas, was employed for this purpose. It
was found that ANN well described the experimental data (R2>0.99)
while the Thomas prediction were a bit less successful with R2>0.97.
The adjusted design parameters using the nonlinear form of Thomas
model was in a good agreement with the experimentally obtained
ones. The results approve the capability of ANN to predict the
cadmium concentration in potable water.
Abstract: Nowadays social media information, such as news,
links, images, or VDOs, is shared extensively. However, the
effectiveness of disseminating information through social media
lacks in quality: less fact checking, more biases, and several rumors.
Many researchers have investigated about credibility on Twitter, but
there is no the research report about credibility information on
Facebook. This paper proposes features for measuring credibility on
Facebook information. We developed the system for credibility on
Facebook. First, we have developed FB credibility evaluator for
measuring credibility of each post by manual human’s labelling. We
then collected the training data for creating a model using Support
Vector Machine (SVM). Secondly, we developed a chrome extension
of FB credibility for Facebook users to evaluate the credibility of
each post. Based on the usage analysis of our FB credibility chrome
extension, about 81% of users’ responses agree with suggested
credibility automatically computed by the proposed system.
Abstract: e-Service has moved from the usual manual and
traditional way of rendering services to electronic service provision
for the public and there are several reasons for implementing these
services, Airline ticketing have gone from its manual traditional way
to an intelligent web-driven service of purchasing. Many companies
have seen their profits doubled through the use of online services in
their operation and a typical example is Hewlett Packard (HP) which
is rapidly transforming their after sales business into a profit
generating e-service business unit.
This paper will examine the various challenges confronting e-
Service adoption and implementation in Nigeria and also analyse
lessons learnt from e-Service adoption and implementation in Asia to
see how it could be useful in Nigeria which is a lower middle income
country. From the analysis of the online survey data, it has been
identified that the public in Nigeria are much aware of e-Services but
successful adoption and implementation have been the problems
faced.
Abstract: Artificial Neural Network (ANN) can be trained using
back propagation (BP). It is the most widely used algorithm for
supervised learning with multi-layered feed-forward networks.
Efficient learning by the BP algorithm is required for many practical
applications. The BP algorithm calculates the weight changes of
artificial neural networks, and a common approach is to use a twoterm
algorithm consisting of a learning rate (LR) and a momentum
factor (MF). The major drawbacks of the two-term BP learning
algorithm are the problems of local minima and slow convergence
speeds, which limit the scope for real-time applications. Recently the
addition of an extra term, called a proportional factor (PF), to the
two-term BP algorithm was proposed. The third increases the speed
of the BP algorithm. However, the PF term also reduces the
convergence of the BP algorithm, and criteria for evaluating
convergence are required to facilitate the application of the three
terms BP algorithm. Although these two seem to be closely related,
as described later, we summarize various improvements to overcome
the drawbacks. Here we compare the different methods of
convergence of the new three-term BP algorithm.
Abstract: Operations research science (OR) deals with good
success in developing and applying scientific methods for problem
solving and decision-making. However, by using OR techniques, we
can enhance the use of computer decision support systems to achieve
optimal management for institutions. OR applies comprehensive
analysis including all factors that effect on it and builds mathematical
modeling to solve business or organizational problems. In addition, it
improves decision-making and uses available resources efficiently.
The adoption of OR by universities would definitely contributes to
the development and enhancement of the performance of OR
techniques. This paper provides an understanding of the structures,
approaches and models of OR in problem solving and decisionmaking.
Abstract: Passing the entrance exam to a university is a major
step in one's life. University entrance exam commonly known as
Kankor is the nationwide entrance exam in Afghanistan. This
examination is prerequisite for all public and private higher education
institutions at undergraduate level. It is usually taken by students who
are graduated from high schools. In this paper, we reflect the major
educational school graduates issues and propose ICT-based test
preparation environment, known as ‘Online Kankor Exam Prep
System’ to give students the tools to help them pass the university
entrance exam on the first try. The system is based on Intelligent
Tutoring System (ITS), which introduced an essential package of
educational technology for learners that features: (I) exam-focused
questions and content; (ii) self-assessment environment; and (iii) test
preparation strategies in order to help students to acquire the necessary
skills in their carrier and keep them up-to-date with instruction.
Abstract: In this paper we describe the Levenvberg-Marquardt
(LM) algorithm for identification and equalization of CDMA
signals received by an antenna array in communication channels.
The synthesis explains the digital separation and equalization of
signals after propagation through multipath generating intersymbol
interference (ISI). Exploiting discrete data transmitted and three
diversities induced at the reception, the problem can be composed
by the Block Component Decomposition (BCD) of a tensor of
order 3 which is a new tensor decomposition generalizing the
PARAFAC decomposition. We optimize the BCD decomposition by
Levenvberg-Marquardt method gives encouraging results compared to
classical alternating least squares algorithm (ALS). In the equalization
part, we use the Minimum Mean Square Error (MMSE) to perform
the presented method. The simulation results using the LM algorithm
are important.
Abstract: In this study, we propose a novel technique for acoustic
echo suppression (AES) during speech recognition under barge-in
conditions. Conventional AES methods based on spectral subtraction
apply fixed weights to the estimated echo path transfer function
(EPTF) at the current signal segment and to the EPTF estimated until
the previous time interval. However, the effects of echo path changes
should be considered for eliminating the undesired echoes. We
describe a new approach that adaptively updates weight parameters in
response to abrupt changes in the acoustic environment due to
background noises or double-talk. Furthermore, we devised a voice
activity detector and an initial time-delay estimator for barge-in speech
recognition in communication networks. The initial time delay is
estimated using log-spectral distance measure, as well as
cross-correlation coefficients. The experimental results show that the
developed techniques can be successfully applied in barge-in speech
recognition systems.
Abstract: In this study, data loss tolerance of Support Vector Machines (SVM) based activity recognition model and multi activity classification performance when data are received over a lossy wireless sensor network is examined. Initially, the classification algorithm we use is evaluated in terms of resilience to random data loss with 3D acceleration sensor data for sitting, lying, walking and standing actions. The results show that the proposed classification method can recognize these activities successfully despite high data loss. Secondly, the effect of differentiated quality of service performance on activity recognition success is measured with activity data acquired from a multi hop wireless sensor network, which introduces high data loss. The effect of number of nodes on the reliability and multi activity classification success is demonstrated in simulation environment. To the best of our knowledge, the effect of data loss in a wireless sensor network on activity detection success rate of an SVM based classification algorithm has not been studied before.
Abstract: Spam is any unwanted electronic message or material
in any form posted too many people. As the world is growing as
global world, social networking sites play an important role in
making world global providing people from different parts of the
world a platform to meet and express their views. Among different
social networking sites Facebook become the leading one. With
increase in usage different users start abusive use of Facebook by
posting or creating ways to post spam. This paper highlights the
potential spam types nowadays Facebook users’ faces. This paper
also provide the reason how user become victim to spam attack. A
methodology is proposed in the end discusses how to handle different
types of spam.
Abstract: In this paper a new algorithm to generate random
simple polygons from a given set of points in a two dimensional
plane is designed. The proposed algorithm uses a genetic algorithm to
generate polygons with few vertices. A new merge algorithm is
presented which converts any two polygons into a simple polygon.
This algorithm at first changes two polygons into a polygonal chain
and then the polygonal chain is converted into a simple polygon. The
process of converting a polygonal chain into a simple polygon is
based on the removal of intersecting edges. The experiments results
show that the proposed algorithm has the ability to generate a great
number of different simple polygons and has better performance in
comparison to celebrated algorithms such as space partitioning and
steady growth.
Abstract: Evaluating the performance of a simulator in the
CAVE has to be confirmed by encouraging people to live the
experience of virtual reality. In this paper, a detailed procedure of
recording video is presented. Limitations of the experimental device
are firstly exposed. Then, solutions for improving this idea are finally
described.
Abstract: In this paper, we propose a method for three-dimensional
(3-D)-model indexing based on defining a new
descriptor, which we call new descriptor using spherical harmonics.
The purpose of the method is to minimize, the processing time on the
database of objects models and the searching time of similar objects
to request object.
Firstly we start by defining the new descriptor using a new
division of 3-D object in a sphere. Then we define a new distance
which will be used in the search for similar objects in the database.