Abstract: The goal of a network-based intrusion detection
system is to classify activities of network traffics into two major
categories: normal and attack (intrusive) activities. Nowadays, data
mining and machine learning plays an important role in many
sciences; including intrusion detection system (IDS) using both
supervised and unsupervised techniques. However, one of the
essential steps of data mining is feature selection that helps in
improving the efficiency, performance and prediction rate of
proposed approach. This paper applies unsupervised K-means
clustering algorithm with information gain (IG) for feature selection
and reduction to build a network intrusion detection system. For our
experimental analysis, we have used the new NSL-KDD dataset,
which is a modified dataset for KDDCup 1999 intrusion detection
benchmark dataset. With a split of 60.0% for the training set and the
remainder for the testing set, a 2 class classifications have been
implemented (Normal, Attack). Weka framework which is a java
based open source software consists of a collection of machine
learning algorithms for data mining tasks has been used in the testing
process. The experimental results show that the proposed approach is
very accurate with low false positive rate and high true positive rate
and it takes less learning time in comparison with using the full
features of the dataset with the same algorithm.
Abstract: In this paper, several improvements are proposed to
previous work of automated classification of alcoholics and nonalcoholics.
In the previous paper, multiplayer-perceptron neural
network classifying energy of gamma band Visual Evoked Potential
(VEP) signals gave the best classification performance using 800
VEP signals from 10 alcoholics and 10 non-alcoholics. Here, the
dataset is extended to include 3560 VEP signals from 102 subjects:
62 alcoholics and 40 non-alcoholics. Three modifications are
introduced to improve the classification performance: i) increasing
the gamma band spectral range by increasing the pass-band width of
the used filter ii) the use of Multiple Signal Classification algorithm
to obtain the power of the dominant frequency in gamma band VEP
signals as features and iii) the use of the simple but effective knearest
neighbour classifier. To validate that these two modifications
do give improved performance, a 10-fold cross validation
classification (CVC) scheme is used. Repeat experiments of the
previously used methodology for the extended dataset are performed
here and improvement from 94.49% to 98.71% in maximum
averaged CVC accuracy is obtained using the modifications. This
latest results show that VEP based classification of alcoholics is
worth exploring further for system development.
Abstract: In Content-Based Image Retrieval systems it is
important to use an efficient indexing technique in order to perform
and accelerate the search in huge databases. The used indexing
technique should also support the high dimensions of image features.
In this paper we present the hierarchical index NOHIS-tree (Non
Overlapping Hierarchical Index Structure) when we scale up to very
large databases. We also present a study of the influence of clustering
on search time. The performance test results show that NOHIS-tree
performs better than SR-tree. Tests also show that NOHIS-tree keeps
its performances in high dimensional spaces. We include the
performance test that try to determine the number of clusters in
NOHIS-tree to have the best search time.
Abstract: It is well-known that in wireless local area networks,
authenticating nodes by their MAC addresses is not secure since it is
very easy for an attacker to learn one of the authorized addresses and
change his MAC address accordingly. In this paper, in order to
prevent MAC address spoofing attacks, we propose to use
dynamically changing MAC addresses and make each address usable
for only one session. The scheme we propose does not require any
change in 802.11 protocols and incurs only a small performance
overhead. One of the nice features of our new scheme is that no third
party can link different communication sessions of the same user by
monitoring MAC addresses therefore our scheme is preferable also
with respect to user privacy.
Abstract: Current proposals for E-passport or ID-Card is similar to a regular passport with the addition of tiny contactless integrated circuit (computer chip) inserted in the back cover, which will act as a secure storage device of the same data visually displayed on the photo page of the passport. In addition, it will include a digital photograph that will enable biometric comparison, through the use of facial recognition technology at international borders. Moreover, the e-passport will have a new interface, incorporating additional antifraud and security features. However, its problems are reliability, security and privacy. Privacy is a serious issue since there is no encryption between the readers and the E-passport. However, security issues such as authentication, data protection and control techniques cannot be embedded in one process. In this paper, design and prototype implementation of an improved E-passport reader is presented. The passport holder is authenticated online by using GSM network. The GSM network is the main interface between identification center and the e-passport reader. The communication data is protected between server and e-passport reader by using AES to encrypt data for protection will transferring through GSM network. Performance measurements indicate a 19% improvement in encryption cycles versus previously reported results.
Abstract: In this paper, we validate crater detection in moon surface image using FLDA. This proposal assumes that it is applied to SLIM (Smart Lander for Investigating Moon) project aiming at the pin-point landing to the moon surface. The point where the lander should land is judged by the position relations of the craters obtained via camera, so the real-time image processing becomes important element. Besides, in the SLIM project, 400kg-class lander is assumed, therefore, high-performance computers for image processing cannot be equipped. We are studying various crater detection methods such as Haar-Like features, LBP, and PCA. And we think these methods are appropriate to the project, however, to identify the unlearned images obtained by actual is insufficient. In this paper, we examine the crater detection using FLDA, and compare with the conventional methods.
Abstract: This paper features the trajectory planning design of a indigenously developed 4-Axis SCARA robot which is used for doing successful robotic manipulation task in the laboratory. Once, a trajectory is being designed and given as input to the robot, the robot's gripper tip moves along that specified trajectory. Trajectories have to be designed in the work space only. The main idea of this paper is to design a continuous path trajectory model for the indigenously developed SCARA robot arm during its maneuvering from one point to another point (during pick and place operations) in a workspace avoiding all the obstacles in its path of motion.
Abstract: Pure phase gallosilicate nitrite sodalite has been synthesized in a single step by low temperature (373 oK) hydrothermal technique. The product obtained was characterized using a combination of techniques including X-ray powder diffraction, IR, Raman spectroscopy, SEM, MAS NMR spectroscopy as well as thermogravimetry. Sodalite with an ideal composition was obtained after synthesis at 3730K and seven days duration using alkaline medium. The structural features of the Na8[GaSiO4]6(NO2)2 sodalite were investigated by IR, MAS NMR spectroscopy of 29Si and 23Na nuclei and by Reitveld refinement of X-ray powder diffraction data. The crystal structure of this sodalite has been refined in the space group P 4 3n; with a cell parameter 8.98386Å, V= 726.9 Å, (Rwp= 0.077 and Rp=0.0537) and Si-O-Ga angle is found to be 132.920 . MAS NMR study confirms complete ordering of Si and Ga in the gallosilicate framework. The surface area of single entity with stoichiometry Na8[GaSiO4]6(NO2)2 was found to be 8.083 x10-15 cm2/g.
Abstract: The radius-of-curvature (ROC) defines the degree of
curvature along the centerline of a roadway whereby a travelling
vehicle must follow. Roadway designs must encompass ROC in
mitigating the cost of earthwork associated with construction while
also allowing vehicles to travel at maximum allowable design speeds.
Thus, a road will tend to follow natural topography where possible,
but curvature must also be optimized to permit fast, but safe vehicle
speeds. The more severe the curvature of the road, the slower the
permissible vehicle speed. For route planning, whether for urban
settings, emergency operations, or even parcel delivery, ROC is a
necessary attribute of road arcs for computing travel time.
It is extremely rare for a geo-spatial database to contain ROC. This
paper will present a procedure and mathematical algorithm to
calculate and assign ROC to a segment pair and/or polyline.
Abstract: A new sythetic gene coding for a Human
Elastin-Like Polypeptide was constructed and expressed. The
recombinant product was tested as coating agent to realize a
surface suitable for cell growth. Coatings showed peculiar
features and different human cell lines were seeded and
cultured. All cell lines tested showed to adhere and proliferate
on this substrate that has been shown also to exert a specific
effect on cells, depending on cell type.
Abstract: The technique of k-anonymization has been proposed to obfuscate private data through associating it with at least k identities. This paper investigates the basic tabular structures that
underline the notion of k-anonymization using cell suppression.
These structures are studied under idealized conditions to identify the
essential features of the k-anonymization notion. We optimize data kanonymization
through requiring a minimum number of anonymized
values that are balanced over all columns and rows. We study the
relationship between the sizes of the anonymized tables, the value k, and the number of attributes. This study has a theoretical value through contributing to develop a mathematical foundation of the kanonymization
concept. Its practical significance is still to be
investigated.
Abstract: This paper used a fuzzy kohonen neural network for medical image segmentation. Image segmentation plays a important role in the many of medical imaging applications by automating or facilitating the diagnostic. The paper analyses the tumor by extraction of the features of (area, entropy, means and standard deviation).These measurements gives a description for a tumor.
Abstract: The African Great Lakes Region refers to the zone
around lakes Victoria, Tanganyika, Albert, Edward, Kivu, and
Malawi. The main source of electricity in this region is hydropower
whose systems are generally characterized by relatively weak,
isolated power schemes, poor maintenance and technical deficiencies
with limited electricity infrastructures. Most of the hydro sources are
rain fed, and as such there is normally a deficiency of water during
the dry seasons and extended droughts. In such calamities fossil fuels
sources, in particular petroleum products and natural gas, are
normally used to rescue the situation but apart from them being nonrenewable,
they also release huge amount of green house gases to our
environment which in turn accelerates the global warming that has at
present reached an amazing stage. Wind power is ample, renewable,
widely distributed, clean, and free energy source that does not
consume or pollute water. Wind generated electricity is one of the
most practical and commercially viable option for grid quality and
utility scale electricity production. However, the main shortcoming
associated with electric wind power generation is fluctuation in its
output both in space and time. Before making a decision to establish
a wind park at a site, the wind speed features there should therefore
be known thoroughly as well as local demand or transmission
capacity. The main objective of this paper is to utilise monthly
average wind speed data collected from one prospective site within
the African Great Lakes Region to demonstrate that the available
wind power there is high enough to generate electricity. The mean
monthly values were calculated from records gathered on hourly
basis for a period of 5 years (2001 to 2005) from a site in Tanzania.
The documentations that were collected at a height of 2 m were
projected to a height of 50 m which is the standard hub height of
wind turbines. The overall monthly average wind speed was found to
be 12.11 m/s whereas June to November was established to be the
windy season as the wind speed during the session is above the
overall monthly wind speed. The available wind power density
corresponding to the overall mean monthly wind speed was evaluated
to be 1072 W/m2, a potential that is worthwhile harvesting for the
purpose of electric generation.
Abstract: Wireless Sensor and Actor Networks (WSANs) constitute an emerging and pervasive technology that is attracting increasing interest in the research community for a wide range of applications. WSANs have two important requirements: coordination interactions and real-time communication to perform correct and timely actions. This paper introduces a methodology to facilitate the task of the application programmer focusing on the coordination and real-time requirements of WSANs. The methodology proposed in this model uses a real-time component model, UM-RTCOM, which will help us to achieve the design and implementation of applications in WSAN by using the component oriented paradigm. This will help us to develop software components which offer some very interesting features, such as reusability and adaptability which are very suitable for WSANs as they are very dynamic environments with rapidly changing conditions. In addition, a high-level coordination model based on tuple channels (TC-WSAN) is integrated into the methodology by providing a component-based specification of this model in UM-RTCOM; this will allow us to satisfy both sensor-actor and actor-actor coordination requirements in WSANs. Finally, we present in this paper the design and implementation of an application which will help us to show how the methodology can be easily used in order to achieve the development of WSANs applications.
Abstract: Learning using labeled and unlabelled data has
received considerable amount of attention in the machine learning
community due its potential in reducing the need for expensive
labeled data. In this work we present a new method for combining
labeled and unlabeled data based on classifier ensembles. The model
we propose assumes each classifier in the ensemble observes the
input using different set of features. Classifiers are initially trained
using some labeled samples. The trained classifiers learn further
through labeling the unknown patterns using a teaching signals that is
generated using the decision of the classifier ensemble, i.e. the
classifiers self-supervise each other. Experiments on a set of object
images are presented. Our experiments investigate different classifier
models, different fusing techniques, different training sizes and
different input features. Experimental results reveal that the proposed
self-supervised ensemble learning approach reduces classification
error over the single classifier and the traditional ensemble classifier
approachs.
Abstract: The novelty proposed in this study is twofold and consists in the developing of a new color similarity metric based on the human visual system and a new color indexing based on a textual approach. The new color similarity metric proposed is based on the color perception of the human visual system. Consequently the results returned by the indexing system can fulfill as much as possibile the user expectations. We developed a web application to collect the users judgments about the similarities between colors, whose results are used to estimate the metric proposed in this study. In order to index the image's colors, we used a text indexing engine to facilitate the integration of visual features in a database of text documents. The textual signature is build by weighting the image's colors in according to their occurrence in the image. The use of a textual indexing engine, provide us a simple, fast and robust solution to index images. A typical usage of the system proposed in this study, is the development of applications whose data type is both visual and textual. In order to evaluate the proposed method we chose a price comparison engine as a case of study, collecting a series of commercial offers containing the textual description and the image representing a specific commercial offer.
Abstract: The international society focuses on the environment
protection and natural energy sources control for the global
cooperation against weather change and sustainable growth. The study
presents the overview of the water shortage status and the necessity of wastewater reuse facility in military facilities and for the possibility of
the introduction, compares the economics by means of cost-benefit
analysis. The military features such as the number of users of military barracks and the water use were surveyed by the design principles by
facility types, the application method of wastewater reuse facility was selected, the feed water, its application and the volume of reuse volume were defined and the expectation was estimated, confirming
the possibility of introducing a wastewater reuse possibility by means of cost-benefit analysis.
Abstract: HIV-1 genome is highly heterogeneous. Due to this
variation, features of HIV-I genome is in a wide range. For this
reason, the ability to infection of the virus changes depending on
different chemokine receptors. From this point of view, R5 HIV
viruses use CCR5 coreceptor while X4 viruses use CXCR5 and
R5X4 viruses can utilize both coreceptors. Recently, in
Bioinformatics, R5X4 viruses have been studied to classify by using
the experiments on HIV-1 genome.
In this study, R5X4 type of HIV viruses were classified using
Auto Regressive (AR) model through Artificial Neural Networks
(ANNs). The statistical data of R5X4, R5 and X4 viruses was
analyzed by using signal processing methods and ANNs. Accessible
residues of these virus sequences were obtained and modeled by AR
model since the dimension of residues is large and different from
each other. Finally the pre-processed data was used to evolve various
ANN structures for determining R5X4 viruses. Furthermore ROC
analysis was applied to ANNs to show their real performances. The
results indicate that R5X4 viruses successfully classified with high
sensitivity and specificity values training and testing ROC analysis
for RBF, which gives the best performance among ANN structures.
Abstract: German electricity European options on futures using
Lévy processes for the underlying asset are examined. Implied
volatility evolution, under each of the considered models, is
discussed after calibrating for the Merton jump diffusion (MJD),
variance gamma (VG), normal inverse Gaussian (NIG), Carr, Geman,
Madan and Yor (CGMY) and the Black and Scholes (B&S) model.
Implied volatility is examined for the entire sample period, revealing
some curious features about market evolution, where data fitting
performances of the five models are compared. It is shown that
variance gamma processes provide relatively better results and that
implied volatility shows significant differences through time, having
increasingly evolved. Volatility changes for changed uncertainty, or
else, increasing futures prices and there is evidence for the need to
account for seasonality when modelling both electricity spot/futures
prices and volatility.
Abstract: The image segmentation method described in this
paper has been developed as a pre-processing stage to be used in
methodologies and tools for video/image indexing and retrieval by
content. This method solves the problem of whole objects extraction
from background and it produces images of single complete objects
from videos or photos. The extracted images are used for calculating
the object visual features necessary for both indexing and retrieval
processes.
The segmentation algorithm is based on the cooperation among an
optical flow evaluation method, edge detection and region growing
procedures. The optical flow estimator belongs to the class of
differential methods. It permits to detect motions ranging from a
fraction of a pixel to a few pixels per frame, achieving good results in
presence of noise without the need of a filtering pre-processing stage
and includes a specialised model for moving object detection.
The first task of the presented method exploits the cues from
motion analysis for moving areas detection. Objects and background
are then refined using respectively edge detection and seeded region
growing procedures. All the tasks are iteratively performed until
objects and background are completely resolved.
The method has been applied to a variety of indoor and outdoor
scenes where objects of different type and shape are represented on
variously textured background.