Abstract: One of the popular methods for recognition of facial
expressions such as happiness, sadness and surprise is based on
deformation of facial features. Motion vectors which show these
deformations can be specified by the optical flow. In this method, for
detecting emotions, the resulted set of motion vectors are compared
with standard deformation template that caused by facial expressions.
In this paper, a new method is introduced to compute the quantity of
likeness in order to make decision based on the importance of
obtained vectors from an optical flow approach. For finding the
vectors, one of the efficient optical flow method developed by
Gautama and VanHulle[17] is used. The suggested method has been
examined over Cohn-Kanade AU-Coded Facial Expression Database,
one of the most comprehensive collections of test images available.
The experimental results show that our method could correctly
recognize the facial expressions in 94% of case studies. The results
also show that only a few number of image frames (three frames) are
sufficient to detect facial expressions with rate of success of about
83.3%. This is a significant improvement over the available methods.
Abstract: Segmentation is an important step in medical image
analysis and classification for radiological evaluation or computer
aided diagnosis. This paper presents the problem of inaccurate lung
segmentation as observed in algorithms presented by researchers
working in the area of medical image analysis. The different lung
segmentation techniques have been tested using the dataset of 19
patients consisting of a total of 917 images. We obtained datasets of
11 patients from Ackron University, USA and of 8 patients from
AGA Khan Medical University, Pakistan. After testing the algorithms
against datasets, the deficiencies of each algorithm have been
highlighted.
Abstract: Using spatial models as a shared common basis of
information about the environment for different kinds of contextaware
systems has been a heavily researched topic in the last years.
Thereby the research focused on how to create, to update, and to
merge spatial models so as to enable highly dynamic, consistent and
coherent spatial models at large scale. In this paper however, we
want to concentrate on how context-aware applications could use this
information so as to adapt their behavior according to the situation
they are in. The main idea is to provide the spatial model
infrastructure with a situation recognition component based on
generic situation templates. A situation template is – as part of a
much larger situation template library – an abstract, machinereadable
description of a certain basic situation type, which could be
used by different applications to evaluate their situation. In this
paper, different theoretical and practical issues – technical, ethical
and philosophical ones – are discussed important for understanding
and developing situation dependent systems based on situation
templates. A basic system design is presented which allows for the
reasoning with uncertain data using an improved version of a
learning algorithm for the automatic adaption of situation templates.
Finally, for supporting the development of adaptive applications, we
present a new situation-aware adaptation concept based on
workflows.
Abstract: This paper compares Hilditch, Rosenfeld, Zhang-
Suen, dan Nagendraprasad Wang Gupta (NWG) thinning algorithms
for Javanese character image recognition. Thinning is an effective
process when the focus in not on the size of the pattern, but rather on
the relative position of the strokes in the pattern. The research
analyzes the thinning of 60 Javanese characters.
Time-wise, Zhang-Suen algorithm gives the best results with the
average process time being 0.00455188 seconds. But if we look at
the percentage of pixels that meet one-pixel thickness, Rosenfelt
algorithm gives the best results, with a 99.98% success rate. From the
number of pixels that are erased, NWG algorithm gives the best
results with the average number of pixels erased being 84.12%. It can
be concluded that the Hilditch algorithm performs least successfully
compared to the other three algorithms.
Abstract: The identification and elimination of bad
measurements is one of the basic functions of a robust state estimator
as bad data have the effect of corrupting the results of state
estimation according to the popular weighted least squares method.
However this is a difficult problem to handle especially when dealing
with multiple errors from the interactive conforming type. In this
paper, a self adaptive genetic based algorithm is proposed. The
algorithm utilizes the results of the classical linearized normal
residuals approach to tune the genetic operators thus instead of
making a randomized search throughout the whole search space it is
more likely to be a directed search thus the optimum solution is
obtained at very early stages(maximum of 5 generations). The
algorithm utilizes the accumulating databases of already computed
cases to reduce the computational burden to minimum. Tests are
conducted with reference to the standard IEEE test systems. Test
results are very promising.
Abstract: The wireless sensor networks have been extensively
deployed and researched. One of the major issues in wireless sensor
networks is a developing energy-efficient clustering protocol.
Clustering algorithm provides an effective way to prolong the lifetime
of a wireless sensor networks. In the paper, we compare several
clustering protocols which significantly affect a balancing of energy
consumption. And we propose an Energy-Efficient Distributed
Unequal Clustering (EEDUC) algorithm which provides a new way of
creating distributed clusters. In EEDUC, each sensor node sets the
waiting time. This waiting time is considered as a function of residual
energy, number of neighborhood nodes. EEDUC uses waiting time to
distribute cluster heads. We also propose an unequal clustering
mechanism to solve the hot-spot problem. Simulation results show that
EEDUC distributes the cluster heads, balances the energy
consumption well among the cluster heads and increases the network
lifetime.
Abstract: In this paper we consider a one-dimensional random
geometric graph process with the inter-nodal gaps evolving according
to an exponential AR(1) process. The transition probability matrix
and stationary distribution are derived for the Markov chains concerning
connectivity and the number of components. We analyze the
algorithm for hitting time regarding disconnectivity. In addition to
dynamical properties, we also study topological properties for static
snapshots. We obtain the degree distributions as well as asymptotic
precise bounds and strong law of large numbers for connectivity
threshold distance and the largest nearest neighbor distance amongst
others. Both exact results and limit theorems are provided in this
paper.
Abstract: The shortest path routing problem is a multiobjective
nonlinear optimization problem with constraints. This problem has
been addressed by considering Quality of service parameters, delay
and cost objectives separately or as a weighted sum of both
objectives. Multiobjective evolutionary algorithms can find multiple
pareto-optimal solutions in one single run and this ability makes them
attractive for solving problems with multiple and conflicting
objectives. This paper uses an elitist multiobjective evolutionary
algorithm based on the Non-dominated Sorting Genetic Algorithm
(NSGA), for solving the dynamic shortest path routing problem in
computer networks. A priority-based encoding scheme is proposed
for population initialization. Elitism ensures that the best solution
does not deteriorate in the next generations. Results for a sample test
network have been presented to demonstrate the capabilities of the
proposed approach to generate well-distributed pareto-optimal
solutions of dynamic routing problem in one single run. The results
obtained by NSGA are compared with single objective weighting
factor method for which Genetic Algorithm (GA) was applied.
Abstract: This paper proposes a Particle Swarm Optimization
(PSO) based technique for the optimal allocation of Distributed
Generation (DG) units in the power systems. In this paper our aim is
to decide optimal number, type, size and location of DG units for
voltage profile improvement and power loss reduction in distribution
network. Two types of DGs are considered and the distribution load
flow is used to calculate exact loss. Load flow algorithm is combined
appropriately with PSO till access to acceptable results of this
operation. The suggested method is programmed under MATLAB
software. Test results indicate that PSO method can obtain better
results than the simple heuristic search method on the 30-bus and 33-
bus radial distribution systems. It can obtain maximum loss reduction
for each of two types of optimally placed multi-DGs. Moreover,
voltage profile improvement is achieved.
Abstract: Most of the real queuing systems include special properties and constraints, which can not be analyzed directly by using the results of solved classical queuing models. Lack of Markov chains features, unexponential patterns and service constraints, are the mentioned conditions. This paper represents an applied general algorithm for analysis and optimizing the queuing systems. The algorithm stages are described through a real case study. It is consisted of an almost completed non-Markov system with limited number of customers and capacities as well as lots of common exception of real queuing networks. Simulation is used for optimizing this system. So introduced stages over the following article include primary modeling, determining queuing system kinds, index defining, statistical analysis and goodness of fit test, validation of model and optimizing methods of system with simulation.
Abstract: Artificial Immune System is adopted as a Heuristic
Algorithm to solve the combinatorial problems for decades.
Nevertheless, many of these applications took advantage of the benefit
for applications but seldom proposed approaches for enhancing the
efficiency. In this paper, we continue the previous research to develop
a Self-evolving Artificial Immune System II via coordinating the T
and B cell in Immune System and built a block-based artificial
chromosome for speeding up the computation time and better
performance for different complexities of problems. Through the
design of Plasma cell and clonal selection which are relative the
function of the Immune Response. The Immune Response will help
the AIS have the global and local searching ability and preventing
trapped in local optima. From the experimental result, the significant
performance validates the SEAIS II is effective when solving the
permutation flows-hop problems.
Abstract: The purpose of this study was to present a reliable mean for human-computer interfacing based on finger gestures made in two dimensions, which could be interpreted and adequately used in controlling a remote robot's movement. The gestures were captured and interpreted using an algorithm based on trigonometric functions, in calculating the angular displacement from one point of touch to another as the user-s finger moved within a time interval; thereby allowing for pattern spotting of the captured gesture. In this paper the design and implementation of such a gesture based user interface was presented, utilizing the aforementioned algorithm. These techniques were then used to control a remote mobile robot's movement. A resistive touch screen was selected as the gesture sensor, then utilizing a programmed microcontroller to interpret them respectively.
Abstract: In Image processing the Image compression can improve
the performance of the digital systems by reducing the cost and
time in image storage and transmission without significant reduction
of the Image quality. This paper describes hardware architecture of
low complexity Discrete Cosine Transform (DCT) architecture for
image compression[6]. In this DCT architecture, common computations
are identified and shared to remove redundant computations
in DCT matrix operation. Vector processing is a method used for
implementation of DCT. This reduction in computational complexity
of 2D DCT reduces power consumption. The 2D DCT is performed
on 8x8 matrix using two 1-Dimensional Discrete cosine transform
blocks and a transposition memory [7]. Inverse discrete cosine
transform (IDCT) is performed to obtain the image matrix and
reconstruct the original image. The proposed image compression
algorithm is comprehended using MATLAB code. The VLSI design
of the architecture is implemented Using Verilog HDL. The proposed
hardware architecture for image compression employing DCT was
synthesized using RTL complier and it was mapped using 180nm
standard cells. . The Simulation is done using Modelsim. The
simulation results from MATLAB and Verilog HDL are compared.
Detailed analysis for power and area was done using RTL compiler
from CADENCE. Power consumption of DCT core is reduced to
1.027mW with minimum area[1].
Abstract: Since communications between tag and reader in RFID
system are by radio, anyone can access the tag and obtain its any
information. And a tag always replies with the same ID so that it is
hard to distinguish between a real and a fake tag. Thus, there are many
security problems in today-s RFID System. Firstly, unauthorized
reader can easily read the ID information of any Tag. Secondly,
Adversary can easily cheat the legitimate reader using the collected
Tag ID information, such as the any legitimate Tag. These security
problems can be typically solved by encryption of messages
transmitted between Tag and Reader and by authentication for Tag.
In this paper, to solve these security problems on RFID system, we
propose the Tag Authentication Scheme based on self shrinking
generator (SSG). SSG Algorithm using in our scheme is proposed by
W.Meier and O.Staffelbach in EUROCRYPT-94. This Algorithm is
organized that only one LFSR and selection logic in order to generate
random stream. Thus it is optimized to implement the hardware logic
on devices with extremely limited resource, and the output generating
from SSG at each time do role as random stream so that it is allow our
to design the light-weight authentication scheme with security against
some network attacks. Therefore, we propose the novel tag
authentication scheme which use SSG to encrypt the Tag-ID
transmitted from tag to reader and achieve authentication of tag.
Abstract: In this paper, an efficient local appearance feature
extraction method based the multi-resolution Curvelet transform is
proposed in order to further enhance the performance of the well
known Linear Discriminant Analysis(LDA) method when applied
to face recognition. Each face is described by a subset of band
filtered images containing block-based Curvelet coefficients. These
coefficients characterize the face texture and a set of simple statistical
measures allows us to form compact and meaningful feature vectors.
The proposed method is compared with some related feature extraction
methods such as Principal component analysis (PCA), as well
as Linear Discriminant Analysis LDA, and independent component
Analysis (ICA). Two different muti-resolution transforms, Wavelet
(DWT) and Contourlet, were also compared against the Block Based
Curvelet-LDA algorithm. Experimental results on ORL, YALE and
FERET face databases convince us that the proposed method provides
a better representation of the class information and obtains much
higher recognition accuracies.
Abstract: The design of a pattern classifier includes an attempt
to select, among a set of possible features, a minimum subset of
weakly correlated features that better discriminate the pattern classes.
This is usually a difficult task in practice, normally requiring the
application of heuristic knowledge about the specific problem
domain. The selection and quality of the features representing each
pattern have a considerable bearing on the success of subsequent
pattern classification. Feature extraction is the process of deriving
new features from the original features in order to reduce the cost of
feature measurement, increase classifier efficiency, and allow higher
classification accuracy. Many current feature extraction techniques
involve linear transformations of the original pattern vectors to new
vectors of lower dimensionality. While this is useful for data
visualization and increasing classification efficiency, it does not
necessarily reduce the number of features that must be measured
since each new feature may be a linear combination of all of the
features in the original pattern vector. In this paper a new approach is
presented to feature extraction in which feature selection, feature
extraction, and classifier training are performed simultaneously using
a genetic algorithm. In this approach each feature value is first
normalized by a linear equation, then scaled by the associated weight
prior to training, testing, and classification. A knn classifier is used to
evaluate each set of feature weights. The genetic algorithm optimizes
a vector of feature weights, which are used to scale the individual
features in the original pattern vectors in either a linear or a nonlinear
fashion. By this approach, the number of features used in classifying
can be finely reduced.
Abstract: A new approach based on the consideration that electroencephalogram (EEG) signals are chaotic signals was presented for automated diagnosis of electroencephalographic changes. This consideration was tested successfully using the nonlinear dynamics tools, like the computation of Lyapunov exponents. This paper presented the usage of statistics over the set of the Lyapunov exponents in order to reduce the dimensionality of the extracted feature vectors. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of electroencephalographic changes. Three types of EEG signals (EEG signals recorded from healthy volunteers with eyes open, epilepsy patients in the epileptogenic zone during a seizure-free interval, and epilepsy patients during epileptic seizures) were classified. The selected Lyapunov exponents of the EEG signals were used as inputs of the MLPNN trained with Levenberg- Marquardt algorithm. The classification results confirmed that the proposed MLPNN has potential in detecting the electroencephalographic changes.
Abstract: Wireless Sensor networks have a wide spectrum of civil and military applications that call for secure communication such as the terrorist tracking, target surveillance in hostile environments. For the secure communication in these application areas, we propose a method for generating a hierarchical key structure for the efficient group key management. In this paper, we apply A* algorithm in generating a hierarchical key structure by considering the history data of the ratio of addition and eviction of sensor nodes in a location where sensor nodes are deployed. Thus generated key tree structure provides an efficient way of managing the group key in terms of energy consumption when addition and eviction event occurs. A* algorithm tries to minimize the number of messages needed for group key management by the history data. The experimentation with the tree shows efficiency of the proposed method.
Abstract: In this paper the problem of estimating the time delay
between two spatially separated noisy sinusoidal signals by system
identification modeling is addressed. The system is assumed to be
perturbed by both input and output additive white Gaussian noise. The
presence of input noise introduces bias in the time delay estimates.
Normally the solution requires a priori knowledge of the input-output
noise variance ratio. We utilize the cascade of a self-tuned filter with
the time delay estimator, thus making the delay estimates robust to
input noise. Simulation results are presented to confirm the superiority
of the proposed approach at low input signal-to-noise ratios.
Abstract: The intention of this paper is, to help the user of evolutionary algorithms to adapt them easier to their problem at hand. For a lot of problems in the technical field it is not necessary to reach an optimum solution, but to reach a good solution in time. In many cases the solution is undetermined or there doesn-t exist a method to determine the solution. For these cases an evolutionary algorithm can be useful. This paper intents to give the user rules of thumb with which it is easier to decide if the problem is suitable for an evolutionary algorithm and how to design them.