Abstract: The competitive learning is an adaptive process in
which the neurons in a neural network gradually become sensitive to
different input pattern clusters. The basic idea behind the Kohonen-s
Self-Organizing Feature Maps (SOFM) is competitive learning.
SOFM can generate mappings from high-dimensional signal spaces
to lower dimensional topological structures. The main features of this
kind of mappings are topology preserving, feature mappings and
probability distribution approximation of input patterns. To overcome
some limitations of SOFM, e.g., a fixed number of neural units and a
topology of fixed dimensionality, Growing Self-Organizing Neural
Network (GSONN) can be used. GSONN can change its topological
structure during learning. It grows by learning and shrinks by
forgetting. To speed up the training and convergence, a new variant
of GSONN, twin growing cell structures (TGCS) is presented here.
This paper first gives an introduction to competitive learning, SOFM
and its variants. Then, we discuss some GSONN with fixed
dimensionality, which include growing cell structures, its variants
and the author-s model: TGCS. It is ended with some testing results
comparison and conclusions.
Abstract: The purpose of this study is to analyze Green IT industry in major developed countries and to suggest overall directions for IT-Energy convergence industry. Recently, IT industry is pointed out as a problem such as environmental pollution, energy exhaustion, and high energy consumption. Therefore, Green IT gets focused which concerns as solution of these problems. However, since it is a beginning stage of this convergence area, there are only a few studies of IT-Energy convergence industry. According to this, this study examined the major developed countries in terms of institution arrangements, resources, markets and companies based on Van de Ven(1999)'s social system framework that shows relationship among key components of industrial infrastructure. Subsequently, the direction of the future study of convergence on IT and Energy industry is proposed.
Abstract: In this paper we investigated a number of the Internet
congestion control algorithms that has been developed in the last few
years. It was obviously found that many of these algorithms were
designed to deal with the Internet traffic merely as a train of
consequent packets. Other few algorithms were specifically tailored
to handle the Internet congestion caused by running media traffic that
represents audiovisual content. This later set of algorithms is
considered to be aware of the nature of this media content. In this
context we briefly explained a number of congestion control
algorithms and hence categorized them into the two following
categories: i) Media congestion control algorithms. ii) Common
congestion control algorithms. We hereby recommend the usage of
the media congestion control algorithms for the reason of being
media content-aware rather than the other common type of
algorithms that blindly manipulates such traffic. We showed that the
spread of such media content-aware algorithms over Internet will
lead to better congestion control status in the coming years. This is
due to the observed emergence of the era of digital convergence
where the media traffic type will form the majority of the Internet
traffic.
Abstract: A proof of convergence of a new continuation algorithm for computing the Analytic SVD for a large sparse parameter– dependent matrix is given. The algorithm itself was developed and numerically tested in [5].
Abstract: In this paper a technique for increasing the
convergence rate of fractionally spaced channel equalizer is
proposed. Instead of symbol-spaced updating of the equalizer filter, a
mechanism has been devised to update the filter at a higher rate. This
ensures convergence of the equalizer filter at a higher rate and
therefore less time-consuming. The proposed technique has been
simulated and tested for two-ray modeled channels with various
delay spreads. These channels include minimum-phase and nonminimum-
phase channels. Simulation results suggest that that
proposed technique outperforms the conventional technique of
symbol-spaced updating of equalizer filter.
Abstract: Throughput is an important measure of performance of production system. Analyzing and modeling of production throughput is complex in today-s dynamic production systems due to uncertainties of production system. The main reasons are that uncertainties are materialized when the production line faces changes in setup time, machinery break down, lead time of manufacturing, and scraps. Besides, demand changes are fluctuating from time to time for each product type. These uncertainties affect the production performance. This paper proposes Bayesian inference for throughput modeling under five production uncertainties. Bayesian model utilized prior distributions related to previous information about the uncertainties where likelihood distributions are associated to the observed data. Gibbs sampling algorithm as the robust procedure of Monte Carlo Markov chain was employed for sampling unknown parameters and estimating the posterior mean of uncertainties. The Bayesian model was validated with respect to convergence and efficiency of its outputs. The results presented that the proposed Bayesian models were capable to predict the production throughput with accuracy of 98.3%.
Abstract: In this paper a modification on Levenberg-Marquardt algorithm for MLP neural network learning is proposed. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. An example is given to show usefulness of this method. Finally a simulation verifies the results of proposed method.
Abstract: In recent years, IT convergence technology has been developed to get creative solution by combining robotics or sports science technology. Object detection and recognition have mainly applied to sports science field that has processed by recognizing face and by tracking human body. But object detection and recognition using vision sensor is challenge task in real world because of illumination. In this paper, object detection and recognition using vision sensor applied to sports simulator has been introduced. Face recognition has been processed to identify user and to update automatically a person athletic recording. Human body has tracked to offer a most accurate way of riding horse simulator. Combined image processing has been processed to reduce illumination adverse affect because illumination has caused low performance in detection and recognition in real world application filed. Face has recognized using standard face graph and human body has tracked using pose model, which has composed of feature nodes generated diverse face and pose images. Face recognition using Gabor wavelet and pose recognition using pose graph is robust to real application. We have simulated using ETRI database, which has constructed on horse riding simulator.
Abstract: Fractional delay FIR filters design method based on
the differential evolution algorithm is presented. Differential evolution
is an evolutionary algorithm for solving a global optimization problems in the continuous search space. In the proposed approach,
an evolutionary algorithm is used to determine the coefficients of
a fractional delay FIR filter based on the Farrow structure. Basic
differential evolution is enhanced with a restricted mating technique,
which improves the algorithm performance in terms of convergence
speed and obtained solution. Evolutionary optimization is carried out by minimizing an objective function which is based on the amplitude
response and phase delay errors. Experimental results show that the proposed algorithm leads to a reduction in the amplitude response and phase delay errors relative to those achieved with the Least-Squares
method.
Abstract: In this work we adopt a combination of Laplace
transform and the decomposition method to find numerical solutions
of a system of multi-pantograph equations. The procedure leads to a
rapid convergence of the series to the exact solution after computing a
few terms. The effectiveness of the method is demonstrated in some
examples by obtaining the exact solution and in others by computing
the absolute error which decreases as the number of terms of the series
increases.
Abstract: The Wavelet-Galerkin finite element method for
solving the one-dimensional heat equation is presented in this work.
Two types of basis functions which are the Lagrange and multi-level
wavelet bases are employed to derive the full form of matrix system.
We consider both linear and quadratic bases in the Galerkin method.
Time derivative is approximated by polynomial time basis that
provides easily extend the order of approximation in time space. Our
numerical results show that the rate of convergences for the linear
Lagrange and the linear wavelet bases are the same and in order 2
while the rate of convergences for the quadratic Lagrange and the
quadratic wavelet bases are approximately in order 4. It also reveals
that the wavelet basis provides an easy treatment to improve
numerical resolutions that can be done by increasing just its desired
levels in the multilevel construction process.
Abstract: This paper reports work done to improve the modeling of complex processes when only small experimental data sets are available. Neural networks are used to capture the nonlinear underlying phenomena contained in the data set and to partly eliminate the burden of having to specify completely the structure of the model. Two different types of neural networks were used for the application of pulping problem. A three layer feed forward neural networks, using the Preconditioned Conjugate Gradient (PCG) methods were used in this investigation. Preconditioning is a method to improve convergence by lowering the condition number and increasing the eigenvalues clustering. The idea is to solve the modified odified problem M-1 Ax= M-1b where M is a positive-definite preconditioner that is closely related to A. We mainly focused on Preconditioned Conjugate Gradient- based training methods which originated from optimization theory, namely Preconditioned Conjugate Gradient with Fletcher-Reeves Update (PCGF), Preconditioned Conjugate Gradient with Polak-Ribiere Update (PCGP) and Preconditioned Conjugate Gradient with Powell-Beale Restarts (PCGB). The behavior of the PCG methods in the simulations proved to be robust against phenomenon such as oscillations due to large step size.
Abstract: Researchers have been applying tional intelligence (AI/CI) methods to computer games. In this research field, further researchesare required to compare AI/CI
methods with respect to each game application. In th
our experimental result on the comparison of three evolutionary algorithms – evolution strategy, genetic algorithm, and their hybrid
applied to evolving controller agents for the CIG 2007 Simulated Car Racing competition. Our experimental result shows that, premature
convergence of solutions was observed in the case of ES, and GA outperformed ES in the last half of generations. Besides, a hybrid
which uses GA first and ES next evolved the best solution among the whole solutions being generated. This result shows the ability of GA in
globally searching promising areas in the early stage and the ability of ES in locally searching the focused area (fine-tuning solutions).
Abstract: Image Compression using Artificial Neural Networks
is a topic where research is being carried out in various directions
towards achieving a generalized and economical network.
Feedforward Networks using Back propagation Algorithm adopting
the method of steepest descent for error minimization is popular and
widely adopted and is directly applied to image compression.
Various research works are directed towards achieving quick
convergence of the network without loss of quality of the restored
image. In general the images used for compression are of different
types like dark image, high intensity image etc. When these images
are compressed using Back-propagation Network, it takes longer
time to converge. The reason for this is, the given image may
contain a number of distinct gray levels with narrow difference with
their neighborhood pixels. If the gray levels of the pixels in an image
and their neighbors are mapped in such a way that the difference in
the gray levels of the neighbors with the pixel is minimum, then
compression ratio as well as the convergence of the network can be
improved. To achieve this, a Cumulative distribution function is
estimated for the image and it is used to map the image pixels. When
the mapped image pixels are used, the Back-propagation Neural
Network yields high compression ratio as well as it converges
quickly.
Abstract: A family of improved secant-like method is proposed in this paper. Further, the analysis of the convergence shows that this method has super-linear convergence. Efficiency are demonstrated by numerical experiments when the choice of α is correct.
Abstract: Iterative learning control aims to achieve zero tracking
error of a specific command. This is accomplished by iteratively
adjusting the command given to a feedback control system, based on
the tracking error observed in the previous iteration. One would like
the iterations to converge to zero tracking error in spite of any error
present in the model used to design the learning law. First, this need
for stability robustness is discussed, and then the need for robustness
of the property that the transients are well behaved. Methods of
producing the needed robustness to parameter variations and to
singular perturbations are presented. Then a method involving
reverse time runs is given that lets the world behavior produce the
ILC gains in such a way as to eliminate the need for a mathematical
model. Since the real world is producing the gains, there is no issue
of model error. Provided the world behaves linearly, the approach
gives an ILC law with both stability robustness and good transient
robustness, without the need to generate a model.
Abstract: In this paper, a new descent-projection method with a
new search direction for monotone structured variational inequalities
is proposed. The method is simple, which needs only projections
and some function evaluations, so its computational load is very tiny.
Under mild conditions on the problem-s data, the method is proved to
converges globally. Some preliminary computational results are also
reported to illustrate the efficiency of the method.
Abstract: In this paper, we present a preconditioned AOR-type iterative method for solving the linear systems Ax = b, where A is a Z-matrix. And give some comparison theorems to show that the rate of convergence of the preconditioned AOR-type iterative method is faster than the rate of convergence of the AOR-type iterative method.
Abstract: The purpose of study is to demonstrate how the characteristics of technology and the process required for development of technology affect technology transfer from public organisations to industry on the technology level. In addition, using the advantage of the analytic level and the novel means of measuring technology convergence, we examine the characteristics of converging technologies as compared to non-converging technologies in technology transfer process. In sum, our study finds that a technology from the public sector is likely to be transferred when its readiness level is closer to generation of profit, when its stage of life cycle is early and when its economic values is high. Our findings also show that converging technologies are less likely to be transferred.
Abstract: In this paper a hybrid technique of Genetic Algorithm
and Simulated Annealing (HGASA) is applied for Fractal Image
Compression (FIC). With the help of this hybrid evolutionary
algorithm effort is made to reduce the search complexity of matching
between range block and domain block. The concept of Simulated
Annealing (SA) is incorporated into Genetic Algorithm (GA) in order
to avoid pre-mature convergence of the strings. One of the image
compression techniques in the spatial domain is Fractal Image
Compression but the main drawback of FIC is that it involves more
computational time due to global search. In order to improve the
computational time along with acceptable quality of the decoded
image, HGASA technique has been proposed. Experimental results
show that the proposed HGASA is a better method than GA in terms
of PSNR for Fractal image Compression.