Abstract: In this paper, we present an experimental testing for
a new algorithm that determines an optimal controller-s coefficients
for output variance reduction related to Linear Time Invariant (LTI)
Systems. The algorithm features simplicity in calculation, generalization
to minimal and non-minimal phase systems, and could be
configured to achieve reference tracking as well as variance reduction
after compromising with the output variance. An experiment of DCmotor
velocity control demonstrates the application of this new
algorithm in designing the controller. The results show that the
controller achieves minimum variance and reference tracking for a
preset velocity reference relying on an identified model of the motor.
Abstract: Wavelet transform or wavelet analysis is a recently
developed mathematical tool in applied mathematics. In numerical
analysis, wavelets also serve as a Galerkin basis to solve partial
differential equations. Haar transform or Haar wavelet transform has
been used as a simplest and earliest example for orthonormal wavelet
transform. Since its popularity in wavelet analysis, there are several
definitions and various generalizations or algorithms for calculating
Haar transform. Fast Haar transform, FHT, is one of the algorithms
which can reduce the tedious calculation works in Haar transform. In
this paper, we present a modified fast and exact algorithm for FHT,
namely Modified Fast Haar Transform, MFHT. The algorithm or
procedure proposed allows certain calculation in the process
decomposition be ignored without affecting the results.
Abstract: Since 1984 many schemes have been proposed for
digital signature protocol, among them those that based on discrete
log and factorizations. However a new identification scheme based
on iterated function (IFS) systems are proposed and proved to be
more efficient. In this study the proposed identification scheme is
transformed into a digital signature scheme by using a one way hash
function. It is a generalization of the GQ signature schemes. The
attractor of the IFS is used to obtain public key from a private one,
and in the encryption and decryption of a hash function. Our aim is
to provide techniques and tools which may be useful towards
developing cryptographic protocols. Comparisons between the
proposed scheme and fractal digital signature scheme based on RSA
setting, as well as, with the conventional Guillou-Quisquater
signature, and RSA signature schemes is performed to prove that, the
proposed scheme is efficient and with high performance.
Abstract: Identity verification of authentic persons by their multiview faces is a real valued problem in machine vision. Multiview faces are having difficulties due to non-linear representation in the feature space. This paper illustrates the usability of the generalization of LDA in the form of canonical covariate for face recognition to multiview faces. In the proposed work, the Gabor filter bank is used to extract facial features that characterized by spatial frequency, spatial locality and orientation. Gabor face representation captures substantial amount of variations of the face instances that often occurs due to illumination, pose and facial expression changes. Convolution of Gabor filter bank to face images of rotated profile views produce Gabor faces with high dimensional features vectors. Canonical covariate is then used to Gabor faces to reduce the high dimensional feature spaces into low dimensional subspaces. Finally, support vector machines are trained with canonical sub-spaces that contain reduced set of features and perform recognition task. The proposed system is evaluated with UMIST face database. The experiment results demonstrate the efficiency and robustness of the proposed system with high recognition rates.
Abstract: We consider linear regression models where both input data (the values of independent variables) and output data (the observations of the dependent variable) are interval-censored. We introduce a possibilistic generalization of the least squares estimator, so called OLS-set for the interval model. This set captures the impact of the loss of information on the OLS estimator caused by interval censoring and provides a tool for quantification of this effect. We study complexity-theoretic properties of the OLS-set. We also deal with restricted versions of the general interval linear regression model, in particular the crisp input – interval output model. We give an argument that natural descriptions of the OLS-set in the crisp input – interval output cannot be computed in polynomial time. Then we derive easily computable approximations for the OLS-set which can be used instead of the exact description. We illustrate the approach by an example.
Abstract: Data mining is an extraordinarily demanding field referring to extraction of implicit knowledge and relationships, which are not explicitly stored in databases. A wide variety of methods of data mining have been introduced (classification, characterization, generalization...). Each one of these methods includes more than algorithm. A system of data mining implies different user categories,, which mean that the user-s behavior must be a component of the system. The problem at this level is to know which algorithm of which method to employ for an exploratory end, which one for a decisional end, and how can they collaborate and communicate. Agent paradigm presents a new way of conception and realizing of data mining system. The purpose is to combine different algorithms of data mining to prepare elements for decision-makers, benefiting from the possibilities offered by the multi-agent systems. In this paper the agent framework for data mining is introduced, and its overall architecture and functionality are presented. The validation is made on spatial data. Principal results will be presented.
Abstract: The group mutual exclusion (GME) problem is an
interesting generalization of the mutual exclusion problem. Several
solutions of the GME problem have been proposed for message
passing distributed systems. However, none of these solutions is
suitable for real time distributed systems. In this paper, we propose a
token-based distributed algorithms for the GME problem in soft real
time distributed systems. The algorithm uses the concepts of priority
queue, dynamic request set and the process state. The algorithm uses
first come first serve approach in selecting the next session type
between the same priority levels and satisfies the concurrent
occupancy property. The algorithm allows all n processors to be
inside their CS provided they request for the same session. The
performance analysis and correctness proof of the algorithm has also
been included in the paper.
Abstract: The transient analysis of a queuing system with fixed-size batch Poisson arrivals and a single server with exponential service times is presented. The focus of the paper is on the use of the functions that arise in the analysis of the transient behaviour of the queuing system. These functions are shown to be a generalization of the modified Bessel functions of the first kind, with the batch size B as the generalizing parameter. Results for the case of single-packet arrivals are obtained first. The similarities between the two families of functions are then used to obtain results for the general case of batch arrival queue with a batch size larger than one.
Abstract: In this work, a Modified Functional Link Artificial
Neural Network (M-FLANN) is proposed which is simpler than a
Multilayer Perceptron (MLP) and improves upon the universal
approximation capability of Functional Link Artificial Neural
Network (FLANN). MLP and its variants: Direct Linear Feedthrough
Artificial Neural Network (DLFANN), FLANN and
M-FLANN have been implemented to model a simulated Water Bath
System and a Continually Stirred Tank Heater (CSTH). Their
convergence speed and generalization ability have been compared.
The networks have been tested for their interpolation and
extrapolation capability using noise-free and noisy data. The results
show that M-FLANN which is computationally cheap, performs
better and has greater generalization ability than other networks
considered in the work.
Abstract: SoftBoost is a recently presented boosting algorithm,
which trades off the size of achieved classification margin and
generalization performance. This paper presents a performance
evaluation of SoftBoost algorithm on the generic object recognition
problem. An appearance-based generic object recognition
model is used. The evaluation experiments are performed using
a difficult object recognition benchmark. An assessment with respect
to different degrees of label noise as well as a comparison to
the well known AdaBoost algorithm is performed. The obtained
results reveal that SoftBoost is encouraged to be used in cases
when the training data is known to have a high degree of noise.
Otherwise, using Adaboost can achieve better performance.
Abstract: The group mutual exclusion (GME) problem is an
interesting generalization of the mutual exclusion problem. In the
group mutual exclusion, multiple processes can enter a critical
section simultaneously if they belong to the same group. In the
extended group mutual exclusion, each process is a member of
multiple groups at the same time. As a result, after the process by
selecting a group enter critical section, other processes can select the
same group with its belonging group and can enter critical section at
the moment, so that it avoids their unnecessary blocking. This paper
presents a quorum-based distributed algorithm for the extended
group mutual exclusion problem. The message complexity of our
algorithm is O(4Q ) in the best case and O(5Q) in the worst case,
where Q is a quorum size.
Abstract: The neural network's performance can be measured by efficiency and accuracy. The major disadvantages of neural network approach are that the generalization capability of neural networks is often significantly low, and it may take a very long time to tune the weights in the net to generate an accurate model for a highly complex and nonlinear systems. This paper presents a novel Neuro-fuzzy architecture based on Extended Kalman filter. To test the performance and applicability of the proposed neuro-fuzzy model, simulation study of nonlinear complex dynamic system is carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction of financial time series. A benchmark case studie is used to demonstrate that the proposed model is a superior neuro-fuzzy modeling technique.
Abstract: In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.
Abstract: In conventional reliability assessment, the reliability data of system components are treated as crisp values. The collected data have some uncertainties due to errors by human beings/machines or any other sources. These uncertainty factors will limit the understanding of system component failure due to the reason of incomplete data. In these situations, we need to generalize classical methods to fuzzy environment for studying and analyzing the systems of interest. Fuzzy set theory has been proposed to handle such vagueness by generalizing the notion of membership in a set. Essentially, in a Fuzzy Set (FS) each element is associated with a point-value selected from the unit interval [0, 1], which is termed as the grade of membership in the set. A Vague Set (VS), as well as an Intuitionistic Fuzzy Set (IFS), is a further generalization of an FS. Instead of using point-based membership as in FS, interval-based membership is used in VS. The interval-based membership in VS is more expressive in capturing vagueness of data. In the present paper, vague set theory coupled with conventional Lambda-Tau method is presented for reliability analysis of repairable systems. The methodology uses Petri nets (PN) to model the system instead of fault tree because it allows efficient simultaneous generation of minimal cuts and path sets. The presented method is illustrated with the press unit of the paper mill.
Abstract: In this paper, the two-dimensional stagger grid
interface pressure (SGIP) model has been generalized and presented
into three-dimensional form. For this purpose, various models of
surface tension force for interfacial flows have been investigated and
compared with each other. The VOF method has been used for
tracking the interface. To show the ability of the SGIP model for
three-dimensional flows in comparison with other models, pressure
contours, maximum spurious velocities, norm spurious flow
velocities and pressure jump error for motionless drop of liquid and
bubble of gas are calculated using different models. It has been
pointed out that SGIP model in comparison with the CSF, CSS and
PCIL models produces the least maximum and norm spurious
velocities. Additionally, the new model produces more accurate
results in calculating the pressure jumps across the interface for
motionless drop of liquid and bubble of gas which is generated in
surface tension force.
Abstract: The paper shows that in the analysis of a queuing system with fixed-size batch arrivals, there emerges a set of polynomials which are a generalization of Chebyshev polynomials of the second kind. The paper uses these polynomials in assessing the transient behaviour of the overflow (equivalently call blocking) probability in the system. A key figure to note is the proportion of the overflow (or blocking) probability resident in the transient component, which is shown in the results to be more significant at the beginning of the transient and naturally decays to zero in the limit of large t. The results also show that the significance of transients is more pronounced in cases of lighter loads, but lasts longer for heavier loads.
Abstract: We introduce the notion of strongly ω -Gorenstein modules, where ω is a faithfully balanced self-orthogonal module. This gives a common generalization of both Gorenstein projective (injective) modules and ω-Gorenstein modules. We investigate some characterizations of strongly ω -Gorenstein modules. Consequently, some properties under change of rings are obtained.
Abstract: This study investigates the possibility providing gully
erosion map by the supervised classification of satellite images
(ETM+) in two mountainous and plain land types. These land types
were the part of Varamin plain, Tehran province, and Roodbar subbasin,
Guilan province, as plain and mountain land types,
respectively. The position of 652 and 124 ground control points were
recorded by GPS respectively in mountain and plain land types. Soil
gully erosion, land uses or plant covers were investigated in these
points. Regarding ground control points and auxiliary points, training
points of gully erosion and other surface features were introduced to
software (Ilwis 3.3 Academic). The supervised classified map of
gully erosion was prepared by maximum likelihood method and then,
overall accuracy of this map was computed. Results showed that the
possibility supervised classification of gully erosion isn-t possible,
although it need more studies for results generalization to other
mountainous regions. Also, with increasing land uses and other
surface features in plain physiography, it decreases the classification
of accuracy.
Abstract: Load forecasting has become in recent years one of the major areas of research in electrical engineering. Most traditional forecasting models and artificial intelligence neural network techniques have been tried out in this task. Artificial neural networks (ANN) have lately received much attention, and a great number of papers have reported successful experiments and practical tests. This article presents the development of an ANN-based short-term load forecasting model with improved generalization technique for the Regional Power Control Center of Saudi Electricity Company, Western Operation Area (SEC-WOA). The proposed ANN is trained with weather-related data and historical electric load-related data using the data from the calendar years 2001, 2002, 2003, and 2004 for training. The model tested for one week at five different seasons, typically, winter, spring, summer, Ramadan and fall seasons, and the mean absolute average error for one hour-ahead load forecasting found 1.12%.
Abstract: The problem of estimating time-varying regression is
inevitably concerned with the necessity to choose the appropriate
level of model volatility - ranging from the full stationarity of instant
regression models to their absolute independence of each other. In the
stationary case the number of regression coefficients to be estimated
equals that of regressors, whereas the absence of any smoothness
assumptions augments the dimension of the unknown vector by the
factor of the time-series length. The Akaike Information Criterion
is a commonly adopted means of adjusting a model to the given
data set within a succession of nested parametric model classes,
but its crucial restriction is that the classes are rigidly defined by
the growing integer-valued dimension of the unknown vector. To
make the Kullback information maximization principle underlying the
classical AIC applicable to the problem of time-varying regression
estimation, we extend it onto a wider class of data models in which
the dimension of the parameter is fixed, but the freedom of its values
is softly constrained by a family of continuously nested a priori
probability distributions.