Abstract: Text categorization is the problem of classifying text
documents into a set of predefined classes. In this paper, we
investigated three approaches to build a meta-classifier in order to
increase the classification accuracy. The basic idea is to learn a metaclassifier
to optimally select the best component classifier for each
data point. The experimental results show that combining classifiers
can significantly improve the accuracy of classification and that our
meta-classification strategy gives better results than each individual
classifier. For 7083 Reuters text documents we obtained a
classification accuracies up to 92.04%.
Abstract: The issue of unintentional islanding in PV grid
interconnection still remains as a challenge in grid-connected
photovoltaic (PV) systems. This paper discusses the overview of
popularly used anti-islanding detection methods, practically applied
in PV grid-connected systems. Anti-islanding methods generally can
be classified into four major groups, which include passive methods,
active methods, hybrid methods and communication base methods.
Active methods have been the preferred detection technique over the
years due to very small non-detected zone (NDZ) in small scale
distribution generation. Passive method is comparatively simpler
than active method in terms of circuitry and operations. However, it
suffers from large NDZ that significantly reduces its performance.
Communication base methods inherit the advantages of active and
passive methods with reduced drawbacks. Hybrid method which
evolved from the combination of both active and passive methods
has been proven to achieve accurate anti-islanding detection by many
researchers. For each of the studied anti-islanding methods, the
operation analysis is described while the advantages and
disadvantages are compared and discussed. It is difficult to pinpoint a
generic method for a specific application, because most of the
methods discussed are governed by the nature of application and
system dependent elements. This study concludes that the setup and
operation cost is the vital factor for anti-islanding method selection in
order to achieve minimal compromising between cost and system
quality.
Abstract: This study reveals that anti-immigrant policies in
Europe result from a process of securitization, and that, within this
process, radical right parties have been formulating discourses and
approaches through a construction process by using some common
security themes. These security themes can be classified as national
security, economic security, cultural security and internal security.
The frequency with which radical right parties use these themes may
vary according to the specific historical, social and cultural
characteristics of a particular country.
Abstract: This paper presents a new steganography approach suitable for Arabic texts. It can be classified under steganography feature coding methods. The approach hides secret information bits within the letters benefiting from their inherited points. To note the specific letters holding secret bits, the scheme considers the two features, the existence of the points in the letters and the redundant Arabic extension character. We use the pointed letters with extension to hold the secret bit 'one' and the un-pointed letters with extension to hold 'zero'. This steganography technique is found attractive to other languages having similar texts to Arabic such as Persian and Urdu.
Abstract: The paper proposes an approach using genetic algorithm for computing the region based image similarity. The image is denoted using a set of segmented regions reflecting color and texture properties of an image. An image is associated with a family of image features corresponding to the regions. The resemblance of two images is then defined as the overall similarity between two families of image features, and quantified by a similarity measure, which integrates properties of all the regions in the images. A genetic algorithm is applied to decide the most plausible matching. The performance of the proposed method is illustrated using examples from an image database of general-purpose images, and is shown to produce good results.
Abstract: Reconfigurable optical add/drop multiplexers
(ROADMs) can be classified into three categories based on their
underlying switching technologies. Category I consists of a single
large optical switch; category II is composed of a number of small
optical switches aligned in parallel; and category III has a single
optical switch and only one wavelength being added/dropped. In this
paper, to evaluate the wavelength-routing capability of ROADMs of
category-II in dynamic optical networks,the dynamic traffic models
are designed based on Bernoulli, Poisson distributions for smooth
and regular types of traffic. Through Analytical and Simulation
results, the routing power of cat-II of ROADM networks for two
traffic models are determined.
Abstract: In this paper we designed and implemented a new
ensemble of classifiers based on a sequence of classifiers which were
specialized in regions of the training dataset where errors of its
trained homologous are concentrated. In order to separate this
regions, and to determine the aptitude of each classifier to properly
respond to a new case, it was used another set of classifiers built
hierarchically. We explored a selection based variant to combine the
base classifiers. We validated this model with different base
classifiers using 37 training datasets. It was carried out a statistical
comparison of these models with the well known Bagging and
Boosting, obtaining significantly superior results with the
hierarchical ensemble using Multilayer Perceptron as base classifier.
Therefore, we demonstrated the efficacy of the proposed ensemble,
as well as its applicability to general problems.
Abstract: This paper examines the problem of designing a robust H8 state-feedback controller for a class of nonlinear two-time scale systems with Markovian Jumps described by a Takagi-Sugeno (TS) fuzzy model. Based on a linear matrix inequality (LMI) approach, LMI-based sufficient conditions for the uncertain Markovian jump nonlinear two-time scale systems to have an H8 performance are derived. The proposed approach does not involve the separation of states into slow and fast ones and it can be applied not only to standard, but also to nonstandard nonlinear two-time scale systems. A numerical example is provided to illustrate the design developed in this paper.
Abstract: In this paper, we propose a robust scheme to work face alignment and recognition under various influences. For face representation, illumination influence and variable expressions are the important factors, especially the accuracy of facial localization and face recognition. In order to solve those of factors, we propose a robust approach to overcome these problems. This approach consists of two phases. One phase is preprocessed for face images by means of the proposed illumination normalization method. The location of facial features can fit more efficient and fast based on the proposed image blending. On the other hand, based on template matching, we further improve the active shape models (called as IASM) to locate the face shape more precise which can gain the recognized rate in the next phase. The other phase is to process feature extraction by using principal component analysis and face recognition by using support vector machine classifiers. The results show that this proposed method can obtain good facial localization and face recognition with varied illumination and local distortion.
Abstract: In this paper we address the problem of musical style
classification, which has a number of applications like indexing in
musical databases or automatic composition systems. Starting from
MIDI files of real-world improvisations, we extract the melody track
and cut it into overlapping segments of equal length. From these
fragments, some numerical features are extracted as descriptors of
style samples. We show that a standard Bayesian classifier can be
conveniently employed to build an effective musical style classifier,
once this set of features has been extracted from musical data.
Preliminary experimental results show the effectiveness of the
developed classifier that represents the first component of a musical
audio retrieval system
Abstract: Recently, information security has become a key issue
in information technology as the number of computer security
breaches are exposed to an increasing number of security threats. A
variety of intrusion detection systems (IDS) have been employed for
protecting computers and networks from malicious network-based or
host-based attacks by using traditional statistical methods to new data
mining approaches in last decades. However, today's commercially
available intrusion detection systems are signature-based that are not
capable of detecting unknown attacks. In this paper, we present a
new learning algorithm for anomaly based network intrusion
detection system using decision tree algorithm that distinguishes
attacks from normal behaviors and identifies different types of
intrusions. Experimental results on the KDD99 benchmark network
intrusion detection dataset demonstrate that the proposed learning
algorithm achieved 98% detection rate (DR) in comparison with
other existing methods.
Abstract: A fusion classifier composed of two modules, one made by a hidden Markov model (HMM) and the other by a support vector machine (SVM), is proposed to recognize faces with pose variations in open-set recognition settings. The HMM module captures the evolution of facial features across a subject-s face using the subject-s facial images only, without referencing to the faces of others. Because of the captured evolutionary process of facial features, the HMM module retains certain robustness against pose variations, yielding low false rejection rates (FRR) for recognizing faces across poses. This is, however, on the price of poor false acceptance rates (FAR) when recognizing other faces because it is built upon withinclass samples only. The SVM module in the proposed model is developed following a special design able to substantially diminish the FAR and further lower down the FRR. The proposed fusion classifier has been evaluated in performance using the CMU PIE database, and proven effective for open-set face recognition with pose variations. Experiments have also shown that it outperforms the face classifier made by HMM or SVM alone.
Abstract: A combination of image fusion and quad tree decomposition method is used for detecting the sunspot trajectories in each month and computation of the latitudes of these trajectories in each solar hemisphere. Daily solar images taken with SOHO satellite are fused for each month and the result of fused image is decomposed with Quad Tree decomposition method in order to classifying the sunspot trajectories and then to achieve the precise information about latitudes of sunspot trajectories. Also with fusion we deduce some physical remarkable conclusions about sun magnetic fields behavior. Using quad tree decomposition we give information about the region on sun surface and the space angle that tremendous flares and hot plasma gases permeate interplanetary space and attack to satellites and human technical systems. Here sunspot images in June, July and August 2001 are used for studying and give a method to compute the latitude of sunspot trajectories in each month with sunspot images.
Abstract: Advances in clinical medical imaging have brought about the routine production of vast numbers of medical images that need to be analyzed. As a result an enormous amount of computer vision research effort has been targeted at achieving automated medical image analysis. Computed Tomography (CT) is highly accurate for diagnosing liver tumors. This study aimed to evaluate the potential role of the wavelet and the neural network in the differential diagnosis of liver tumors in CT images. The tumors considered in this study are hepatocellular carcinoma, cholangio carcinoma, hemangeoma and hepatoadenoma. Each suspicious tumor region was automatically extracted from the CT abdominal images and the textural information obtained was used to train the Probabilistic Neural Network (PNN) to classify the tumors. Results obtained were evaluated with the help of radiologists. The system differentiates the tumor with relatively high accuracy and is therefore clinically useful.
Abstract: It is important to predict yield in semiconductor test process in order to increase yield. In this study, yield prediction means finding out defective die, wafer or lot effectively. Semiconductor test process consists of some test steps and each test includes various test items. In other world, test data has a big and complicated characteristic. It also is disproportionably distributed as the number of data belonging to FAIL class is extremely low. For yield prediction, general data mining techniques have a limitation without any data preprocessing due to eigen properties of test data. Therefore, this study proposes an under-sampling method using support vector machine (SVM) to eliminate an imbalanced characteristic. For evaluating a performance, randomly under-sampling method is compared with the proposed method using actual semiconductor test data. As a result, sampling method using SVM is effective in generating robust model for yield prediction.
Abstract: Nowadays, with the emerging of the new applications
like robot control in image processing, artificial vision for visual
servoing is a rapidly growing discipline and Human-machine
interaction plays a significant role for controlling the robot. This
paper presents a new algorithm based on spatio-temporal volumes for
visual servoing aims to control robots. In this algorithm, after
applying necessary pre-processing on video frames, a spatio-temporal
volume is constructed for each gesture and feature vector is extracted.
These volumes are then analyzed for matching in two consecutive
stages. For hand gesture recognition and classification we tested
different classifiers including k-Nearest neighbor, learning vector
quantization and back propagation neural networks. We tested the
proposed algorithm with the collected data set and results showed the
correct gesture recognition rate of 99.58 percent. We also tested the
algorithm with noisy images and algorithm showed the correct
recognition rate of 97.92 percent in noisy images.
Abstract: The statistical process control (SPC) is one of the most powerful tools developed to assist ineffective control of quality, involves collecting, organizing and interpreting data during production. This article aims to show how the use of CEP industries can control and continuously improve product quality through monitoring of production that can detect deviations of parameters representing the process by reducing the amount of off-specification products and thus the costs of production. This study aimed to conduct a technological forecasting in order to characterize the research being done related to the CEP. The survey was conducted in the databases Spacenet, WIPO and the National Institute of Industrial Property (INPI). Among the largest are the United States depositors and deposits via PCT, the classification section that was presented in greater abundance to F.
Abstract: Several works regarding facial recognition have dealt with methods which identify isolated characteristics of the face or with templates which encompass several regions of it. In this paper a new technique which approaches the problem holistically dispensing with the need to identify geometrical characteristics or regions of the face is introduced. The characterization of a face is achieved by randomly sampling selected attributes of the pixels of its image. From this information we construct a set of data, which correspond to the values of low frequencies, gradient, entropy and another several characteristics of pixel of the image. Generating a set of “p" variables. The multivariate data set with different polynomials minimizing the data fitness error in the minimax sense (L∞ - Norm) is approximated. With the use of a Genetic Algorithm (GA) it is able to circumvent the problem of dimensionality inherent to higher degree polynomial approximations. The GA yields the degree and values of a set of coefficients of the polynomials approximating of the image of a face. By finding a family of characteristic polynomials from several variables (pixel characteristics) for each face (say Fi ) in the data base through a resampling process the system in use, is trained. A face (say F ) is recognized by finding its characteristic polynomials and using an AdaBoost Classifier from F -s polynomials to each of the Fi -s polynomials. The winner is the polynomial family closer to F -s corresponding to target face in data base.
Abstract: Coronary artery bypass grafts (CABG) are widely
studied with respect to hemodynamic conditions which play
important role in presence of a restenosis. However, papers which
concern with constitutive modeling of CABG are lacking in the
literature. The purpose of this study is to find a constitutive model for
CABG tissue. A sample of the CABG obtained within an autopsy
underwent an inflation–extension test. Displacements were
recoredered by CCD cameras and subsequently evaluated by digital
image correlation. Pressure – radius and axial force – elongation
data were used to fit material model. The tissue was modeled as onelayered
composite reinforced by two families of helical fibers. The
material is assumed to be locally orthotropic, nonlinear,
incompressible and hyperelastic. Material parameters are estimated
for two strain energy functions (SEF). The first is classical
exponential. The second SEF is logarithmic which allows
interpretation by means of limiting (finite) strain extensibility.
Presented material parameters are estimated by optimization based
on radial and axial equilibrium equation in a thick-walled tube. Both
material models fit experimental data successfully. The exponential
model fits significantly better relationship between axial force and
axial strain than logarithmic one.
Abstract: In the recent works related with mixture discriminant
analysis (MDA), expectation and maximization (EM) algorithm is
used to estimate parameters of Gaussian mixtures. But, initial values
of EM algorithm affect the final parameters- estimates. Also, when
EM algorithm is applied two times, for the same data set, it can be
give different results for the estimate of parameters and this affect the
classification accuracy of MDA. Forthcoming this problem, we use
Self Organizing Mixture Network (SOMN) algorithm to estimate
parameters of Gaussians mixtures in MDA that SOMN is more robust
when random the initial values of the parameters are used [5]. We
show effectiveness of this method on popular simulated waveform
datasets and real glass data set.