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: Many agricultural and especially greenhouse
applications like plant inspection, data gathering, spraying and
selective harvesting could be performed by robots. In this paper
multiple nonholonomic robots are used in order to create a desired
formation scheme for screening solar energy in a greenhouse through
data gathering. The formation consists from a leader and a team
member equipped with appropriate sensors. Each robot is dedicated
to its mission in the greenhouse that is predefined by the
requirements of the application. The feasibility of the proposed
application includes experimental results with three unmanned
ground vehicles (UGV).
Abstract: More and more governments around the world are
introducing e-government as a means of reducing costs, improving
services, saving time and increasing effectiveness and efficiency in
the public sector Therefore e-government has been identified as one
of the top priorities for Saudi government and all its agencies.
However, the adoption of e-government is facing many challenges
and barriers such as technological, cultural, organizational, and social
issues which must be considered and treated carefully by any
government contemplating its adoption. This paper reports on a pilot
study amongst online (e-ready) citizens to identify the challenges and
barriers that affect the adoption of e-government services especially
from their perspective in Saudi society. Based on the analysis of data
collected from an online survey the researcher was able to identify
some of the important barriers and challenges from the e-ready
citizen perspective. As a result, this study has generated a list of
possible strategies to move towards successful adoption of egovernment
services in Saudi Arabia.
Abstract: In the area of Human Resource Management, the trend is towards online exchange of information about human resources. For example, online applications for employment become standard and job offerings are posted in many job portals. However, there are too many job portals to monitor all of them if someone is interested in a new job. We developed a prototype for integrating information of different job portals into one meta-search engine. First, existing job portals were investigated and XML schema documents were derived automated from these portals. Second, translation rules for transforming each schema to a central HR-XML-conform schema were determined. The HR-XML-schema is used to build a form for searching jobs. The data supplied by a user in this form is now translated into queries for the different job portals. Each result obtained by a job portal is sent to the meta-search engine that ranks the result of all received job offers according to user's preferences.
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: Using Turkish data, in this study it is investigated that
whether a firm’s ownership structure has an impact on its stock
prices after the crisis. A linear regression model is conducted on the
data of non-financial firms that are trading in Istanbul Stock
Exchange 100 Index (ISE 100) index. The findings show that, all
explanatory variables such as inside ownership, largest ownership,
concentrated ownership, foreign shareholders, family controlled and
dispersed ownership are not very important to explain stock prices
after the crisis. Family controlled firms and concentrated ownership
is positively related to stock price, dispersed ownership, largest
ownership, foreign shareholders, and inside ownership structures
have negative interaction between stock prices, but because of the p
value is not under the value of 0.05 this relation is not significant. In
addition, the analysis shows that, the shares of firms that have inside,
largest and dispersed ownership structure are outperform comparing
with the other firms. Furthermore, ownership concentrated firms
outperform to family controlled firms.
Abstract: Distant-talking voice-based HCI system suffers from
performance degradation due to mismatch between the acoustic
speech (runtime) and the acoustic model (training). Mismatch is
caused by the change in the power of the speech signal as observed at
the microphones. This change is greatly influenced by the change in
distance, affecting speech dynamics inside the room before reaching
the microphones. Moreover, as the speech signal is reflected, its
acoustical characteristic is also altered by the room properties. In
general, power mismatch due to distance is a complex problem. This
paper presents a novel approach in dealing with distance-induced
mismatch by intelligently sensing instantaneous voice power variation
and compensating model parameters. First, the distant-talking speech
signal is processed through microphone array processing, and the
corresponding distance information is extracted. Distance-sensitive
Gaussian Mixture Models (GMMs), pre-trained to capture both
speech power and room property are used to predict the optimal
distance of the speech source. Consequently, pre-computed statistic
priors corresponding to the optimal distance is selected to correct
the statistics of the generic model which was frozen during training.
Thus, model combinatorics are post-conditioned to match the power
of instantaneous speech acoustics at runtime. This results to an
improved likelihood in predicting the correct speech command at
farther distances. We experiment using real data recorded inside two
rooms. Experimental evaluation shows voice recognition performance
using our method is more robust to the change in distance compared
to the conventional approach. In our experiment, under the most
acoustically challenging environment (i.e., Room 2: 2.5 meters), our
method achieved 24.2% improvement in recognition performance
against the best-performing conventional method.
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: In this work, we present for the first time in our perception an efficient digital watermarking scheme for mpeg audio layer 3 files that operates directly in the compressed data domain, while manipulating the time and subband/channel domain. In addition, it does not need the original signal to detect the watermark. Our scheme was implemented taking special care for the efficient usage of the two limited resources of computer systems: time and space. It offers to the industrial user the capability of watermark embedding and detection in time immediately comparable to the real music time of the original audio file that depends on the mpeg compression, while the end user/audience does not face any artifacts or delays hearing the watermarked audio file. Furthermore, it overcomes the disadvantage of algorithms operating in the PCMData domain to be vulnerable to compression/recompression attacks, as it places the watermark in the scale factors domain and not in the digitized sound audio data. The strength of our scheme, that allows it to be used with success in both authentication and copyright protection, relies on the fact that it gives to the users the enhanced capability their ownership of the audio file not to be accomplished simply by detecting the bit pattern that comprises the watermark itself, but by showing that the legal owner knows a hard to compute property of the watermark.
Abstract: Multi-dimensional principal component analysis
(PCA) is the extension of the PCA, which is used widely as the
dimensionality reduction technique in multivariate data analysis, to
handle multi-dimensional data. To calculate the PCA the singular
value decomposition (SVD) is commonly employed by the reason of
its numerical stability. The multi-dimensional PCA can be calculated
by using the higher-order SVD (HOSVD), which is proposed by
Lathauwer et al., similarly with the case of ordinary PCA. In this
paper, we apply the multi-dimensional PCA to the multi-dimensional
medical data including the functional independence measure (FIM)
score, and describe the results of experimental analysis.
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: One of the essential requirements of a realistic
surgical simulator is to reproduce haptic sensations due to the
interactions in the virtual environment. However, the interaction need
to be performed in real-time, since a delay between the user action
and the system reaction reduces the immersion sensation. In this
paper, a prototype of a coronary stent implant simulator is present;
this system allows real-time interactions with an artery by means of a
specific haptic device. To improve the realism of the simulation, the
building of the virtual environment is based on real patients- images
and a Web Portal is used to search in the geographically remote
medical centres a virtual environment with specific features in terms
of pathology or anatomy. The functional architecture of the system
defines several Medical Centres in which virtual environments built
from the real patients- images and related metadata with specific
features in terms of pathology or anatomy are stored. The searched
data are downloaded from the Medical Centre to the Training Centre
provided with a specific haptic device and with the software
necessary both to manage the interaction in the virtual environment.
After the integration of the virtual environment in the simulation
system it is possible to perform training on the specific surgical
procedure.
Abstract: Eukaryotic protein-coding genes are interrupted by spliceosomal introns, which are removed from the RNA transcripts before translation into a protein. The exon-intron structures of different eukaryotic species are quite different from each other, and the evolution of such structures raises many questions. We try to address some of these questions using statistical analysis of whole genomes. We go through all the protein-coding genes in a genome and study correlations between the net length of all the exons in a gene, the number of the exons, and the average length of an exon. We also take average values of these features for each chromosome and study correlations between those averages on the chromosomal level. Our data show universal features of exon-intron structures common to animals, plants, and protists (specifically, Arabidopsis thaliana, Caenorhabditis elegans, Drosophila melanogaster, Cryptococcus neoformans, Homo sapiens, Mus musculus, Oryza sativa, and Plasmodium falciparum). We have verified linear correlation between the number of exons in a gene and the length of a protein coded by the gene, while the protein length increases in proportion to the number of exons. On the other hand, the average length of an exon always decreases with the number of exons. Finally, chromosome clustering based on average chromosome properties and parameters of linear regression between the number of exons in a gene and the net length of those exons demonstrates that these average chromosome properties are genome-specific features.
Abstract: Webcam systems now function as the new privileged
vantage points from which to view the city. This transformation of
CCTV technology from surveillance to promotional tool is significant
because its'scopic regime' presents, back to the public, a new virtual
'site' that sits alongside its real-time counterpart. Significantly,
thisraw 'image' data can, in fact,be co-optedand processed so as to
disrupt their original purpose. This paper will demonstrate this
disruptive capacity through an architectural project. It will reveal how
the adaption the webcam image offers a technical springboard by
which to initiate alternate urban form making decisions and subvert
the disciplinary reliance on the 'flat' orthographic plan. In so doing,
the paper will show how this 'digital material' exceeds the imagistic
function of the image; shiftingit from being a vehicle of signification
to a site of affect.
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: Main Memory Database systems (MMDB) store their
data in main physical memory and provide very high-speed access.
Conventional database systems are optimized for the particular
characteristics of disk storage mechanisms. Memory resident
systems, on the other hand, use different optimizations to structure
and organize data, as well as to make it reliable.
This paper provides a brief overview on MMDBs and one of the
memory resident systems named FastDB and compares the
processing time of this system with a typical disc resident database
based on the results of the implementation of TPC benchmarks
environment on both.
Abstract: Dust storms are one of the most costly and destructive
events in many desert regions. They can cause massive damages both
in natural environments and human lives. This paper is aimed at
presenting a preliminary study on dust storms, as a major natural
hazard in arid and semi-arid regions. As a case study, dust storm
events occurred in Zabol city located in Sistan Region of Iran was
analyzed to diagnose and predict dust storms. The identification and
prediction of dust storm events could have significant impacts on
damages reduction. Present models for this purpose are complicated
and not appropriate for many areas with poor-data environments. The
present study explores Gamma test for identifying inputs of ANNs
model, for dust storm prediction. Results indicate that more attempts
must be carried out concerning dust storms identification and
segregate between various dust storm types.
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.
Abstract: This paper proposes a new method for analyzing textual data. The method deals with items of textual data, where each item is described based on various viewpoints. The method acquires 2- class classification models of the viewpoints by applying an inductive learning method to items with multiple viewpoints. The method infers whether the viewpoints are assigned to the new items or not by using the models. The method extracts expressions from the new items classified into the viewpoints and extracts characteristic expressions corresponding to the viewpoints by comparing the frequency of expressions among the viewpoints. This paper also applies the method to questionnaire data given by guests at a hotel and verifies its effect through numerical experiments.