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: The inherent iterative nature of product design and development poses significant challenge to reduce the product design and development time (PD). In order to shorten the time to market, organizations have adopted concurrent development where multiple specialized tasks and design activities are carried out in parallel. Iterative nature of work coupled with the overlap of activities can result in unpredictable time to completion and significant rework. Many of the products have missed the time to market window due to unanticipated or rather unplanned iteration and rework. The iterative and often overlapped processes introduce greater amounts of ambiguity in design and development, where the traditional methods and tools of project management provide less value. In this context, identifying critical metrics to understand the iteration probability is an open research area where significant contribution can be made given that iteration has been the key driver of cost and schedule risk in PD projects. Two important questions that the proposed study attempts to address are: Can we predict and identify the number of iterations in a product development flow? Can we provide managerial insights for a better control over iteration? The proposal introduces the concept of decision points and using this concept intends to develop metrics that can provide managerial insights into iteration predictability. By characterizing the product development flow as a network of decision points, the proposed research intends to delve further into iteration probability and attempts to provide more clarity.
Abstract: Over half of the total electricity consumption is used in buildings. Air-conditioning and electric lighting are the two main resources of electricity consumption in high rise buildings. One way to reduce electricity consumption would be to limit heat gain into buildings, therefore reduce the demand for air-conditioning during hot summer months especially in hot regions. On the other hand natural daylight can be used to reduce the use of electricity for artificial lighting. In this paper effective factors on minimizing heat gain and achieving required day light were reviewed .As daylight always accompanied by solar heat gain. Also interactions between heat gain and daylight were discussed through previous studies and equations which are related to heat gain and day lighting especially in high rise buildings. As a result importance of building-s form and its component on energy consumption in buildings were clarified.
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: Land degradation is of concern in many countries. People more and more must address the problems associated with the degradation of soil properties due to man. Increasingly, organic soil amendments, such as compost are being examined for their potential use in soil restoration and for preventing soil erosion. In the Czech Republic, compost is the most used to improve soil structure and increase the content of soil organic matter. Land reclamation / restoration is one of the ways to evaluate industrially produced compost because Czech farmers are not willing to use compost as organic fertilizer. The most common use of reclamation substrates in the Czech Republic is for the rehabilitation of landfills and contaminated sites.
This paper deals with the influence of reclamation substrates (RS) with different proportions of compost and sand on selected soil properties–chemical characteristics, nitrogen bioavailability, leaching of mineral nitrogen, respiration activity and plant biomass production. Chemical properties vary proportionally with addition of compost and sand to the control variant (topsoil). The highest differences between the variants were recorded in leaching of mineral nitrogen (varies from 1.36mg dm-3 in C to 9.09mg dm-3). Addition of compost to soil improves conditions for plant growth in comparison with soil alone. However, too high addition of compost may have adverse effects on plant growth. In addition, high proportion of compost increases leaching of mineral N. Therefore, mixture of 70% of soil with 10% of compost and 20% of sand may be recommended as optimal composition of RS.
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: The aim of this study was to screen for
microorganism that able to utilize 3-N-trimethylamino-1-propanol
(homocholine) as a sole source of carbon and nitrogen. The aerobic
degradation of homocholine has been found by a gram-positive
Rhodococcus sp. bacterium isolated from soil. The isolate was
identified as Rhodococcus sp. strain A4 based on the phenotypic
features, physiologic and biochemical characteristics, and
phylogenetic analysis. The cells of the isolated strain grown on both
basal-TMAP and nutrient agar medium displayed elementary
branching mycelia fragmented into irregular rod and coccoid
elements. Comparative 16S rDNA sequencing studies indicated that
the strain A4 falls into the Rhodococcus erythropolis subclade and
forms a monophyletic group with the type-strains of R. opacus, and
R. wratislaviensis. Metabolites analysis by capillary electrophoresis,
fast atom bombardment-mass spectrometry, and gas
chromatography- mass spectrometry, showed trimethylamine (TMA)
as the major metabolite beside β-alanine betaine and
trimethylaminopropionaldehyde. Therefore, the possible degradation
pathway of trimethylamino propanol in the isolated strain is through
consequence oxidation of alcohol group (-OH) to aldehyde (-CHO)
and acid (-COOH), and thereafter the cleavage of β-alanine betaine
C-N bonds yielded trimethylamine and alkyl chain.
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: The purpose of this study was to understand the main
sources of copper (Cu) accumulation in target organs of tilapia
(Oreochromis mossambicus) and to investigate how the organism
mediate the process of Cu accumulation under prolonged conditions.
By measuring both dietary and waterborne Cu accumulation and total
concentrations in tilapia with biokinetic modeling approach, we were
able to clarify the biokinetic coping mechanisms for the long term Cu
accumulation. This study showed that water and food are both the
major source of Cu for the muscle and liver of tilapia. This implied
that control the Cu concentration in these two routes will be correlated
to the Cu bioavailability for tilapia. We found that exposure duration
and level of waterborne Cu drove the Cu accumulation in tilapia. The
ability for Cu biouptake and depuration in organs of tilapia were
actively mediated under prolonged exposure conditions. Generally,
the uptake rate, depuration rate and net bioaccumulation ability in all
selected organs decreased with the increasing level of waterborne Cu
and extension of exposure duration.Muscle tissues accounted for over
50%of the total accumulated Cu and played a key role in buffering the
Cu burden in the initial period of exposure, alternatively, the liver
acted a more important role in the storage of Cu with the extension of
exposures. We concluded that assumption of the constant biokinetic
rates could lead to incorrect predictions with overestimating the
long-term Cu accumulation in ecotoxicological risk assessments.
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: In the present essay, a model of choice by actors is analysedby utilizing the theory of chaos to explain how change comes about. Then, by using ancient and modern sources of literature, the theory of the social contract is analysed as a historical phenomenon that first appeared during the period of Classical Greece. Then, based on the findings of this analysis, the practice of direct democracy and public choice in ancient Athens is analysed, through two historical cases: Eubulus and Lycurgus political program in the second half of the 4th century. The main finding of this research is that these policies can be interpreted as an implementation of a social contract, through which citizens were taking decisions based on rational choice according to economic considerations.