Abstract: There are multiple reasons to expect that detecting the
word order errors in a text will be a difficult problem, and detection
rates reported in the literature are in fact low. Although grammatical
rules constructed by computer linguists improve the performance of
grammar checker in word order diagnosis, the repairing task is still
very difficult. This paper presents an approach for repairing word
order errors in English text by reordering words in a sentence and
choosing the version that maximizes the number of trigram hits
according to a language model. The novelty of this method concerns
the use of an efficient confusion matrix technique for reordering the
words. The comparative advantage of this method is that works with
a large set of words, and avoids the laborious and costly process of
collecting word order errors for creating error patterns.
Abstract: This paper presents modern vibration signalprocessing
techniques for vehicle gearbox fault diagnosis, via the
wavelet analysis and the Squared Envelope (SE) technique. The
wavelet analysis is regarded as a powerful tool for the detection of
sudden changes in non-stationary signals. The Squared Envelope
(SE) technique has been extensively used for rolling bearing
diagnostics. In the present work a scheme of using the Squared
Envelope technique for early detection of gear tooth pit. The pitting
defect is manufactured on the tooth side of a fifth speed gear on the
intermediate shaft of a vehicle gearbox. The objective is to
supplement the current techniques of gearbox fault diagnosis based
on using the raw vibration and ordered signals. The test stand is
equipped with three dynamometers; the input dynamometer serves as
the internal combustion engine, the output dynamometers introduce
the load on the flanges of output joint shafts. The gearbox used for
experimental measurements is the type most commonly used in
modern small to mid-sized passenger cars with transversely mounted
powertrain and front wheel drive; a five-speed gearbox with final
drive gear and front wheel differential. The results show that the
approaches methods are effective for detecting and diagnosing
localized gear faults in early stage under different operation
conditions, and are more sensitive and robust than current gear
diagnostic techniques.
Abstract: Recently, the issue of machine condition monitoring
and fault diagnosis as a part of maintenance system became global
due to the potential advantages to be gained from reduced
maintenance costs, improved productivity and increased machine
availability. The aim of this work is to investigate the effectiveness
of a new fault diagnosis method based on power spectral density
(PSD) of vibration signals in combination with decision trees and
fuzzy inference system (FIS). To this end, a series of studies was
conducted on an external gear hydraulic pump. After a test under
normal condition, a number of different machine defect conditions
were introduced for three working levels of pump speed (1000, 1500,
and 2000 rpm), corresponding to (i) Journal-bearing with inner face
wear (BIFW), (ii) Gear with tooth face wear (GTFW), and (iii)
Journal-bearing with inner face wear plus Gear with tooth face wear
(B&GW). The features of PSD values of vibration signal were
extracted using descriptive statistical parameters. J48 algorithm is
used as a feature selection procedure to select pertinent features from
data set. The output of J48 algorithm was employed to produce the
crisp if-then rule and membership function sets. The structure of FIS
classifier was then defined based on the crisp sets. In order to
evaluate the proposed PSD-J48-FIS model, the data sets obtained
from vibration signals of the pump were used. Results showed that
the total classification accuracy for 1000, 1500, and 2000 rpm
conditions were 96.42%, 100%, and 96.42% respectively. The results
indicate that the combined PSD-J48-FIS model has the potential for
fault diagnosis of hydraulic pumps.
Abstract: Model-based approaches have been applied successfully
to a wide range of tasks such as specification, simulation, testing, and
diagnosis. But one bottleneck often prevents the introduction of these
ideas: Manual modeling is a non-trivial, time-consuming task.
Automatically deriving models by observing and analyzing running
systems is one possible way to amend this bottleneck. To
derive a model automatically, some a-priori knowledge about the
model structure–i.e. about the system–must exist. Such a model
formalism would be used as follows: (i) By observing the network
traffic, a model of the long-term system behavior could be generated
automatically, (ii) Test vectors can be generated from the model,
(iii) While the system is running, the model could be used to diagnose
non-normal system behavior.
The main contribution of this paper is the introduction of a model
formalism called 'probabilistic regression automaton' suitable for the
tasks mentioned above.
Abstract: Support vector machines (SVMs) have shown
superior performance compared to other machine learning techniques,
especially in classification problems. Yet one limitation of SVMs is
the lack of an explanation capability which is crucial in some
applications, e.g. in the medical and security domains. In this paper, a
novel approach for eclectic rule-extraction from support vector
machines is presented. This approach utilizes the knowledge acquired
by the SVM and represented in its support vectors as well as the
parameters associated with them. The approach includes three stages;
training, propositional rule-extraction and rule quality evaluation.
Results from four different experiments have demonstrated the value
of the approach for extracting comprehensible rules of high accuracy
and fidelity.
Abstract: Approximate tandem repeats in a genomic sequence are
two or more contiguous, similar copies of a pattern of nucleotides.
They are used in DNA mapping, studying molecular evolution
mechanisms, forensic analysis and research in diagnosis of inherited
diseases. All their functions are still investigated and not well
defined, but increasing biological databases together with tools for
identification of these repeats may lead to discovery of their specific
role or correlation with particular features. This paper presents a new
approach for finding approximate tandem repeats in a given sequence,
where the similarity between consecutive repeats is measured using
the Hamming distance. It is an enhancement of a method for finding
exact tandem repeats in DNA sequences based on the Burrows-
Wheeler transform.
Abstract: Brucellosis is a zoonotic disease; its symptoms and appearances are not exclusive in human and its traditional diagnosis is based on culture, serological methods and conventional PCR. For more sensitive, specific detection and differentiation of Brucella spp., the real time PCR method is recommended. This research has performed to determine the presence and prevalence of Brucella spp. and differentiation of Brucella abortus and Brucella melitensis in house mouse (Mus musculus) in west of Iran. A TaqMan analysis and single-step PCR was carried out in total 326 DNA of Mouse's spleen samples. From the total number of 326 samples, 128 (39.27%) gave positive results for Brucella spp. by conventional PCR, also 65 and 32 out of the 128 specimens were positive for B. melitensis, B. abortus, respectively. These results indicate a high presence of this pathogen in this area and that real time PCR is considerably faster than current standard methods for identification and differentiation of Brucella species. To our knowledge, this study is the first prevalence report of direct identification and differentiation of B. abortus and B. melitensis by real time PCR in mouse tissue samples in Iran.
Abstract: A lot of recent research have spoken on the relation
between the increase of the homocysteinemia and some kinds of
cancer . For that, our study was based on the research of a possible
relation between the increase of the concentration of this amino-acid
in the plasma and the appearance of the disease of the Acute
Lymphoblastic Leukaemia in a part of Algerian children with Berber
origin in the East of Algeria . The study has done on 47 ill persons
with an average age of (09±06 ) years , with whom the disease has
diagnosed by blood and marrow examination in the hospital of blood
diseases in the CHU of Batna, and on 194 healthy witnesses of the
same age. The two groups were benefited by a dosage of the
concentration of the homocysteine vitamin B9 ,vitamin B12 , and
also of the study of special polymorphisms of indispensable enzymes
in the metabolism of this acid , and that by the use of the method (
Light cycler ) Real time PCR , on the following enzymes : MS (
C2756G ), MSR ( A66G ) ,MTHFR1 ( C677T ) and MTHFR2
(A1298C). The obtained results have revealed that the rate of the
homozygote muted genotype is the less frequent in the two groups ,
and that exist at list one genotype of each enzyme in the ill group and
in which the percentage exceed with remarkable way the same
genotype in the healthy group and we notice specially the muted
genotype GG of -the methionine synthetase-and the form TT of the
enzyme – methyline tetra hydrofolate reductase – We notice the
existence of considerable number of genotypes in the ill group lied
with characteristic increase of this Amino-acid ,and that for the
reduction of the biologic activity of these enzymes which become
inefficient in the transfer of the homocysteine into the methionine
and cause the diminution of the biologic activity of these enzymes
and with consequence the reduction of the percentage of methylic
radicals in the DNA of studied genes and that lead to the increase of
the activity and the capacity of transcription , and it-s so probably
that this last one is one of the factors of this disease especially if we
know that the specific check-up of vitamins is normal and similar in
the two groups , which ovoid the hypothesis of the reduction of
vitamins . We notice also that the heterozygote genotype is the less in
the sick category except the MTHFR2. Wild genotype is more
frequent in the witness group except MSR. Even these results are
partials; they open a new way in the genetic diagnosis of this
malicious disease which allow a precocious diagnosis and the use of
an effective and appropriated treatment in the same time.
Abstract: Sensors possess several properties of physical
measures. Whether devices that convert a sensed signal into an
electrical signal, chemical sensors and biosensors, thus all these
sensors can be considered as an interface between the physical and
electrical equipment. The problem is the analysis of the multitudes of
saved settings as input variables. However, they do not all have the
same level of influence on the outputs. In order to identify the most
sensitive parameters, those that can guide users in gathering
information on the ground and in the process of model calibration
and sensitivity analysis for the effect of each change made.
Mathematical models used for processing become very complex.
In this paper a fuzzy rule-based system is proposed as a solution
for this problem. The system collects the available signals
information from sensors. Moreover, the system allows the study of
the influence of the various factors that take part in the decision
system. Since its inception fuzzy set theory has been regarded as a
formalism suitable to deal with the imprecision intrinsic to many
problems. At the same time, fuzzy sets allow to use symbolic models.
In this study an example was applied for resolving variety of
physiological parameters that define human health state. The
application system was done for medical diagnosis help. The inputs
are the signals expressed the cardiovascular system parameters, blood
pressure, Respiratory system paramsystem was done, it will be able
to predict the state of patient according any input values.
Abstract: This paper illustrates the use of a combined neural
network model for classification of electrocardiogram (ECG) beats.
We present a trainable neural network ensemble approach to develop
customized electrocardiogram beat classifier in an effort to further
improve the performance of ECG processing and to offer
individualized health care.
We process a three stage technique for detection of premature
ventricular contraction (PVC) from normal beats and other heart
diseases. This method includes a denoising, a feature extraction and a
classification. At first we investigate the application of stationary
wavelet transform (SWT) for noise reduction of the
electrocardiogram (ECG) signals. Then feature extraction module
extracts 10 ECG morphological features and one timing interval
feature. Then a number of multilayer perceptrons (MLPs) neural
networks with different topologies are designed.
The performance of the different combination methods as well as
the efficiency of the whole system is presented. Among them,
Stacked Generalization as a proposed trainable combined neural
network model possesses the highest recognition rate of around 95%.
Therefore, this network proves to be a suitable candidate in ECG
signal diagnosis systems. ECG samples attributing to the different
ECG beat types were extracted from the MIT-BIH arrhythmia
database for the study.
Abstract: The Major Depressive Disorder has been a burden of
medical expense in Taiwan as well as the situation around the world.
Major Depressive Disorder can be defined into different categories by
previous human activities. According to machine learning, we can
classify emotion in correct textual language in advance. It can help
medical diagnosis to recognize the variance in Major Depressive
Disorder automatically. Association language incremental is the
characteristic and relationship that can discovery words in sentence.
There is an overlapping-category problem for classification. In this
paper, we would like to improve the performance in classification in
principle of no overlapping-category problems. We present an
approach that to discovery words in sentence and it can find in high
frequency in the same time and can-t overlap in each category, called
Association Language Features by its Category (ALFC).
Experimental results show that ALFC distinguish well in Major
Depressive Disorder and have better performance. We also compare
the approach with baseline and mutual information that use single
words alone or correlation measure.
Abstract: In Multiple Sclerosis, pathological changes in the
brain results in deviations in signal intensity on Magnetic Resonance
Images (MRI). Quantitative analysis of these changes and their
correlation with clinical finding provides important information for
diagnosis. This constitutes the objective of our work. A new approach
is developed. After the enhancement of images contrast and the brain
extraction by mathematical morphology algorithm, we proceed to the
brain segmentation. Our approach is based on building statistical
model from data itself, for normal brain MRI and including clustering
tissue type. Then we detect signal abnormalities (MS lesions) as a
rejection class containing voxels that are not explained by the built
model. We validate the method on MR images of Multiple Sclerosis
patients by comparing its results with those of human expert
segmentation.
Abstract: Heart failure is the most common reason of death
nowadays, but if the medical help is given directly, the patient-s life
may be saved in many cases. Numerous heart diseases can be
detected by means of analyzing electrocardiograms (ECG). Artificial
Neural Networks (ANN) are computer-based expert systems that
have proved to be useful in pattern recognition tasks. ANN can be
used in different phases of the decision-making process, from
classification to diagnostic procedures. This work concentrates on a
review followed by a novel method.
The purpose of the review is to assess the evidence of healthcare
benefits involving the application of artificial neural networks to the
clinical functions of diagnosis, prognosis and survival analysis, in
ECG signals. The developed method is based on a compound neural
network (CNN), to classify ECGs as normal or carrying an
AtrioVentricular heart Block (AVB). This method uses three
different feed forward multilayer neural networks. A single output
unit encodes the probability of AVB occurrences. A value between 0
and 0.1 is the desired output for a normal ECG; a value between 0.1
and 1 would infer an occurrence of an AVB. The results show that
this compound network has a good performance in detecting AVBs,
with a sensitivity of 90.7% and a specificity of 86.05%. The accuracy
value is 87.9%.
Abstract: Fourier transform infrared (FT-IR) spectroscopic imaging
is an emerging technique that provides both chemically and
spatially resolved information. The rich chemical content of data
may be utilized for computer-aided determinations of structure and
pathologic state (cancer diagnosis) in histological tissue sections for
prostate cancer. FT-IR spectroscopic imaging of prostate tissue has
shown that tissue type (histological) classification can be performed to
a high degree of accuracy [1] and cancer diagnosis can be performed
with an accuracy of about 80% [2] on a microscopic (≈ 6μm)
length scale. In performing these analyses, it has been observed
that there is large variability (more than 60%) between spectra from
different points on tissue that is expected to consist of the same
essential chemical constituents. Spectra at the edges of tissues are
characteristically and consistently different from chemically similar
tissue in the middle of the same sample. Here, we explain these
differences using a rigorous electromagnetic model for light-sample
interaction. Spectra from FT-IR spectroscopic imaging of chemically
heterogeneous samples are different from bulk spectra of individual
chemical constituents of the sample. This is because spectra not
only depend on chemistry, but also on the shape of the sample.
Using coupled wave analysis, we characterize and quantify the nature
of spectral distortions at the edges of tissues. Furthermore, we
present a method of performing histological classification of tissue
samples. Since the mid-infrared spectrum is typically assumed to
be a quantitative measure of chemical composition, classification
results can vary widely due to spectral distortions. However, we
demonstrate that the selection of localized metrics based on chemical
information can make our data robust to the spectral distortions
caused by scattering at the tissue boundary.
Abstract: Sputum smear conversion after one month of antituberculosis
therapy in new smear positive pulmonary tuberculosis
patients (PTB+) is a vital indicator towards treatment success. The
objective of this study is to determine the rate of sputum smear
conversion in new PTB+ patients after one month under treatment of
National Institute of Diseases of the Chest and Hospital (NIDCH).
Analysis of sputum smear conversion was done by re-clinical
examination with sputum smear microscopic test after one month.
Socio-demographic and hematological parameters were evaluated to
perceive the correlation with the disease status. Among all enrolled
patients only 33.33% were available for follow up diagnosis and of
them only 42.86% patients turned to smear negative. Probably this
consequence is due to non-coherence to the proper disease
management. 66.67% and 78.78% patients reported low haemoglobin
and packed cell volume level respectively whereas 80% and 93.33%
patients accounted accelerated platelet count and erythrocyte
sedimentation rate correspondingly.
Abstract: Dengue fever is an important human arboviral disease. Outbreaks are now reported quite often from many parts of the world. The number of cases involving pregnant women and infant cases are increasing every year. The illness is often severe and complications may occur. Deaths often occur because of the difficulties in early diagnosis and in the improper management of the diseases. Dengue antibodies from pregnant women are passed on to infants and this protects the infants from dengue infections. Antibodies from the mother are transferred to the fetus when it is still in the womb. In this study, we formulate a mathematical model to describe the transmission of this disease in pregnant women. The model is formulated by dividing the human population into pregnant women and non-pregnant human (men and non-pregnant women). Each class is subdivided into susceptible (S), infectious (I) and recovered (R) subclasses. We apply standard dynamical analysis to our model. Conditions for the local stability of the equilibrium points are given. The numerical simulations are shown. The bifurcation diagrams of our model are discussed. The control of this disease in pregnant women is discussed in terms of the threshold conditions.
Abstract: Recently, a quality of motors is inspected by human
ears. In this paper, I propose two systems using a method of speech
recognition for automation of the inspection. The first system is based
on a method of linear processing which uses K-means and Nearest
Neighbor method, and the second is based on a method of non-linear
processing which uses neural networks. I used motor sounds in these
systems, and I successfully recognize 86.67% of motor sounds in the
linear processing system and 97.78% in the non-linear processing
system.
Abstract: In this article, we propose an Intelligent Medical
Diagnostic System (IMDS) accessible through common
web-based interface, to on-line perform initial screening for
osteoporosis. The fundamental approaches which construct the
proposed system are mainly based on the fuzzy-neural theory,
which can exhibit superiority over other conventional technologies
in many fields. In diagnosis process, users simply answer
a series of directed questions to the system, and then they
will immediately receive a list of results which represents the
risk degrees of osteoporosis. According to clinical testing results,
it is shown that the proposed system can provide the general
public or even health care providers with a convenient, reliable,
inexpensive approach to osteoporosis risk assessment.
Abstract: Phase-Contrast MR imaging methods are widely used
for measurement of blood flow velocity components. Also there are
some other tools such as CT and Ultrasound for velocity map
detection in intravascular studies. These data are used in deriving
flow characteristics. Some clinical applications are investigated
which use pressure distribution in diagnosis of intravascular disorders
such as vascular stenosis. In this paper an approach to the problem of
measurement of intravascular pressure field by using velocity field
obtained from flow images is proposed. The method presented in this
paper uses an algorithm to calculate nonlinear equations of Navier-
Stokes, assuming blood as an incompressible and Newtonian fluid.
Flow images usually suffer the lack of spatial resolution. Our
attempt is to consider the effect of spatial resolution on the pressure
distribution estimated from this method. In order to achieve this aim,
velocity map of a numerical phantom is derived at six different
spatial resolutions. To determine the effects of vascular stenoses on
pressure distribution, a stenotic phantom geometry is considered. A
comparison between the pressure distribution obtained from the
phantom and the pressure resulted from the algorithm is presented. In
this regard we also compared the effects of collocated and staggered
computational grids on the pressure distribution resulted from this
algorithm.
Abstract: Availability of high dimensional biological datasets such as from gene expression, proteomic, and metabolic experiments can be leveraged for the diagnosis and prognosis of diseases. Many classification methods in this area have been studied to predict disease states and separate between predefined classes such as patients with a special disease versus healthy controls. However, most of the existing research only focuses on a specific dataset. There is a lack of generic comparison between classifiers, which might provide a guideline for biologists or bioinformaticians to select the proper algorithm for new datasets. In this study, we compare the performance of popular classifiers, which are Support Vector Machine (SVM), Logistic Regression, k-Nearest Neighbor (k-NN), Naive Bayes, Decision Tree, and Random Forest based on mock datasets. We mimic common biological scenarios simulating various proportions of real discriminating biomarkers and different effect sizes thereof. The result shows that SVM performs quite stable and reaches a higher AUC compared to other methods. This may be explained due to the ability of SVM to minimize the probability of error. Moreover, Decision Tree with its good applicability for diagnosis and prognosis shows good performance in our experimental setup. Logistic Regression and Random Forest, however, strongly depend on the ratio of discriminators and perform better when having a higher number of discriminators.