Abstract: In this paper, the requirement for Coke quality
prediction, its role in Blast furnaces, and the model output is
explained. By applying method of Artificial Neural Networking
(ANN) using back propagation (BP) algorithm, prediction model has
been developed to predict CSR. Important blast furnace functions
such as permeability, heat exchanging, melting, and reducing
capacity are mostly connected to coke quality. Coke quality is further
dependent upon coal characterization and coke making process
parameters. The ANN model developed is a useful tool for process
experts to adjust the control parameters in case of coke quality
deviations. The model also makes it possible to predict CSR for new
coal blends which are yet to be used in Coke Plant. Input data to the
model was structured into 3 modules, for tenure of past 2 years and
the incremental models thus developed assists in identifying the
group causing the deviation of CSR.
Abstract: The importance of machining process in today-s
industry requires the establishment of more practical approaches to
clearly represent the intimate and severe contact on the tool-chipworkpiece
interfaces. Mathematical models are developed using the
measured force signals to relate each of the tool-chip friction
components on the rake face to the operating cutting parameters in
rough turning operation using multilayers coated carbide inserts.
Nonlinear modeling proved to have high capability to detect the
nonlinear functional variability embedded in the experimental data.
While feedrate is found to be the most influential parameter on the
friction coefficient and its related force components, both cutting
speed and depth of cut are found to have slight influence. Greater
deformed chip thickness is found to lower the value of friction
coefficient as the sliding length on the tool-chip interface is reduced.
Abstract: Chaos and fractals are novel fields of physics and mathematics showing up a new way of universe viewpoint and creating many ideas to solve several present problems. In this paper, a novel algorithm based on the chaotic sequence generator with the highest ability to adapt and reach the global optima is proposed. The adaptive ability of proposal algorithm is flexible in 2 steps. The first one is a breadth-first search and the second one is a depth-first search. The proposal algorithm is examined by 2 functions, the Camel function and the Schaffer function. Furthermore, the proposal algorithm is applied to optimize training Multilayer Neural Networks.
Abstract: Human identification at a distance has recently gained
growing interest from computer vision researchers. Gait recognition
aims essentially to address this problem by identifying people based
on the way they walk [1]. Gait recognition has 3 steps. The first step
is preprocessing, the second step is feature extraction and the third
one is classification. This paper focuses on the classification step that
is essential to increase the CCR (Correct Classification Rate).
Multilayer Perceptron (MLP) is used in this work. Neural Networks
imitate the human brain to perform intelligent tasks [3].They can
represent complicated relationships between input and output and
acquire knowledge about these relationships directly from the data
[2]. In this paper we apply MLP NN for 11 views in our database and
compare the CCR values for these views. Experiments are performed
with the NLPR databases, and the effectiveness of the proposed
method for gait recognition is demonstrated.
Abstract: In recent years, scanning probe atomic force
microscopy SPM AFM has gained acceptance over a wide spectrum
of research and science applications. Most fields focuses on physical,
chemical, biological while less attention is devoted to manufacturing
and machining aspects. The purpose of the current study is to assess
the possible implementation of the SPM AFM features and its
NanoScope software in general machining applications with special
attention to the tribological aspects of cutting tool. The surface
morphology of coated and uncoated as-received carbide inserts is
examined, analyzed, and characterized through the determination of
the appropriate scanning setting, the suitable data type imaging
techniques and the most representative data analysis parameters
using the MultiMode SPM AFM in contact mode. The NanoScope
operating software is used to capture realtime three data types
images: “Height", “Deflection" and “Friction". Three scan sizes are
independently performed: 2, 6, and 12 μm with a 2.5 μm vertical
range (Z). Offline mode analysis includes the determination of three
functional topographical parameters: surface “Roughness", power
spectral density “PSD" and “Section". The 12 μm scan size in
association with “Height" imaging is found efficient to capture every
tiny features and tribological aspects of the examined surface. Also,
“Friction" analysis is found to produce a comprehensive explanation
about the lateral characteristics of the scanned surface. Configuration
of many surface defects and drawbacks has been precisely detected
and analyzed.
Abstract: The main goal in this paper is to quantify the quality of
different techniques for radiation treatment plans, a back-propagation
artificial neural network (ANN) combined with biomedicine theory
was used to model thirteen dosimetric parameters and to calculate
two dosimetric indices. The correlations between dosimetric indices
and quality of life were extracted as the features and used in the ANN
model to make decisions in the clinic. The simulation results show
that a trained multilayer back-propagation neural network model can
help a doctor accept or reject a plan efficiently. In addition, the
models are flexible and whenever a new treatment technique enters
the market, the feature variables simply need to be imported and the
model re-trained for it to be ready for use.
Abstract: The effect of the number of quantum dot (QD) layers
on the saturated gain of doped QD semiconductor optical amplifiers
(SOAs) has been studied using multi-population coupled rate
equations. The developed model takes into account the effect of
carrier coupling between adjacent layers. It has been found that
increasing the number of QD layers (K) increases the unsaturated
optical gain for K
Abstract: Thermal load calculations have been performed for
multi-layered walls that are composed of three different parts; a
common (sand and cement) plaster, and two types of locally
produced soft and hard bricks. The masonry construction of these
layered walls was based on concrete-backed stone masonry made of
limestone bricks joined by mortar. These multilayered walls are
forming the outer walls of the building envelope of a typical Libyan
house. Based on the periodic seasonal weather conditions, within the
Libyan cost region during summer and winter, measured thermal
conductivity values were used to implement such seasonal variation
of heat flow and the temperature variations through the walls. The
experimental measured thermal conductivity values were obtained
using the Hot Disk technique. The estimation of the thermal
resistance of the wall layers ( R-values) is based on measurements
and calculations. The numerical calculations were done using a
simplified analytical model that considers two different wall
constructions which are characteristics of such houses. According to
the obtained results, the R-values were quite low and therefore,
several suggestions have been proposed to improve the thermal
loading performance that will lead to a reasonable human comfort
and reduce energy consumption.
Abstract: The design of a complete expansion that allows for
compact representation of certain relevant classes of signals is a
central problem in signal processing applications. Achieving such a
representation means knowing the signal features for the purpose of
denoising, classification, interpolation and forecasting. Multilayer
Neural Networks are relatively a new class of techniques that are
mathematically proven to approximate any continuous function
arbitrarily well. Radial Basis Function Networks, which make use of
Gaussian activation function, are also shown to be a universal
approximator. In this age of ever-increasing digitization in the
storage, processing, analysis and communication of information,
there are numerous examples of applications where one needs to
construct a continuously defined function or numerical algorithm to
approximate, represent and reconstruct the given discrete data of a
signal. Many a times one wishes to manipulate the data in a way that
requires information not included explicitly in the data, which is
done through interpolation and/or extrapolation.
Tidal data are a very perfect example of time series and many
statistical techniques have been applied for tidal data analysis and
representation. ANN is recent addition to such techniques. In the
present paper we describe the time series representation capabilities
of a special type of ANN- Radial Basis Function networks and
present the results of tidal data representation using RBF. Tidal data
analysis & representation is one of the important requirements in
marine science for forecasting.
Abstract: A power cable is widely used for power supply in
power distributing networks and power transmission lines. Due to
limitations in the production, delivery and setting up power cables,
they are produced and delivered in several separate lengths. Cable
itself, consists of two cable terminations and arbitrary number of
cable joints, depending on the cable route length. Electrical stress
control is needed to prevent a dielectric breakdown at the end of the
insulation shield in both the air and cable insulation. Reliability of
cable joint depends on its materials, design, installation and operating
environment. The paper describes design and performance results for
new modeled cable joints. Design concepts, based on numerical
calculations, must be correct. An Equivalent Electrodes
Method/Boundary Elements Method-hybrid approach that allows
electromagnetic field calculations in multilayer dielectric media,
including inhomogeneous regions, is presented.
Abstract: In this paper, we proposed the effects of Mo thickness
on the properties of AZO/Mo/AZO multilayer thin films for
opto-electronics applications. The structural, optical and electrical
properties of AZO/Mo/AZO thin films were investigated.
Optimization of the thin films coatings resulted with low resistivity of
9.98 × 10-5 )-cm, mobility of 12.75 cm2/V-s, carrier concentration of
1.05 × 1022 cm-3, maximum transmittance of 79.13% over visible
spectrum of 380 – 780 nm and Haacke figure of merit (FOM) are 5.95
× 10-2 )-1 under Mo layer thickness of 15 nm. These results indicate an
alternative candidate for use as a transparent electrode in solar cells
and various displays applications.
Abstract: The innovative intelligent fuzzy weighted input
estimation method (FWIEM) can be applied to the inverse heat
transfer conduction problem (IHCP) to estimate the unknown
time-varying heat flux of the multilayer materials as presented in this
paper. The feasibility of this method can be verified by adopting the
temperature measurement experiment. The experiment modular may
be designed by using the copper sample which is stacked up 4
aluminum samples with different thicknesses. Furthermore, the
bottoms of copper samples are heated by applying the standard heat
source, and the temperatures on the tops of aluminum are measured by
using the thermocouples. The temperature measurements are then
regarded as the inputs into the presented method to estimate the heat
flux in the bottoms of copper samples. The influence on the estimation
caused by the temperature measurement of the sample with different
thickness, the processing noise covariance Q, the weighting factor γ ,
the sampling time interval Δt , and the space discrete interval Δx ,
will be investigated by utilizing the experiment verification. The
results show that this method is efficient and robust to estimate the
unknown time-varying heat input of the multilayer materials.
Abstract: The machining of Carbon Fiber Reinforced Plastics
has come to constitute a significant challenge for many fields of
industry. The resulting surface finish of machined parts is of primary
concern for several reasons, including contact quality and impact on
the assembly. Therefore, the characterization and prediction of
roughness based on machining parameters are crucial for costeffective
operations. In this study, a PCD tool comprised of two
straight flutes was used to trim 32-ply carbon fiber laminates in a bid
to analyze the effects of the feed rate and the cutting speed on the
surface roughness. The results show that while the speed has but a
slight impact on the surface finish, the feed rate for its part affects it
strongly. A detailed study was also conducted on the effect of fiber
orientation on surface roughness, for quasi-isotropic laminates used
in aerospace. The resulting roughness profiles for the four-ply
orientation lay-up were compared, and it was found that fiber angle is
a critical parameter relating to surface roughness. One of the four
orientations studied led to very poor surface finishes, and
characteristic roughness profiles were identified and found to only
relate to the ply orientations of multilayer carbon fiber laminates.
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: Semiconductor materials with coatings have a wide range of applications in MEMS and NEMS. This work uses transfermatrix method for calculating the radiative properties. Dopped silicon is used and the coherent formulation is applied. The Drude model for the optical constants of doped silicon is employed. Results showed that for the visible wavelengths, more emittance occurs in greater concentrations and the reflectance decreases as the concentration increases. In these wavelengths, transmittance is negligible. Donars and acceptors act similar in visible wavelengths. The effect of wave interference can be understood by plotting the spectral properties such as reflectance or transmittance of a thin dielectric film versus the film thickness and analyzing the oscillations of properties due to constructive and destructive interferences. But this effect has not been shown at visible wavelengths. At room temperature, the scattering process is dominated by lattice scattering for lightly doped silicon, and the impurity scattering becomes important for heavily doped silicon when the dopant concentration exceeds1018cm-3 .
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: Inverse kinematics analysis plays an important role in developing a robot manipulator. But it is not too easy to derive the inverse kinematic equation of a robot manipulator especially robot manipulator which has numerous degree of freedom. This paper describes an application of Artificial Neural Network for modeling the inverse kinematics equation of a robot manipulator. In this case, the robot has three degree of freedoms and the robot was implemented for drilling a printed circuit board. The artificial neural network architecture used for modeling is a multilayer perceptron networks with steepest descent backpropagation training algorithm. The designed artificial neural network has 2 inputs, 2 outputs and varies in number of hidden layer. Experiments were done in variation of number of hidden layer and learning rate. Experimental results show that the best architecture of artificial neural network used for modeling inverse kinematics of is multilayer perceptron with 1 hidden layer and 38 neurons per hidden layer. This network resulted a RMSE value of 0.01474.
Abstract: A complete spectral representation for the
electromagnetic field of planar multilayered waveguides
inhomogeneously filled with omega media is presented. The problem
of guided electromagnetic propagation is reduced to an eigenvalue
equation related to a 2 ´ 2 matrix differential operator. Using the
concept of adjoint waveguide, general bi-orthogonality relations for
the hybrid modes (either from the discrete or from the continuous
spectrum) are derived. For the special case of homogeneous layers
the linear operator formalism is reduced to a simple 2 ´ 2 coupling
matrix eigenvalue problem. Finally, as an example of application, the
surface and the radiation modes of a grounded omega slab waveguide
are analyzed.
Abstract: The conjugate gradient optimization algorithm
usually used for nonlinear least squares is presented and is
combined with the modified back propagation algorithm yielding
a new fast training multilayer perceptron (MLP) algorithm
(CGFR/AG). The approaches presented in the paper consist of
three steps: (1) Modification on standard back propagation
algorithm by introducing gain variation term of the activation
function, (2) Calculating the gradient descent on error with
respect to the weights and gains values and (3) the determination
of the new search direction by exploiting the information
calculated by gradient descent in step (2) as well as the previous
search direction. The proposed method improved the training
efficiency of back propagation algorithm by adaptively modifying
the initial search direction. Performance of the proposed method
is demonstrated by comparing to the conjugate gradient algorithm
from neural network toolbox for the chosen benchmark. The
results show that the number of iterations required by the
proposed method to converge is less than 20% of what is required
by the standard conjugate gradient and neural network toolbox
algorithm.
Abstract: In this paper we present an efficient system for
independent speaker speech recognition based on neural network
approach. The proposed architecture comprises two phases: a
preprocessing phase which consists in segmental normalization and
features extraction and a classification phase which uses neural
networks based on nonparametric density estimation namely the
general regression neural network (GRNN). The relative
performances of the proposed model are compared to the similar
recognition systems based on the Multilayer Perceptron (MLP), the
Recurrent Neural Network (RNN) and the well known Discrete
Hidden Markov Model (HMM-VQ) that we have achieved also.
Experimental results obtained with Arabic digits have shown that the
use of nonparametric density estimation with an appropriate
smoothing factor (spread) improves the generalization power of the
neural network. The word error rate (WER) is reduced significantly
over the baseline HMM method. GRNN computation is a successful
alternative to the other neural network and DHMM.