Abstract: Lately there has been a significant boost of interest in
music digital libraries, which constitute an attractive area of research
and development due to their inherent interesting issues and
challenging technical problems, solutions to which will be highly
appreciated by enthusiastic end-users. We present here a DL that we
have developed to support users in their quest for classical music
pieces within a particular collection of 18,000+ audio recordings.
To cope with the early DL model limitations, we have used a refined
socio-semantic and contextual model that allows rich bibliographic
content description, along with semantic annotations, reviewing,
rating, knowledge sharing etc. The multi-layered service model
allows incorporation of local and distributed information,
construction of rich hypermedia documents, expressing the complex
relationships between various objects and multi-dimensional spaces,
agents, actors, services, communities, scenarios etc., and facilitates
collaborative activities to offer to individual users the needed
collections and services.
Abstract: Classifier fusion may generate more accurate
classification than each of the basic classifiers. Fusion is often based
on fixed combination rules like the product, average etc. This paper
presents decision templates as classifier fusion method for the
recognition of the handwritten English and Farsi numerals (1-9).
The process involves extracting a feature vector on well-known
image databases. The extracted feature vector is fed to multiple
classifier fusion. A set of experiments were conducted to compare
decision templates (DTs) with some combination rules. Results from
decision templates conclude 97.99% and 97.28% for Farsi and
English handwritten digits.
Abstract: The forest stand consisted of four layers. The species
composition between the third and the bottom layers was almost
similar, whereas it was almost exclusive between the top and the lower
three layers. The values of Shannon-s index H' and Pielou-s index
J ' tended to increase from the bottom layer upward, except for
H' -value of the top layer. The values of H' and J ' were 4.21 bit
and 0.73, respectively, for the total stand. High woody species
diversity of the forest depended on large trees in the upper layers,
which trend was different from a subtropical evergreen broadleaf
forest grown in silicate habitat in the northern part of Okinawa Island.
The spatial distribution of trees was overlapped between the third and
the bottom layers, whereas it was independent or slightly exclusive
between the top and the lower three layers. Mean tree weight of each
layer decreased from the top toward the bottom layer, whereas the
corresponding tree density increased from the top downward. This
relationship was analogous to the process of self-thinning plant
populations.
Abstract: In this paper, an improved technique for contingency
ranking using artificial neural network (ANN) is presented. The
proposed approach is based on multi-layer perceptrons trained by
backpropagation to contingency analysis. Severity indices in dynamic
stability assessment are presented. These indices are based on the
concept of coherency and three dot products of the system variables.
It is well known that some indices work better than others for a
particular power system. This paper along with test results using
several different systems, demonstrates that combination of indices
with ANN provides better ranking than a single index. The presented
results are obtained through the use of power system simulation
(PSS/E) and MATLAB 6.5 software.
Abstract: Gene, principal unit of inheritance, is an ordered
sequence of nucleotides. The genes of eukaryotic organisms include
alternating segments of exons and introns. The region of
Deoxyribonucleic acid (DNA) within a gene containing instructions
for coding a protein is called exon. On the other hand, non-coding
regions called introns are another part of DNA that regulates gene
expression by removing from the messenger Ribonucleic acid (RNA)
in a splicing process. This paper proposes to determine splice
junctions that are exon-intron boundaries by analyzing DNA
sequences. A splice junction can be either exon-intron (EI) or intron
exon (IE). Because of the popularity and compatibility of the
artificial neural network (ANN) in genetic fields; various ANN
models are applied in this research. Multi-layer Perceptron (MLP),
Radial Basis Function (RBF) and Generalized Regression Neural
Networks (GRNN) are used to analyze and detect the splice junctions
of gene sequences. 10-fold cross validation is used to demonstrate
the accuracy of networks. The real performances of these networks
are found by applying Receiver Operating Characteristic (ROC)
analysis.
Abstract: Research results and optimal parameters investigation
of laser cut and profiling of diamond and quartz substrates by
femtosecond laser pulses are presented. Profiles 10 μm in width, ~25
μm in depth and several millimeters long were made. Investigation of
boundaries quality has been carried out with the use of AFM
«Vecco». Possibility of technological formation of profiles and
micro-holes in diamond and quartz substrates with nanometer-scale
boundaries is shown. Experimental results of multilayer dielectric
cover treatment are also presented. Possibility of precise upper layer
(thickness of 70–140 nm) removal is demonstrated. Processes of thin
metal film (60 nm and 350 nm thick) treatment are considered.
Isolation tracks (conductance ~ 10-11 S) 1.6–2.5 μm in width in
conductive metal layers are formed.
Abstract: This paper makes an attempt to solve the problem of
searching and retrieving of similar MRI photos via Internet services
using morphological features which are sourced via the original
image. This study is aiming to be considered as an additional tool of
searching and retrieve methods. Until now the main way of the
searching mechanism is based on the syntactic way using keywords.
The technique it proposes aims to serve the new requirements of
libraries. One of these is the development of computational tools for
the control and preservation of the intellectual property of digital
objects, and especially of digital images. For this purpose, this paper
proposes the use of a serial number extracted by using a previously
tested semantic properties method. This method, with its center being
the multi-layers of a set of arithmetic points, assures the following
two properties: the uniqueness of the final extracted number and the
semantic dependence of this number on the image used as the
method-s input. The major advantage of this method is that it can
control the authentication of a published image or its partial
modification to a reliable degree. Also, it acquires the better of the
known Hash functions that the digital signature schemes use and
produces alphanumeric strings for cases of authentication checking,
and the degree of similarity between an unknown image and an
original image.
Abstract: In this paper, for the first time, a two-dimensional
(2D) analytical drain current model for sub-100 nm multi-layered
gate material engineered trapezoidal recessed channel (MLGMETRC)
MOSFET: a novel design is presented and investigated using
ATLAS and DEVEDIT device simulators, to mitigate the large gate
leakages and increased standby power consumption that arise due to
continued scaling of SiO2-based gate dielectrics. The twodimensional
(2D) analytical model based on solution of Poisson-s
equation in cylindrical coordinates, utilizing the cylindrical
approximation, has been developed which evaluate the surface
potential, electric field, drain current, switching metric: ION/IOFF
ratio and transconductance for the proposed design. A good
agreement between the model predictions and device simulation
results is obtained, verifying the accuracy of the proposed analytical
model.
Abstract: A complex valued neural network is a neural network, which consists of complex valued input and/or weights and/or thresholds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in image and vision processing. In Neural networks, radial basis functions are often used for interpolation in multidimensional space. A Radial Basis function is a function, which has built into it a distance criterion with respect to a centre. Radial basis functions have often been applied in the area of neural networks where they may be used as a replacement for the sigmoid hidden layer transfer characteristic in multi-layer perceptron. This paper aims to present exhaustive results of using RBF units in a complex-valued neural network model that uses the back-propagation algorithm (called 'Complex-BP') for learning. Our experiments results demonstrate the effectiveness of a Radial basis function in a complex valued neural network in image recognition over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error on a neural network model with RBF units. Some inherent properties of this complex back propagation algorithm are also studied and discussed.
Abstract: Conventionally the selection of parameters depends
intensely on the operator-s experience or conservative technological
data provided by the EDM equipment manufacturers that assign
inconsistent machining performance. The parameter settings given by
the manufacturers are only relevant with common steel grades. A
single parameter change influences the process in a complex way.
Hence, the present research proposes artificial neural network (ANN)
models for the prediction of surface roughness on first commenced
Ti-15-3 alloy in electrical discharge machining (EDM) process. The
proposed models use peak current, pulse on time, pulse off time and
servo voltage as input parameters. Multilayer perceptron (MLP) with
three hidden layer feedforward networks are applied. An assessment
is carried out with the models of distinct hidden layer. Training of the
models is performed with data from an extensive series of
experiments utilizing copper electrode as positive polarity. The
predictions based on the above developed models have been verified
with another set of experiments and are found to be in good
agreement with the experimental results. Beside this they can be
exercised as precious tools for the process planning for EDM.
Abstract: Face detection and recognition has many applications
in a variety of fields such as security system, videoconferencing and
identification. Face classification is currently implemented in
software. A hardware implementation allows real-time processing,
but has higher cost and time to-market.
The objective of this work is to implement a classifier based on
neural networks MLP (Multi-layer Perceptron) for face detection.
The MLP is used to classify face and non-face patterns. The systm is
described using C language on a P4 (2.4 Ghz) to extract weight
values. Then a Hardware implementation is achieved using VHDL
based Methodology. We target Xilinx FPGA as the implementation
support.
Abstract: Scheduling algorithms are used in operating systems
to optimize the usage of processors. One of the most efficient
algorithms for scheduling is Multi-Layer Feedback Queue (MLFQ)
algorithm which uses several queues with different quanta. The most
important weakness of this method is the inability to define the
optimized the number of the queues and quantum of each queue. This
weakness has been improved in IMLFQ scheduling algorithm.
Number of the queues and quantum of each queue affect the response
time directly. In this paper, we review the IMLFQ algorithm for
solving these problems and minimizing the response time. In this
algorithm Recurrent Neural Network has been utilized to find both
the number of queues and the optimized quantum of each queue.
Also in order to prevent any probable faults in processes' response
time computation, a new fault tolerant approach has been presented.
In this approach we use combinational software redundancy to
prevent the any probable faults. The experimental results show that
using the IMLFQ algorithm results in better response time in
comparison with other scheduling algorithms also by using fault
tolerant mechanism we improve IMLFQ performance.
Abstract: The Multi-Layered Perceptron (MLP) Neural
networks have been very successful in a number of signal processing
applications. In this work we have studied the possibilities and the
met difficulties in the application of the MLP neural networks for the
prediction of daily solar radiation data. We have used the Polack-Ribière algorithm for training the neural networks. A comparison, in
term of the statistical indicators, with a linear model most used in
literature, is also performed, and the obtained results show that the
neural networks are more efficient and gave the best results.
Abstract: Choosing the right metadata is a critical, as good
information (metadata) attached to an image will facilitate its
visibility from a pile of other images. The image-s value is enhanced
not only by the quality of attached metadata but also by the technique
of the search. This study proposes a technique that is simple but
efficient to predict a single human image from a website using the
basic image data and the embedded metadata of the image-s content
appearing on web pages. The result is very encouraging with the
prediction accuracy of 95%. This technique may become a great
assist to librarians, researchers and many others for automatically and
efficiently identifying a set of human images out of a greater set of
images.
Abstract: In a particular case of behavioural model reduction by ANNs, a validity domain shortening has been found. In mechanics, as in other domains, the notion of validity domain allows the engineer to choose a valid model for a particular analysis or simulation. In the study of mechanical behaviour for a cantilever beam (using linear and non-linear models), Multi-Layer Perceptron (MLP) Backpropagation (BP) networks have been applied as model reduction technique. This reduced model is constructed to be more efficient than the non-reduced model. Within a less extended domain, the ANN reduced model estimates correctly the non-linear response, with a lower computational cost. It has been found that the neural network model is not able to approximate the linear behaviour while it does approximate the non-linear behaviour very well. The details of the case are provided with an example of the cantilever beam behaviour modelling.
Abstract: In this paper we present an adaptive method for image
compression that is based on complexity level of the image. The
basic compressor/de-compressor structure of this method is a multilayer
perceptron artificial neural network. In adaptive approach
different Back-Propagation artificial neural networks are used as
compressor and de-compressor and this is done by dividing the
image into blocks, computing the complexity of each block and then
selecting one network for each block according to its complexity
value. Three complexity measure methods, called Entropy, Activity
and Pattern-based are used to determine the level of complexity in
image blocks and their ability in complexity estimation are evaluated
and compared. In training and evaluation, each image block is
assigned to a network based on its complexity value. Best-SNR is
another alternative in selecting compressor network for image blocks
in evolution phase which chooses one of the trained networks such
that results best SNR in compressing the input image block. In our
evaluations, best results are obtained when overlapping the blocks is
allowed and choosing the networks in compressor is based on the
Best-SNR. In this case, the results demonstrate superiority of this
method comparing with previous similar works and JPEG standard
coding.
Abstract: In the present work, we propose a new technique to
enhance the learning capabilities and reduce the computation
intensity of a competitive learning multi-layered neural network
using the K-means clustering algorithm. The proposed model use
multi-layered network architecture with a back propagation learning
mechanism. The K-means algorithm is first applied to the training
dataset to reduce the amount of samples to be presented to the neural
network, by automatically selecting an optimal set of samples. The
obtained results demonstrate that the proposed technique performs
exceptionally in terms of both accuracy and computation time when
applied to the KDD99 dataset compared to a standard learning
schema that use the full dataset.
Abstract: This paper proposes new algorithms for the computeraided
design and manufacture (CAD/CAM) of 3D woven multi-layer
textile structures. Existing commercial CAD/CAM systems are often
restricted to the design and manufacture of 2D weaves. Those
CAD/CAM systems that do support the design and manufacture of
3D multi-layer weaves are often limited to manual editing of design
paper grids on the computer display and weave retrieval from stored
archives. This complex design activity is time-consuming, tedious
and error-prone and requires considerable experience and skill of a
technical weaver. Recent research reported in the literature has
addressed some of the shortcomings of commercial 3D multi-layer
weave CAD/CAM systems. However, earlier research results have
shown the need for further work on weave specification, weave
generation, yarn path editing and layer binding. Analysis of 3D
multi-layer weaves in this research has led to the design and
development of efficient and robust algorithms for the CAD/CAM of
3D woven multi-layer textile structures. The resulting algorithmically
generated weave designs can be used as a basis for lifting plans that
can be loaded onto looms equipped with electronic shedding
mechanisms for the CAM of 3D woven multi-layer textile structures.
Abstract: In this paper, the modelling and design of artificial neural network architecture for load forecasting purposes is investigated. The primary pre-requisite for power system planning is to arrive at realistic estimates of future demand of power, which is known as Load Forecasting. Short Term Load Forecasting (STLF) helps in determining the economic, reliable and secure operating strategies for power system. The dependence of load on several factors makes the load forecasting a very challenging job. An over estimation of the load may cause premature investment and unnecessary blocking of the capital where as under estimation of load may result in shortage of equipment and circuits. It is always better to plan the system for the load slightly higher than expected one so that no exigency may arise. In this paper, a load-forecasting model is proposed using a multilayer neural network with an appropriately modified back propagation learning algorithm. Once the neural network model is designed and trained, it can forecast the load of the power system 24 hours ahead on daily basis and can also forecast the cumulative load on daily basis. The real load data that is used for the Artificial Neural Network training was taken from LDC, Gujarat Electricity Board, Jambuva, Gujarat, India. The results show that the load forecasting of the ANN model follows the actual load pattern more accurately throughout the forecasted period.
Abstract: Fluid flow and heat transfer of vertical full cone
embedded in porous media is studied in this paper. Nonlinear
differential equation arising from similarity solution of inverted cone
(subjected to wall temperature boundary conditions) embedded in
porous medium is solved using a hybrid neural network- particle
swarm optimization method.
To aim this purpose, a trial solution of the differential equation is
defined as sum of two parts. The first part satisfies the initial/
boundary conditions and does contain an adjustable parameter and
the second part which is constructed so as not to affect the
initial/boundary conditions and involves adjustable parameters (the
weights and biases) for a multi-layer perceptron neural network.
Particle swarm optimization (PSO) is applied to find adjustable
parameters of trial solution (in first and second part). The obtained
solution in comparison with the numerical ones represents a
remarkable accuracy.