Abstract: The objective of this paper is to propose an adaptive multi threshold for image segmentation precisely in object detection. Due to the different types of license plates being used, the requirement of an automatic LPR is rather different for each country. The proposed technique is applied on Malaysian LPR application. It is based on Multi Layer Perceptron trained by back propagation. The proposed adaptive threshold is introduced to find the optimum threshold values. The technique relies on the peak value from the graph of the number object versus specific range of threshold values. The proposed approach has improved the overall performance compared to current optimal threshold techniques. Further improvement on this method is in progress to accommodate real time system specification.
Abstract: Industrial radiography is a famous technique for the identification and evaluation of discontinuities, or defects, such as cracks, porosity and foreign inclusions found in welded joints. Although this technique has been well developed, improving both the inspection process and operating time, it does suffer from several drawbacks. The poor quality of radiographic images is due to the physical nature of radiography as well as small size of the defects and their poor orientation relatively to the size and thickness of the evaluated parts. Digital image processing techniques allow the interpretation of the image to be automated, avoiding the presence of human operators making the inspection system more reliable, reproducible and faster. This paper describes our attempt to develop and implement digital image processing algorithms for the purpose of automatic defect detection in radiographic images. Because of the complex nature of the considered images, and in order that the detected defect region represents the most accurately possible the real defect, the choice of global and local preprocessing and segmentation methods must be appropriated.
Abstract: Segmentation techniques based on Active Contour
Models have been strongly benefited from the use of prior information
during their evolution. Shape prior information is captured from
a training set and is introduced in the optimization procedure to
restrict the evolution into allowable shapes. In this way, the evolution
converges onto regions even with weak boundaries. Although
significant effort has been devoted on different ways of capturing
and analyzing prior information, very little thought has been devoted
on the way of combining image information with prior information.
This paper focuses on a more natural way of incorporating the
prior information in the level set framework. For proof of concept
the method is applied on hippocampus segmentation in T1-MR
images. Hippocampus segmentation is a very challenging task, due
to the multivariate surrounding region and the missing boundary
with the neighboring amygdala, whose intensities are identical. The
proposed method, mimics the human segmentation way and thus
shows enhancements in the segmentation accuracy.
Abstract: The main goal of the present work is to decrease the
computational burden for optimum design of steel frames with
frequency constraints using a new type of neural networks called
Wavelet Neural Network. It is contested to train a suitable neural
network for frequency approximation work as the analysis program.
The combination of wavelet theory and Neural Networks (NN)
has lead to the development of wavelet neural networks.
Wavelet neural networks are feed-forward networks using
wavelet as activation function. Wavelets are mathematical
functions within suitable inner parameters, which help them to
approximate arbitrary functions. WNN was used to predict the
frequency of the structures. In WNN a RAtional function with
Second order Poles (RASP) wavelet was used as a transfer
function. It is shown that the convergence speed was faster
than other neural networks. Also comparisons of WNN with
the embedded Artificial Neural Network (ANN) and with
approximate techniques and also with analytical solutions are
available in the literature.
Abstract: This paper presents a computational methodology
based on matrix operations for a computer based solution to the
problem of performance analysis of software reliability models
(SRMs). A set of seven comparison criteria have been formulated to
rank various non-homogenous Poisson process software reliability
models proposed during the past 30 years to estimate software
reliability measures such as the number of remaining faults, software
failure rate, and software reliability. Selection of optimal SRM for
use in a particular case has been an area of interest for researchers in
the field of software reliability. Tools and techniques for software
reliability model selection found in the literature cannot be used with
high level of confidence as they use a limited number of model
selection criteria. A real data set of middle size software project from
published papers has been used for demonstration of matrix method.
The result of this study will be a ranking of SRMs based on the
Permanent value of the criteria matrix formed for each model based
on the comparison criteria. The software reliability model with
highest value of the Permanent is ranked at number – 1 and so on.
Abstract: Most routing protocols (DSR, AODV etc.) that have
been designed for wireless adhoc networks incorporate the broadcasting
operation in their route discovery scheme. Probabilistic broadcasting
techniques have been developed to optimize the broadcast operation
which is otherwise very expensive in terms of the redundancy
and the traffic it generates. In this paper we have explored percolation
theory to gain a different perspective on probabilistic broadcasting
schemes which have been actively researched in the recent years.
This theory has helped us estimate the value of broadcast probability
in a wireless adhoc network as a function of the size of the network.
We also show that, operating at those optimal values of broadcast
probability there is at least 25-30% reduction in packet regeneration
during successful broadcasting.
Abstract: The purpose of this study is to present a non invasive
method for the marginal adaptation evaluation in class V composite
restorations. Standardized class V cavities, prepared in human
extracted teeth, were filled with Premise (Kerr) composite. The
specimens were thermo cycled. The interfaces were examined by
Optical Coherence Tomography method (OCT) combined with the
confocal microscopy and fluorescence. The optical configuration
uses two single mode directional couplers with a superluminiscent
diode as the source at 1300 nm. The scanning procedure is similar to
that used in any confocal microscope, where the fast scanning is enface
(line rate) and the depth scanning is much slower (at the frame
rate). Gaps at the interfaces as well as inside the composite resin
materials were identified. OCT has numerous advantages which
justify its use in vivo as well as in vitro in comparison with
conventional techniques.
Abstract: Corporate credit rating prediction using statistical and
artificial intelligence (AI) techniques has been one of the attractive
research topics in the literature. In recent years, multiclass
classification models such as artificial neural network (ANN) or
multiclass support vector machine (MSVM) have become a very
appealing machine learning approaches due to their good
performance. However, most of them have only focused on classifying
samples into nominal categories, thus the unique characteristic of the
credit rating - ordinality - has been seldom considered in their
approaches. This study proposes new types of ANN and MSVM
classifiers, which are named OMANN and OMSVM respectively.
OMANN and OMSVM are designed to extend binary ANN or SVM
classifiers by applying ordinal pairwise partitioning (OPP) strategy.
These models can handle ordinal multiple classes efficiently and
effectively. To validate the usefulness of these two models, we applied
them to the real-world bond rating case. We compared the results of
our models to those of conventional approaches. The experimental
results showed that our proposed models improve classification
accuracy in comparison to typical multiclass classification techniques
with the reduced computation resource.
Abstract: The response surface methodology (RSM) is a
collection of mathematical and statistical techniques useful in the
modeling and analysis of problems in which the dependent variable
receives the influence of several independent variables, in order to
determine which are the conditions under which should operate these
variables to optimize a production process. The RSM estimated a
regression model of first order, and sets the search direction using the
method of maximum / minimum slope up / down MMS U/D.
However, this method selects the step size intuitively, which can
affect the efficiency of the RSM. This paper assesses how the step
size affects the efficiency of this methodology. The numerical
examples are carried out through Monte Carlo experiments,
evaluating three response variables: efficiency gain function, the
optimum distance and the number of iterations. The results in the
simulation experiments showed that in response variables efficiency
and gain function at the optimum distance were not affected by the
step size, while the number of iterations is found that the efficiency if
it is affected by the size of the step and function type of test used.
Abstract: Within the domain of Systems Engineering the need
to perform property aggregation to understand, analyze and manage
complex systems is unequivocal. This can be seen in numerous
domains such as capability analysis, Mission Essential Competencies
(MEC) and Critical Design Features (CDF). Furthermore, the need
to consider uncertainty propagation as well as the sensitivity of
related properties within such analysis is equally as important when
determining a set of critical properties within such a system.
This paper describes this property breakdown in a number of
domains within Systems Engineering and, within the area of CDFs,
emphasizes the importance of uncertainty analysis. As part of this, a
section of the paper describes possible techniques which may be used
within uncertainty propagation and in conclusion an example is
described utilizing one of the techniques for property and uncertainty
aggregation within an aircraft system to aid the determination of
Critical Design Features.
Abstract: Octree compression techniques have been used
for several years for compressing large three dimensional data
sets into homogeneous regions. This compression technique
is ideally suited to datasets which have similar values in
clusters. Oil engineers represent reservoirs as a three dimensional
grid where hydrocarbons occur naturally in clusters. This
research looks at the efficiency of storing these grids using
octree compression techniques where grid cells are broken
into active and inactive regions. Initial experiments yielded
high compression ratios as only active leaf nodes and their
ancestor, header nodes are stored as a bitstream to file on
disk. Savings in computational time and memory were possible
at decompression, as only active leaf nodes are sent to the
graphics card eliminating the need of reconstructing the original
matrix. This results in a more compact vertex table, which can
be loaded into the graphics card quicker and generating shorter
refresh delay times.
Abstract: The paper presents the potential of fuzzy logic (FL-I)
and neural network techniques (ANN-I) for predicting the
compressive strength, for SCC mixtures. Six input parameters that is
contents of cement, sand, coarse aggregate, fly ash, superplasticizer
percentage and water-to-binder ratio and an output parameter i.e. 28-
day compressive strength for ANN-I and FL-I are used for modeling.
The fuzzy logic model showed better performance than neural
network model.
Abstract: This paper presents three models which enable the
customisation of Universal Description, Discovery and Integration
(UDDI) query results, based on some pre-defined and/or real-time
changing parameters. These proposed models detail the requirements,
design and techniques which make ranking of Web service discovery
results from a service registry possible. Our contribution is two fold:
First, we present an extension to the UDDI inquiry capabilities. This
enables a private UDDI registry owner to customise or rank the query
results, based on its business requirements. Second, our proposal
utilises existing technologies and standards which require minimal
changes to existing UDDI interfaces or its data structures. We believe
these models will serve as valuable reference for enhancing the
service discovery methods within a private UDDI registry
environment.
Abstract: A trend in agent community or enterprises is that they are shifting from closed to open architectures composed of a large number of autonomous agents. One of its implications could be that interface agent framework is getting more important in multi-agent system (MAS); so that systems constructed for different application domains could share a common understanding in human computer interface (HCI) methods, as well as human-agent and agent-agent interfaces. However, interface agent framework usually receives less attention than other aspects of MAS. In this paper, we will propose an interface web agent framework which is based on our former project called WAF and a Distributed HCI template. A group of new functionalities and implications will be discussed, such as web agent presentation, off-line agent reference, reconfigurable activation map of agents, etc. Their enabling techniques and current standards (e.g. existing ontological framework) are also suggested and shown by examples from our own implementation in WAF.
Abstract: Self-Excited Induction Generator (SEIG) builds up voltage while it enters in its magnetic saturation region. Due to non-linear magnetic characteristics, the performance analysis of SEIG involves cumbersome mathematical computations. The dependence of air-gap voltage on saturated magnetizing reactance can only be established at rated frequency by conducting a laboratory test commonly known as synchronous run test. But, there is no laboratory method to determine saturated magnetizing reactance and air-gap voltage of SEIG at varying speed, terminal capacitance and other loading conditions. For overall analysis of SEIG, prior information of magnetizing reactance, generated frequency and air-gap voltage is essentially required. Thus, analytical methods are the only alternative to determine these variables. Non-existence of direct mathematical relationship of these variables for different terminal conditions has forced the researchers to evolve new computational techniques. Artificial Neural Networks (ANNs) are very useful for solution of such complex problems, as they do not require any a priori information about the system. In this paper, an attempt is made to use cascaded neural networks to first determine the generated frequency and magnetizing reactance with varying terminal conditions and then air-gap voltage of SEIG. The results obtained from the ANN model are used to evaluate the overall performance of SEIG and are found to be in good agreement with experimental results. Hence, it is concluded that analysis of SEIG can be carried out effectively using ANNs.
Abstract: This paper presents a new approach using Combined Artificial Neural Network (CANN) module for daily peak load forecasting. Five different computational techniques –Constrained method, Unconstrained method, Evolutionary Programming (EP), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) – have been used to identify the CANN module for peak load forecasting. In this paper, a set of neural networks has been trained with different architecture and training parameters. The networks are trained and tested for the actual load data of Chennai city (India). A set of better trained conventional ANNs are selected to develop a CANN module using different algorithms instead of using one best conventional ANN. Obtained results using CANN module confirm its validity.
Abstract: Directional over current relays (DOCR) are commonly used in power system protection as a primary protection in distribution and sub-transmission electrical systems and as a secondary protection in transmission systems. Coordination of protective relays is necessary to obtain selective tripping. In this paper, an approach for efficiency reduction of DOCRs nonlinear optimum coordination (OC) is proposed. This was achieved by modifying the objective function and relaxing several constraints depending on the four constraints classification, non-valid, redundant, pre-obtained and valid constraints. According to this classification, the far end fault effect on the objective function and constraints, and in consequently on relay operating time, was studied. The study was carried out, firstly by taking into account the near-end and far-end faults in DOCRs coordination problem formulation; and then faults very close to the primary relays (nearend faults). The optimal coordination (OC) was achieved by simultaneously optimizing all variables (TDS and Ip) in nonlinear environment by using of Genetic algorithm nonlinear programming techniques. The results application of the above two approaches on 6-bus and 26-bus system verify that the far-end faults consideration on OC problem formulation don-t lose the optimality.
Abstract: The evolution of technology and construction techniques has enabled the upgrading of transport networks. In particular, the high-speed rail networks allow convoys to peak at above 300 km/h. These structures, however, often significantly impact the surrounding environment. Among the effects of greater importance are the ones provoked by the soundwave connected to train transit. The wave propagation affects the quality of life in areas surrounding the tracks, often for several hundred metres. There are substantial damages to properties (buildings and land), in terms of market depreciation. The present study, integrating expertise in acoustics, computering and evaluation fields, outlines a useful model to select project paths so as to minimize the noise impact and reduce the causes of possible litigation. It also facilitates the rational selection of initiatives to contain the environmental damage to the already existing railway tracks. The research is developed with reference to the Italian regulatory framework (usually more stringent than European and international standards) and refers to a case study concerning the high speed network in Italy.
Abstract: The dynamic or complex modulus test is considered
to be a mechanistically based laboratory test to reliably characterize
the strength and load-resistance of Hot-Mix Asphalt (HMA) mixes
used in the construction of roads. The most common observation is
that the data collected from these tests are often noisy and somewhat
non-sinusoidal. This hampers accurate analysis of the data to obtain
engineering insight. The goal of the work presented in this paper is to
develop and compare automated evolutionary computational
techniques to filter test noise in the collection of data for the HMA
complex modulus test. The results showed that the Covariance
Matrix Adaptation-Evolutionary Strategy (CMA-ES) approach is
computationally efficient for filtering data obtained from the HMA
complex modulus test.
Abstract: Schema matching plays a key role in many different
applications, such as schema integration, data integration, data
warehousing, data transformation, E-commerce, peer-to-peer data
management, ontology matching and integration, semantic Web,
semantic query processing, etc. Manual matching is expensive and
error-prone, so it is therefore important to develop techniques to
automate the schema matching process. In this paper, we present a
solution for XML schema automated matching problem which
produces semantic mappings between corresponding schema
elements of given source and target schemas. This solution
contributed in solving more comprehensively and efficiently XML
schema automated matching problem. Our solution based on
combining linguistic similarity, data type compatibility and structural
similarity of XML schema elements. After describing our solution,
we present experimental results that demonstrate the effectiveness of
this approach.