Abstract: SVM ( Support Vector Machine ) is a new method in the artificial neural network ( ANN ). In the steel making, how to use computer to predict the end point of BOF accuracy is a great problem. A lot of method and theory have been claimed, but most of the results is not satisfied. Now the hot topic in the BOF end point predicting is to use optical way the predict the end point in the BOF. And we found that there exist some regular in the characteristic curve of the flame from the mouse of pudding. And we can use SVM to predict end point of the BOF, just single spectrum intensity should be required as the input parameter. Moreover, its compatibility for the input space is better than the BP network.
Abstract: A Novel fuzzy neural network combining with support vector learning mechanism called support-vector-based fuzzy neural networks (SVBFNN) is proposed. The SVBFNN combine the capability of minimizing the empirical risk (training error) and expected risk (testing error) of support vector learning in high dimensional data spaces and the efficient human-like reasoning of FNN.
Abstract: Flexible manufacturing system is a system that is able to respond to changed conditions. In general, this flexibility is divided into two key categories and several subcategories. The first category is the so called machine flexibility which enables to make various products by the given machinery. The second category is routing flexibility enabling to execute the same operation by various machines. Flexible manufacturing systems usually consist of three main parts: CNC machine tools, transport system and control system. A higher level of flexible manufacturing systems is represented by the so called intelligent manufacturing systems.
Abstract: Manufacturing tolerancing is intended to determine
the intermediate geometrical and dimensional states of the part
during its manufacturing process. These manufacturing dimensions
also serve to satisfy not only the functional requirements given in
the definition drawing, but also the manufacturing constraints, for
example geometrical defects of the machine, vibration and the
wear of the cutting tool. In this paper, an experimental study on the
influence of the wear of the cutting tool (systematic dispersions) is
explored. This study was carried out on three stages .The first stage
allows machining without elimination of dispersions (random,
systematic) so the tolerances of manufacture according to total
dispersions. In the second stage, the results of the first stage are
filtered in such way to obtain the tolerances according to random
dispersions. Finally, from the two previous stages, the systematic
dispersions are generated. The objective of this study is to model
by the least squares method the error of manufacture based on
systematic dispersion. Finally, an approach of optimization of the
manufacturing tolerances was developed for machining on a CNC
machine tool
Abstract: In this paper a novel method for finding the fault zone
on a Thyristor Controlled Series Capacitor (TCSC) incorporated
transmission line is presented. The method makes use of the Support
Vector Machine (SVM), used in the classification mode to
distinguish between the zones, before or after the TCSC. The use of
Discrete Wavelet Transform is made to prepare the features which
would be given as the input to the SVM. This method was tested on a
400 kV, 50 Hz, 300 Km transmission line and the results were highly
accurate.
Abstract: Pattern recognition is the research area of Artificial
Intelligence that studies the operation and design of systems that
recognize patterns in the data. Important application areas are image
analysis, character recognition, fingerprint classification, speech
analysis, DNA sequence identification, man and machine
diagnostics, person identification and industrial inspection. The
interest in improving the classification systems of data analysis is
independent from the context of applications. In fact, in many
studies it is often the case to have to recognize and to distinguish
groups of various objects, which requires the need for valid
instruments capable to perform this task. The objective of this article
is to show several methodologies of Artificial Intelligence for data
classification applied to biomedical patterns. In particular, this work
deals with the realization of a Computer-Aided Detection system
(CADe) that is able to assist the radiologist in identifying types of
mammary tumor lesions. As an additional biomedical application of
the classification systems, we present a study conducted on blood
samples which shows how these methods may help to distinguish
between carriers of Thalassemia (or Mediterranean Anaemia) and
healthy subjects.
Abstract: This paper presents the use of a semi-classical signal
analysis method that has been developed recently for the analysis of
turbomachinery flow unsteadiness. We will focus on the correlation
between theSemi-Classical Signal Analysis parameters and some
physical parameters in relation with turbomachinery features. To
demonstrate the potential of the proposed approach, a static pressure
signal issued from a rotor/stator interaction of a centrifugal pump is
studied. Several configurations of the pump are compared.
Abstract: Fault-proneness of a software module is the
probability that the module contains faults. To predict faultproneness
of modules different techniques have been proposed which
includes statistical methods, machine learning techniques, neural
network techniques and clustering techniques. The aim of proposed
study is to explore whether metrics available in the early lifecycle
(i.e. requirement metrics), metrics available in the late lifecycle (i.e.
code metrics) and metrics available in the early lifecycle (i.e.
requirement metrics) combined with metrics available in the late
lifecycle (i.e. code metrics) can be used to identify fault prone
modules using Genetic Algorithm technique. This approach has been
tested with real time defect C Programming language datasets of
NASA software projects. The results show that the fusion of
requirement and code metric is the best prediction model for
detecting the faults as compared with commonly used code based
model.
Abstract: The process of wafer fabrication is arguably the most
technologically complex and capital intensive stage in semiconductor
manufacturing. This large-scale discrete-event process is highly reentrant,
and involves hundreds of machines, restrictions, and
processing steps. Therefore, production control of wafer fabrication
facilities (fab), specifically scheduling, is one of the most challenging
problems that this industry faces. Dispatching rules have been
extensively applied to the scheduling problems in semiconductor
manufacturing. Moreover, lot release policies are commonly used in
this manufacturing setting to further improve the performance of such
systems and reduce its inherent variability. In this work, simulation is
used in the scheduling of re-entrant flow shop manufacturing systems
with an application in semiconductor wafer fabrication; where, a
simulation model has been developed for the Intel Five-Machine Six
Step Mini-Fab using the ExtendTM simulation environment. The
Mini-Fab has been selected as it captures the challenges involved in
scheduling the highly re-entrant semiconductor manufacturing lines.
A number of scenarios have been developed and have been used to
evaluate the effect of different dispatching rules and lot release
policies on the selected performance measures. Results of simulation
showed that the performance of the Mini-Fab can be drastically
improved using a combination of dispatching rules and lot release
policy.
Abstract: Serial Analysis of Gene Expression is a powerful
quantification technique for generating cell or tissue gene expression
data. The profile of the gene expression of cell or tissue in several
different states is difficult for biologists to analyze because of the large
number of genes typically involved. However, feature selection in
machine learning can successfully reduce this problem. The method
allows reducing the features (genes) in specific SAGE data, and
determines only relevant genes. In this study, we used a genetic
algorithm to implement feature selection, and evaluate the
classification accuracy of the selected features with the K-nearest
neighbor method. In order to validate the proposed method, we used
two SAGE data sets for testing. The results of this study conclusively
prove that the number of features of the original SAGE data set can be
significantly reduced and higher classification accuracy can be
achieved.
Abstract: A considerable progress has been achieved in transient
stability analysis (TSA) with various FACTS controllers. But, all
these controllers are associated with single transmission line. This
paper is intended to discuss a new approach i.e. a multi-line FACTS
controller which is interline power flow controller (IPFC) for TSA of
a multi-machine power system network. A mathematical model of
IPFC, termed as power injection model (PIM) presented and this
model is incorporated in Newton-Raphson (NR) power flow
algorithm. Then, the reduced admittance matrix of a multi-machine
power system network for a three phase fault without and with IPFC
is obtained which is required to draw the machine swing curves. A
general approach based on L-index has also been discussed to find
the best location of IPFC to reduce the proximity to instability of a
power system. Numerical results are carried out on two test systems
namely, 6-bus and 11-bus systems. A program in MATLAB has
been written to plot the variation of generator rotor angle and speed
difference curves without and with IPFC for TSA and also a simple
approach has been presented to evaluate critical clearing time for test
systems. The results obtained without and with IPFC are compared
and discussed.
Abstract: This paper presents the theoretical background and
the real implementation of an automated computer system to
introduce machine vision in flower, fruit and vegetable processing
for recollection, cutting, packaging, classification, or fumigation
tasks. The considerations and implementation issues presented in this
work can be applied to a wide range of varieties of flowers, fruits and
vegetables, although some of them are especially relevant due to the
great amount of units that are manipulated and processed each year
over the world. The computer vision algorithms developed in this
work are shown in detail, and can be easily extended to other
applications. A special attention is given to the electromagnetic
compatibility in order to avoid noisy images. Furthermore, real
experimentation has been carried out in order to validate the
developed application. In particular, the tests show that the method
has good robustness and high success percentage in the object
characterization.
Abstract: With the turn of this century, many researchers
started showing interest in Embedded Firewall (EF) implementations.
These are not the usual firewalls that are used as checkpoints at network gateways. They are, rather, applied near those hosts that need protection. Hence by using them, individual or grouped network
components can be protected from the inside as well as from external attacks.
This paper presents a study of EF-s, looking at their architecture and problems. A comparative study assesses how practical each kind is. It particularly focuses on the architecture, weak points, and
portability of each kind. A look at their use by different categories of users is also presented.
Abstract: More and more natural disasters are happening every
year: floods, earthquakes, volcanic eruptions, etc. In order to reduce
the risk of possible damages, governments all around the world are
investing into development of Early Warning Systems (EWS) for
environmental applications. The most important task of the EWS is
identification of the onset of critical situations affecting environment
and population, early enough to inform the authorities and general
public. This paper describes an approach for monitoring of flood
protections systems based on machine learning methods. An
Artificial Intelligence (AI) component has been developed for
detection of abnormal dike behaviour. The AI module has been
integrated into an EWS platform of the UrbanFlood project (EU
Seventh Framework Programme) and validated on real-time
measurements from the sensors installed in a dike.
Abstract: This study aims to identify processes, current
situations, and issues of recycling systems for four home appliances,
namely, air conditioners, television receivers, refrigerators, and
washing machines, among e-wastes in China and Japan for
understanding and comparison of their characteristics. In accordance
with results of a literature search, review of information disclosed
online, and questionnaire survey conducted, conclusions of the study
boil down to:
(1)The results show that in Japan most of the home appliances
mentioned above have been collected through home appliance
recycling tickets, resulting in an issue of “requiring some effort" in
treatment and recycling stages, and most plants have contracted out
their e-waste recycling.
(2)It is found out that advantages of the recycling system in Japan
include easiness to monitor concrete data and thorough
environmental friendliness ensured while its disadvantages include
illegal dumping and export. It becomes apparent that advantages of
the recycling system in China include a high reuse rate, low
treatment cost, and fewer illegal dumping while its disadvantages
include less safe reused products, environmental pollution caused by
e-waste treatment, illegal import, and difficulty in obtaining data.
Abstract: During last decades, worldwide researchers dedicated
efforts to develop machine-based seismic Early Warning systems,
aiming at reducing the huge human losses and economic damages.
The elaboration time of seismic waveforms is to be reduced in order
to increase the time interval available for the activation of safety
measures. This paper suggests a Data Mining model able to correctly
and quickly estimate dangerousness of the running seismic event.
Several thousand seismic recordings of Japanese and Italian
earthquakes were analyzed and a model was obtained by means of a
Bayesian Network (BN), which was tested just over the first
recordings of seismic events in order to reduce the decision time and
the test results were very satisfactory.
The model was integrated within an Early Warning System
prototype able to collect and elaborate data from a seismic sensor
network, estimate the dangerousness of the running earthquake and
take the decision of activating the warning promptly.
Abstract: A business case is a proposal for an investment
initiative to satisfy business and functional requirements. The
business case provides the foundation for tactical decision making
and technology risk management. It helps to clarify how the
organization will use its resources in the best way by providing
justification for investment of resources. This paper describes how
simulation was used for business case benefits and return on
investment for the procurement of 8 production machines. With
investment costs of about 4.7 million dollars and annual operating
costs of about 1.3 million, we needed to determine if the machines
would provide enough cost savings and cost avoidance. We
constructed a model of the existing factory environment consisting of
8 machines and subsequently, we conducted average day simulations
with light and heavy volumes to facilitate planning decisions
required to be documented and substantiated in the business case.
Abstract: Hair is a non homogenous complex material which
can be associated with a polymer. It is made up 95% of Keratin.
Hair has a great social significance for human beings. In the High
Middle Ages, for example, long hairs have been reserved for kings
and nobles.
Most common interest in hair is focused on hair growth, hair types
and hair care, but hair is also an important biomaterial which can
vary depending on ethnic origin or on age, hair colour for example
can be a sign of ethnic ancestry or age (dark hair for Asiatic, blond
hair for Caucasian and white hair for old people in general).
In this context, different approaches have been conducted to
determine the differences in mechanical properties and characterize
the fracture topography at the surface of hair depending on its type
and its age.
A tensile testing machine was especially designed to achieve
tensile tests on hair. This device is composed of a microdisplacement
system and a force sensor whose peak load is limited to
3N. The curves and the values extracted from each experiment, allow
us to compare the evolution of the mechanical properties from one
hair to another.
Observations with a Scanning Electron Microscope (SEM) and
with an interferometer were made on different hairs. Thus, it is
possible to access the cuticle state and the fracture topography for
each category.
Abstract: An evolutionary method whose selection and recombination
operations are based on generalization error-bounds of
support vector machine (SVM) can select a subset of potentially
informative genes for SVM classifier very efficiently [7]. In this
paper, we will use the derivative of error-bound (first-order criteria)
to select and recombine gene features in the evolutionary process,
and compare the performance of the derivative of error-bound with
the error-bound itself (zero-order) in the evolutionary process. We
also investigate several error-bounds and their derivatives to compare
the performance, and find the best criteria for gene selection
and classification. We use 7 cancer-related human gene expression
datasets to evaluate the performance of the zero-order and first-order
criteria of error-bounds. Though both criteria have the same strategy
in theoretically, experimental results demonstrate the best criterion
for microarray gene expression data.
Abstract: Optimization of cutting parameters important in precision machining in regards to efficiency and surface integrity of the machined part. Usually productivity and precision in machining is limited by the forces emanating from the cutting process. Due to the inherent varying nature of the workpiece in terms of geometry and material composition, the peak cutting forces vary from point to point during machining process. In order to increase productivity without compromising on machining accuracy, it is important to control these cutting forces. In this paper a fuzzy logic control algorithm is developed that can be applied in the control of peak cutting forces in milling of spherical surfaces using ball end mills. The controller can adaptively vary the feedrate to maintain allowable cutting force on the tool. This control algorithm is implemented in a computer numerical control (CNC) machine. It has been demonstrated that the controller can provide stable machining and improve the performance of the CNC milling process by varying feedrate.