Abstract: This paper provides the design steps of a robust Linear
Matrix Inequality (LMI) based iterative multivariable PID controller
whose duty is to drive a sample power system that comprises a
synchronous generator connected to a large network via a step-up
transformer and a transmission line. The generator is equipped with
two control-loops, namely, the speed/power (governor) and voltage
(exciter). Both loops are lumped in one where the error in the
terminal voltage and output active power represent the controller
inputs and the generator-exciter voltage and governor-valve position
represent its outputs. Multivariable PID is considered here because of
its wide use in the industry, simple structure and easy
implementation. It is also preferred in plants of higher order that
cannot be reduced to lower ones. To improve its robustness to
variation in the controlled variables, H∞-norm of the system transfer
function is used. To show the effectiveness of the controller, divers
tests, namely, step/tracking in the controlled variables, and variation
in plant parameters, are applied. A comparative study between the
proposed controller and a robust H∞ LMI-based output feedback is
given by its robustness to disturbance rejection. From the simulation
results, the iterative multivariable PID shows superiority.
Abstract: In this paper, a novel method for recognition of musical
instruments in a polyphonic music is presented by using an
embedded hidden Markov model (EHMM). EHMM is a doubly
embedded HMM structure where each state of the external HMM
is an independent HMM. The classification is accomplished for
two different internal HMM structures where GMMs are used as
likelihood estimators for the internal HMMs. The results are compared
to those achieved by an artificial neural network with two
hidden layers. Appropriate classification accuracies were achieved
both for solo instrument performance and instrument combinations
which demonstrates that the new approach outperforms the similar
classification methods by means of the dynamic of the signal.
Abstract: Losses reduction initiatives in distribution systems
have been activated due to the increasing cost of supplying
electricity, the shortage in fuel with ever-increasing cost to produce
more power, and the global warming concerns. These initiatives have
been introduced to the utilities in shape of incentives and penalties.
Recently, the electricity distribution companies in Oman have been
incentivized to reduce the distribution technical and non-technical
losses with an equal annual reduction rate for 6 years. In this paper,
different techniques for losses reduction in Mazoon Electricity
Company (MZEC) are addressed. In this company, high numbers of
substation and feeders were found to be non-compliant with the
Distribution System Security Standard (DSSS). Therefore, 33
projects have been suggested to bring non-complying 29 substations
and 28 feeders to meet the planed criteria and to comply with the
DSSS. The largest part of MZEC-s network (South Batinah region)
was modeled by ETAP software package. The model has been
extended to implement the proposed projects and to examine their
effects on losses reduction. Simulation results have shown that the
implementation of these projects leads to a significant improvement
in voltage profile, and reduction in the active and the reactive power
losses. Finally, the economical analysis has revealed that the
implementation of the proposed projects in MZEC leads to an annual
saving of about US$ 5 million.
Abstract: This paper presents an approach for daily optimal operation of distribution networks considering Distributed Generators (DGs). Due to private ownership of DGs, a cost based compensation method is used to encourage DGs in active and reactive power generation. The objective function is summation of electrical energy generated by DGs and substation bus (main bus) in the next day. A genetic algorithm is used to solve the optimal operation problem. The approach is tested on an IEEE34 buses distribution feeder.
Abstract: This paper presents the feasibility study of CO2 sequestration from the sources to the sinks in the prospective of Italian Industries. CO2 produced at these sources captured, compressed to supercritical pressures, transported via pipelines and stored in underground geologic formations such as depleted oil and natural gas reservoirs, un-minable coal seams and deep saline aquifers. In this work, we present the optimized pipeline infrastructure for the CO2 with appropriate constraints to find lower cost system by the use of nonlinear optimization software LINGO 11.0. This study was conducted on CO2 transportation complex network of Italian Industries, to find minimum cost network for transporting the CO2 from sources to the sinks.
Abstract: In this paper, low end Digital Signal Processors (DSPs)
are applied to accelerate integer neural networks. The use of DSPs
to accelerate neural networks has been a topic of study for some
time, and has demonstrated significant performance improvements.
Recently, work has been done on integer only neural networks, which
greatly reduces hardware requirements, and thus allows for cheaper
hardware implementation. DSPs with Arithmetic Logic Units (ALUs)
that support floating or fixed point arithmetic are generally more
expensive than their integer only counterparts due to increased circuit
complexity. However if the need for floating or fixed point math
operation can be removed, then simpler, lower cost DSPs can be
used. To achieve this, an integer only neural network is created in
this paper, which is then accelerated by using DSP instructions to
improve performance.
Abstract: An Artificial Neural Network based modeling
technique has been used to study the influence of different
combinations of meteorological parameters on evaporation from a
reservoir. The data set used is taken from an earlier reported study.
Several input combination were tried so as to find out the importance
of different input parameters in predicting the evaporation. The
prediction accuracy of Artificial Neural Network has also been
compared with the accuracy of linear regression for predicting
evaporation. The comparison demonstrated superior performance of
Artificial Neural Network over linear regression approach. The
findings of the study also revealed the requirement of all input
parameters considered together, instead of individual parameters
taken one at a time as reported in earlier studies, in predicting the
evaporation. The highest correlation coefficient (0.960) along with
lowest root mean square error (0.865) was obtained with the input
combination of air temperature, wind speed, sunshine hours and
mean relative humidity. A graph between the actual and predicted
values of evaporation suggests that most of the values lie within a
scatter of ±15% with all input parameters. The findings of this study
suggest the usefulness of ANN technique in predicting the
evaporation losses from reservoirs.
Abstract: An economic operation scheduling problem of a
hydro-thermal power generation system has been properly solved by
the proposed multipath adaptive tabu search algorithm (MATS). Four
reservoirs with their own hydro plants and another one thermal plant
are integrated to be a studied system used to formulate the objective
function under complicated constraints, eg water managements,
power balance and thermal generator limits. MATS with four subsearch
units (ATSs) and two stages of discarding mechanism (DM),
has been setting and trying to solve the problem through 25 trials
under function evaluation criterion. It is shown that MATS can
provide superior results with respect to single ATS and other
previous methods, genetic algorithms (GA) and differential evolution
(DE).
Abstract: Intelligent deep-drawing is an instrumental research field in sheet metal forming. A set of 28 different experimental data have been employed in this paper, investigating the roles of die radius, punch radius, friction coefficients and drawing ratios for axisymmetric workpieces deep drawing. This paper focuses an evolutionary neural network, specifically, error back propagation in collaboration with genetic algorithm. The neural network encompasses a number of different functional nodes defined through the established principles. The input parameters, i.e., punch radii, die radii, friction coefficients and drawing ratios are set to the network; thereafter, the material outputs at two critical points are accurately calculated. The output of the network is used to establish the best parameters leading to the most uniform thickness in the product via the genetic algorithm. This research achieved satisfactory results based on demonstration of neural networks.
Abstract: In this paper, we first consider the quality of service
problems in heterogeneous wireless networks for sending the video
data, which their problem of being real-time is pronounced. At last,
we present a method for ensuring the end-to-end quality of service at
application layer level for adaptable sending of the video data at
heterogeneous wireless networks. To do this, mechanism in different
layers has been used. We have used the stop mechanism, the
adaptation mechanism and the graceful degrade at the application
layer, the multi-level congestion feedback mechanism in the network
layer and connection cutting off decision mechanism in the link
layer. At the end, the presented method and the achieved
improvement is simulated and presented in the NS-2 software.
Abstract: Advancement in Artificial Intelligence has lead to the
developments of various “smart" devices. Character recognition
device is one of such smart devices that acquire partial human
intelligence with the ability to capture and recognize various
characters in different languages. Firstly multiscale neural training
with modifications in the input training vectors is adopted in this
paper to acquire its advantage in training higher resolution character
images. Secondly selective thresholding using minimum distance
technique is proposed to be used to increase the level of accuracy of
character recognition. A simulator program (a GUI) is designed in
such a way that the characters can be located on any spot on the
blank paper in which the characters are written. The results show that
such methods with moderate level of training epochs can produce
accuracies of at least 85% and more for handwritten upper case
English characters and numerals.
Abstract: This paper aims to present the reviews of the
application of neural network in shunt active power filter (SAPF).
From the review, three out of four components of SAPF structure,
which are harmonic detection component, compensating current
control, and DC bus voltage control, have been adopted some of
neural network architecture as part of its component or even
substitution. The objectives of most papers in using neural network in
SAPF are to increase the efficiency, stability, accuracy, robustness,
tracking ability of the systems of each component. Moreover,
minimizing unneeded signal due to the distortion is the ultimate goal
in applying neural network to the SAPF. The most famous
architecture of neural network in SAPF applications are ADALINE
and Backpropagation (BP).
Abstract: With the exponential growth of networked system and
application such as eCommerce, the demand for effective internet
security is increasing. Cryptology is the science and study of systems
for secret communication. It consists of two complementary fields of
study: cryptography and cryptanalysis. The application of genetic
algorithms in the cryptanalysis of knapsack ciphers is suggested by
Spillman [7]. In order to improve the efficiency of genetic algorithm
attack on knapsack cipher, the previously published attack was
enhanced and re-implemented with variation of initial assumptions
and results are compared with Spillman results. The experimental
result of research indicates that the efficiency of genetic algorithm
attack on knapsack cipher can be improved with variation of initial
assumption.
Abstract: This paper solves the environmental/ economic dispatch
power system problem using the Non-dominated Sorting Genetic
Algorithm-II (NSGA-II) and its hybrid with a Convergence Accelerator
Operator (CAO), called the NSGA-II/CAO. These multiobjective
evolutionary algorithms were applied to the standard IEEE 30-bus
six-generator test system. Several optimization runs were carried out
on different cases of problem complexity. Different quality measure
which compare the performance of the two solution techniques were
considered. The results demonstrated that the inclusion of the CAO
in the original NSGA-II improves its convergence while preserving
the diversity properties of the solution set.
Abstract: LABVIEW is a graphical programming language that has its roots in automation control and data acquisition. In this paper we have utilized this platform to provide a powerful toolset for process identification and control of nonlinear systems based on artificial neural networks (ANN). This tool has been applied to the monitoring and control of a lab-scale distillation column DELTALAB DC-SP. The proposed control scheme offers high speed of response for changes in set points and null stationary error for dual composition control and shows robustness in presence of externally imposed disturbance.
Abstract: Collaborative working environments for distance
education can be considered as a more generic form of contemporary
remote labs. At present, the majority of existing real laboratories are
not constructed to allow the involved participants to collaborate in
real time. To make this revolutionary learning environment possible
we must allow the different users to carry out an experiment
simultaneously. In recent times, multi-user environments are
successfully applied in many applications such as air traffic control
systems, team-oriented military systems, chat-text tools, multi-player
games etc. Thus, understanding the ideas and techniques behind these
systems could be of great importance in the contribution of ideas to
our e-learning environment for collaborative working. In this
investigation, collaborative working environments from theoretical
and practical perspectives are considered in order to build an
effective collaborative real laboratory, which allows two students or
more to conduct remote experiments at the same time as a team. In
order to achieve this goal, we have implemented distributed system
architecture, enabling students to obtain an automated help by either
a human tutor or a rule-based e-tutor.
Abstract: As the Internet continues to grow at a rapid pace as
the primary medium for communications and commerce and as
telecommunication networks and systems continue to expand their
global reach, digital information has become the most popular and
important information resource and our dependence upon the
underlying cyber infrastructure has been increasing significantly.
Unfortunately, as our dependency has grown, so has the threat to the
cyber infrastructure from spammers, attackers and criminal
enterprises. In this paper, we propose a new machine learning based
network intrusion detection framework for cyber security. The
detection process of the framework consists of two stages: model
construction and intrusion detection. In the model construction stage,
a semi-supervised machine learning algorithm is applied to a
collected set of network audit data to generate a profile of normal
network behavior and in the intrusion detection stage, input network
events are analyzed and compared with the patterns gathered in the
profile, and some of them are then flagged as anomalies should these
events are sufficiently far from the expected normal behavior. The
proposed framework is particularly applicable to the situations where
there is only a small amount of labeled network training data
available, which is very typical in real world network environments.
Abstract: Quality of Service (QoS) Routing aims to find path between source and destination satisfying the QoS requirements which efficiently using the network resources and underlying routing algorithm and to fmd low-cost paths that satisfy given QoS constraints. One of the key issues in providing end-to-end QoS guarantees in packet networks is determining feasible path that satisfies a number of QoS constraints. We present a Optimized Multi- Constrained Routing (OMCR) algorithm for the computation of constrained paths for QoS routing in computer networks. OMCR applies distance vector to construct a shortest path for each destination with reference to a given optimization metric, from which a set of feasible paths are derived at each node. OMCR is able to fmd feasible paths as well as optimize the utilization of network resources. OMCR operates with the hop-by-hop, connectionless routing model in IP Internet and does not create any loops while fmding the feasible paths. Nodes running OMCR not necessarily maintaining global view of network state such as topology, resource information and routing updates are sent only to neighboring nodes whereas its counterpart link-state routing method depend on complete network state for constrained path computation and that incurs excessive communication overhead.
Abstract: As the enormous amount of on-line text grows on the
World-Wide Web, the development of methods for automatically
summarizing this text becomes more important. The primary goal of
this research is to create an efficient tool that is able to summarize
large documents automatically. We propose an Evolving
connectionist System that is adaptive, incremental learning and
knowledge representation system that evolves its structure and
functionality. In this paper, we propose a novel approach for Part of
Speech disambiguation using a recurrent neural network, a paradigm
capable of dealing with sequential data. We observed that
connectionist approach to text summarization has a natural way of
learning grammatical structures through experience. Experimental
results show that our approach achieves acceptable performance.
Abstract: The third phase of web means semantic web requires many web pages which are annotated with metadata. Thus, a crucial question is where to acquire these metadata. In this paper we propose our approach, a semi-automatic method to annotate the texts of documents and web pages and employs with a quite comprehensive knowledge base to categorize instances with regard to ontology. The approach is evaluated against the manual annotations and one of the most popular annotation tools which works the same as our tool. The approach is implemented in .net framework and uses the WordNet for knowledge base, an annotation tool for the Semantic Web.