2018-11-16T19:57:39Z
http://ijste.shirazu.ac.ir/?_action=export&rf=summon&issue=254
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Robust segmentation of medical images using competitive hopfield neural network as a clustering tool
This paper presents the application of competitive Hopfield neural network (CHNN) for medical images segmentation. Our proposed approach consists of two steps: 1) translating segmentation of the given medical image into an optimization problem, and 2) solving this problem by a version of Hopfield network known as CHNN. Segmentation is considered as a clustering problem and its validity criterion is based on both intraset distance (<em>IAD</em>) and interset distance (<em>IED</em>). The algorithm proposed in this paper is based on gray level features only. This leads to near optimal solutions if both <em>IAD</em> and <em>IED</em> are considered at the same time. If only one of these distances is considered, the result of segmentation process by CHNN will be far from optimal solution and incorrect even for very simple cases. Furthermore, sometimes the algorithm receives at unacceptable states. Both these problems may be solved by contributing both <em>IAD</em> and <em>IED</em>distances in the segmentation (optimization) process. The performance of the proposed algorithm is tested on both phantom and real medical images. The promising results and the robustness of algorithm to system noises show near optimal solutions.
Medical image segmentation
competitive Hopfield neural network
interest and intraset distances
clustering
2013
02
17
427
439
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Adaptive control of an induction rotor-flux oriented
reference frame induction motor drive
In this paper, simultaneous estimation of the rotor speed and time constant estimation for a voltage source inverter–fed induction motor drive is discussed. Application of the Model Reference Adaptive System (MRAS) on the vector controlling of an induction motor drive in the rotor-flux-oriented reference frame is examined. Furthermore, to eliminate the offset error caused by the change in the stator resistance, a fuzzy resistance is also designed.
vector control
Induction motor
adaptive system
2013
02
17
441
452
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Design of neuro fuzzy fault tolerant control using an adaptive observer
There is a growing acceptance that general purpose parallel computing requires the use of a scalable shared memory environment. The Cray T3D, IBM SP2 and Intel Paragon message passing machines support a scalable interconnect for up to 100´s or 1000´s of processors, with linear increases in bisection bandwidth as the number of processors grow. Supporting a shared address space on these machines results in a two-level memory hierarchy, in which data are either local or shared across the machine. The next few years will see a trend towards cache coherent multiprocessors, using the techniques employed by machines such as the KSR (cach-only memory) and the DASH (distributed directories). This will simplify the programming model by processoring a single level memory hierarchy. This paper describes a highly scalable caching technique, which is targeted at a <em>weakly</em> <em>coherent</em> form of shared memory, supported by the WPRAM computational model. (A processor wishing to read newly written shared data must explicitly synchronize in some way with the writer of that data). The example provides supports coherency for barrier synchronisation operation, but can be extended to other forms. A case study using the simplex method for linear programming is given. Results are based on a simulation of a scalable distributed memory machine
Computational models
caching
weak coherency
parallel algorithms
2013
02
17
543
554
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Predictive control of ac electric arc furnace and its stability analysis
An active power filter with dynamic control method is used for harmonic elimination and power factor correction of an Electric Arc Furnace (EAF). This new control technique is very suitable for suppressing harmonics of nonlinear loads. In addition, other parameters such as the power factor can also be controlled. A nonlinear model of EAF and its Box-Jenkins model are used and compared. These models are parameterized by actual field data. The stability of the entire system is analyzed by using “Stable Equilibrium Area Existence” lemma.
Electric arc furnace
active filter
predictive control
Stability
2013
02
17
463
474
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Leveling and gyrocompassing of stable platforms using neural networks
This paper presents the application of neural networks for the adaptive leveling and gyrocompassing of stable platforms. The stable platform is a three input and two output nonlinear plant, and the control of its error dynamics (leveling) is of vital importance for the proper operation of the inertial navigation systems of aircraft. Also, another important pre-flight step in the inertial navigation system using the stable platform is gyrocompassing. Gyrocompassing provides the navigation system with the wander angle, which is the angle between the Y-axis of the stable platform and true north.
In this paper, neural networks are employed to identify the dynamics of the platform and to level it, based on the identified neural model; gyrocompassing is also performed using an inverse neural identification of the stable platform. In order to show the effectiveness of the proposed neural adaptive controller for platform leveling and gyrocompassing, the results of practical leveling tests performed on an inertial navigation unit of a fighter aircraft and simulation results for gyrocompassing are presented.
Leveling
gyrocompassing
Neural Networks
stable platform
inertial navigation
2013
02
17
475
482
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
H¥PSS DESIGN FOR MULTI-MACHINE POWER SYSTEM
Decentralized control strategy in a multi-machine power system reduces the complexity involved in control design and analysis. Problems arise when the effect of the external system on the local system is no longer negligible. In this paper a well-defined and systematic methodology based on H<sub>¥</sub> optimal control theory is presented to deal with this problem, without involving any detailed dynamics of the external system. Simulation results are also presented to evaluate the proposed approach
Power system stabilizer (PSS)
decentralized control
H¥ optimization
2013
02
17
483
497
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Analysis of slot-coupled, ridged-circular disk microstrip antenna element using the cavity model
A theoretical analysis of a multilayered ridged-circular patch microstrip antenna element excited by a rectangular slot using the cavity model together with an eigenvector expansion, is presented. The approach is based on conserving the reaction at the coupling slot and the ridged positions. The theoretical results are compared with the available experimental results.
Aperture-coupled
cavity model
microstrip antenna
resonance frequency
ridged circular patch
characteristic equation
2013
02
17
499
508
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Robust H¥ control of uncertain nonlinear time-varing systems via state feedback
This paper considers the robust control problem for an affine nonlinear time-varing system with gain bounded uncertainty. We address the problem of designing a state feedback controller such that -gain of the mapping from the exogenous input to the controlled output is less than or equal to a prescribed number g. It is shown that a state feedback control law can be found from a smooth solution of a “scaled” Hamilton-Jacobi-Isaacs inequality
Robust H¥control
nonlinear time-varing systems
2013
02
17
509
513
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
New classes of learning automata based schemes for adaptation of backpropagation algorithm parameters
One popular learning algorithm for feedforward neural networks is the back-propagation (BP) algorithm which includes parameters: learning rate (), momentum factor (a) and steepness parameter (l). The appropriate selections of these parameters have a large effect on the convergence of the algorithm. Many techniques that adaptively adjust these parameters have been developed to increase speed of convergence. In this paper, we shall present several classes of learning automata based solutions to the problem of adaptation of BP algorithm parameters. By interconnection of learning automata to the feedforward neural networks, we use learning automata schemes for adjusting the parameters , a, and l based on the observation of random response of the neural networks. One of the important aspects of proposed scheme is its ability to escape from local minima with high possibility during the training period. The feasibility of the proposed methods are shown through the simulations on several problems.
Neural Network
back-propagation
fixed structure learning automata
steepness parameter
2013
02
17
515
532
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Inadequacies in finite difference solution of magnetostatic problems
This paper investigates the reason behind the low magnetic field computation in cylindrical coordinates using finite difference method, when boundary conditions of the third or fourth kind are used. The same field computation has also been performed using the finite element method but this problem did not occur. It thus, presents a technique to overcome the problem of low magnetic field calculation using finite difference method. The results obtained by the new technique are in close agreement with the finite element method as well as the analytical solution. Finally, an analysis of the possible source of error in modeling magnetostatic boundary conditions in finite difference formulation of vector Poisson or Laplace equation in cylindrical coordinates is performed.
Magnetostatics
magnetic field computation
numerical methods in electromagnetic
2013
02
17
533
541
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Scalable caching techniques for a weakly coherent memory
There is a growing acceptance that general purpose parallel computing requires the use of a scalable shared memory environment. The Cray T3D, IBM SP2 and Intel Paragon message passing machines support a scalable interconnect for up to 100´s or 1000´s of processors, with linear increases in bisection bandwidth as the number of processors grow. Supporting a shared address space on these machines results in a two-level memory hierarchy, in which data are either local or shared across the machine. The next few years will see a trend towards cache coherent multiprocessors, using the techniques employed by machines such as the KSR (cach-only memory) and the DASH (distributed directories). This will simplify the programming model by processoring a single level memory hierarchy. This paper describes a highly scalable caching technique, which is targeted at a <em>weakly</em> <em>coherent</em> form of shared memory, supported by the WPRAM computational model. (A processor wishing to read newly written shared data must explicitly synchronize in some way with the writer of that data). The example provides supports coherency for barrier synchronisation operation, but can be extended to other forms. A case study using the simplex method for linear programming is given. Results are based on a simulation of a scalable distributed memory machine
Computational models
caching
weak coherency
parallel algorithms
2013
02
17
543
544
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
A model for physical suitability evaluation of kor and sivand subbasin
Integrating a Geographic Information System (GIS) with an expert system can overcome the deficiencies of each system. This paper illustrates the integration of a GIS with an expert system in order to find the suitability rating of seven crops (maize, cotton, barley, soybean, tobacco, wheat, and rice) for the Kor and Sivand Sub-basin. Although GIS can perform various analyses like overlaying, buffering, and etc., but it does not have the tools to analyze multiple interrelated factors. On the other hand, expert systems can carry out various analyses but they cannot consider georeferenced information. Land evaluation is a vital activity for rural development and planning worldwide. A physical suitability evaluation indicates the degree of suitability for land use, without respect to economic conditions. Since different crops need different physical conditions to grow, the main aim here is to find how much each crop yields given the climatic, edaphic and slope conditions. The model discussed in this paper considers not only the management views (practicality of raising and saving different crops) but also the interaction between different multiple interrelated factors. In addition, the suitability rating discussed in this paper is based on the FAO framework.
Geographic information system
Expert system
land evaluation
physical suitability evaluation
2013
02
17
555
561
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
An adaptive neuro-fuzzy controller for mold level control in continuous casting
Mold level variations in continuous casting are believed to be the main cause of surface defects in the final product. Although a PID controller is well capable of controlling the level under normal conditions, it cannot prevent large variations of mold level when a disturbance occurs in the form of nozzle unclogging. In this paper, dual controller architecture is presented, a PID controller is used as the main controller of the plant and an adaptive neuro-fuzzy controller is used as an auxiliary controller to help the PID during disturbed phases. The control is passed back to the PID controller after the disturbance is being dealt with. Simulation results prove the effectiveness of this control strategy in reducing mold level variations during the unclogging period.
Mold level control
continuous casting
adaptive neuro-fuzzy control
dual control architecture
2013
02
17
563
572
Iranian Journal of Science and Technology Transactions of Electrical Engineering
2228-6179
2228-6179
2001
25
3
Determining voltage instability point using bifurcation theory
Voltage stability
maximum loading point
convergence of power flow
saddle-node bifurcation
local elimination of singularity
2013
02
17
573
582