A Novel Method For Lung Segmentation On Chest Ct Images: Complex-Valued Artificial Neural Network With Complex Wavelet Transform, Murat Ceylan, Yüksel Özbay, Osman Nuri̇ Uçan, Erkan Yildirim
Turkish Journal of Electrical Engineering and Computer Sciences
Image segmentation is an important step in many computer vision algorithms. The objective of segmentation is to obtained an optimal region of convergences (ROC). Error in this stage will impact all higher level activities. This paper focuses on a new efficient method denoted as Complex-Valued Artificial Neural Network with Complex Wavelet Transform (CWT-CVANN) for the segmentation of lung region on chest CT images. In this combined architecture is composed of two cascade stages: feature extraction with various levels of complex wavelet transform and segmentation with complex-valued artificial neural network. Here, 32 CT images of 6 female and 26 male patients …
Adaptive Neuro-Fuzzy Inference System To Improve The Power Quality Of Variable-Speed Wind Power Generation System,
2010
TÜBİTAK
Adaptive Neuro-Fuzzy Inference System To Improve The Power Quality Of Variable-Speed Wind Power Generation System, Yüksel Oğuz, Kami̇l Ri̇fat İrfan Güney
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, an adaptive neuro-fuzzy inference system is designed for output voltage and frequency control of a variable-speed wind power generation system. Variable-speed wind power generation systems (VSWPGS) provide the opportunity to capture more power than fixed speed turbines. On the other hand, the variable-speed wind turbine output can be variable voltage and variable frequency for fluctuating wind speeds. The quality of output power can be improved if adequate controls are incorporated in the system. To bring the output voltage and frequency of system by means of control of blade pitch angle of wind turbine to a desirable value, …
Programmable Design And Implementation Of A Chaotic System Utilizing Multiple Nonlinear Functions,
2010
TÜBİTAK
Programmable Design And Implementation Of A Chaotic System Utilizing Multiple Nonlinear Functions, Recai̇ Kiliç, Fatma Yildirim Dalkiran
Turkish Journal of Electrical Engineering and Computer Sciences
In addition to exhibiting a rich variety of bifurcation and chaos via tuning parameters, a chaotic system introduced by Sprott can be modeled and realized with a fixed main system block and many different changeable nonlinear function blocks such as piecewise-linear function, cubic function and other trigonometric functions. This system is very suitable for implementing a programmable chaos generator according to its changeable nonlinearity. This paper presents a FPAA (Field Programmable Analog Array)-based programmable implementation of this system. Nonlinear function blocks used in this chaotic system are modeled with FPAA programming and a model is rapidly changed for realizing other …
The Analysis Of A Semiconductor Single Asymmetric And Symmetric Step-Index Laser For Even And Odd Fields By Alpha Method,
2010
TÜBİTAK
The Analysis Of A Semiconductor Single Asymmetric And Symmetric Step-Index Laser For Even And Odd Fields By Alpha Method, Mustafa Temi̇z, Mehmet Ünal
Turkish Journal of Electrical Engineering and Computer Sciences
In this work, semiconductor step-index single waveguide has been analyzed by Alpha Method. A requested quantity of wave guide can be obtained in terms of normalized propagation constant, which is represented by alpha belonging to active region. Based on this method, structural properties of the material containing any requested quantity of the waveguide is theoretically calculated, when the width of the active region, the refractive indices of the regions and the wavelength are given. In the TE mode some important parameters, such as the propagation constants for regions of the semiconductor step-index single waveguide, the wave numbers, the effective index …
Active Illumination And Appearance Model For Face Alignment,
2010
TÜBİTAK
Active Illumination And Appearance Model For Face Alignment, Muhi̇tti̇n Gökmen, Fati̇h Kahraman, Sune Darkner, Rasmus Larsen
Turkish Journal of Electrical Engineering and Computer Sciences
Illumination conditions have an explicit effect on the performance of face recognition systems. In particular, varying the illumination upon the face imposes such complex effects that the identification often fails to provide a stable performance level. In this paper, we propose an approach integrating face identity and illumination models in order to reach acceptable and stable face recognition rates. For this purpose, Active Appearance Model (AAM) and illumination model of faces are combined in order to obtain an illumination invariant face localization. The proposed method is an integrated Active Illumination and Appearance Model (AIA) which combines identity, illumination and shape …
Robust Feedback Design For Nonlinear Systems: A Survey,
2010
TÜBİTAK
Robust Feedback Design For Nonlinear Systems: A Survey, Alberto Isidori
Turkish Journal of Electrical Engineering and Computer Sciences
No abstract provided.
Sdre Optimal Control Of Drug Administration In Cancer Treatment,
2010
TÜBİTAK
Sdre Optimal Control Of Drug Administration In Cancer Treatment, Mehmet İti̇k, Meti̇n Uymaz Salamci̇, Stephen Paul Banks
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, we apply State Dependent Riccati Equation (SDRE) based optimal control technique to a nonlinear tumor growth model. The model consists of three biological cells which are normal tissue, tumor and immune cells. The effect of chemotherapy treatment is also included in the model. Chemotherapy administration is considered as a control input to the nonlinear cancer dynamics and the amount of administered drug is determined by using SDRE optimal control. The optimal control is applied to the model in order not only to drive the tumor cells to the healthy equilibrium state but also to minimize the amount …
Fractional Order Sliding Mode Control With Reaching Law Approach,
2010
TÜBİTAK
Fractional Order Sliding Mode Control With Reaching Law Approach, Mehmet Önder Efe
Turkish Journal of Electrical Engineering and Computer Sciences
Fractional order sliding mode control is studied in this paper. The control objectives are achieved by adopting the reaching law approach of sliding mode control. The main contribution of this work is to show that the philosophy of integer order sliding mode control is valid also for the systems represented by fractional order operators. A sufficient condition and its implications for stability are given. Matched and unmatched uncertainties are studied. The attractor nature of the switching manifold is analyzed together with a stable sliding subspace design condition. The claims are justified through a set of simulations and the results obtained …
Formation Control Of Nonholonomic Mobile Robots Using Implicit Polynomials And Elliptic Fourier Descriptors,
2010
TÜBİTAK
Formation Control Of Nonholonomic Mobile Robots Using Implicit Polynomials And Elliptic Fourier Descriptors, Yeşi̇m Hümay Esi̇n, Mustafa Ünel
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents a novel method for the formation control of a group of nonholonomic mobile robots using implicit and parametric descriptions of the desired formation shape. The formation control strategy employs implicit polynomial (IP) representations to generate potential fields for achieving the desired formation and the elliptical Fourier descriptors (EFD) to maintain the formation once achieved. Coordination of the robots is modeled by linear springs between each robot and its two nearest neighbors. Advantages of this new method are increased flexibility in the formation shape, scalability to different swarm sizes and easy implementation. The shape formation control is first …
A Novel Algorithm For Sensorless Motion Control Of Flexible Structures,
2010
TÜBİTAK
A Novel Algorithm For Sensorless Motion Control Of Flexible Structures, Islam Shoukry Mohammed Khalil, Emrah Deni̇z Kunt, Asif Sabanovic
Turkish Journal of Electrical Engineering and Computer Sciences
This article demonstrates the validity of using an actuator as a single platform for measurements during a motion control assignment of flexible systems kept free from any kind of measurement. System acceleration level dynamics, parameters and interaction forces with the environment are coupled in an incident reaction torque that naturally rises when a flexible system is subjected to an action imposed by an attached actuator to the system. This work attempts to decouple each of the system parameters out of the incident coupled reaction torque at the interface point of the actuator with the flexible system by way of measurements …
Modeling And Control Of Flow Problems By Adaptation-Based Linear Parameter Varying Models,
2010
TÜBİTAK
Modeling And Control Of Flow Problems By Adaptation-Based Linear Parameter Varying Models, Coşku Kasnakoğlu
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper a systematic modeling and control approach for flow problems is considered. A nonlinear Galerkin model is obtained from the partial differential equations (PDEs) describing the flow; and a Linear Parameter Varying (LPV) model is constructed to approximate the Galerkin model, where the parameter variation of the LPV model is controller by an adaptation mechanism. The LPV model is then treated as a surrogate on which the control design is carried out, where the parameter variations provide a range of uncertainty in which the control design must perform satisfactorily. It is shown that if certain conditions are met, …
Simultaneous Rotor And Stator Resistance Estimation Of Squirrel Cage Induction Machine With A Single Extended Kalman Filter,
2010
TÜBİTAK
Simultaneous Rotor And Stator Resistance Estimation Of Squirrel Cage Induction Machine With A Single Extended Kalman Filter, Eşref Emre Özsoy, Meti̇n Gökaşan, Ovsanna Seta Estrada
Turkish Journal of Electrical Engineering and Computer Sciences
Accurate knowledge of rotor and stator resistance variations in a squirrel-cage induction motor (SCIM) is crucial for the performance of sensorless control of SCIM over a wide range of speeds. This study seeks to address this issue with a single Extended Kalman Filter (EKF) based solution, which is also known to have accuracy limitations when a high number of parameters/states are estimated with a limited number of inputs. To this aim, different from the author's previous approach in operating several EKFs in an alternating manner (the so-called braided EKF), an 8^{th}-order EKF is implemented in this study to test its …
Experimental Investigation Of Shaft Transducerless Speed And Position Control Of Ac Induction And Interior Permanent Magnet Motors, Ömer Göksu, Ahmet Masum Hava
Turkish Journal of Electrical Engineering and Computer Sciences
In order to drive AC motors with high efficiency and high motion performance, and to provide accurate speed/position control, motor shaft speed and/or position feedback is required. For this purpose, usually transducers (encoder, tachogenerator, resolver, etc.) are installed on the shaft. However, transducers are not preferred in most of the applications since they increase the cost and decrease the reliability of the drive due to their failure prone structure and connections. In such applications, the speed and/or position information of the motor is obtained by estimation methods without using shaft transducers. In this work, motor types and speed/position estimation methods …
Analysis And Estimation Of Motion Transmission Errors Of A Timing Belt Drive,
2010
TÜBİTAK
Analysis And Estimation Of Motion Transmission Errors Of A Timing Belt Drive, Ergi̇n Kiliç, Meli̇k Dölen, Ahmet Buğra Koku
Turkish Journal of Electrical Engineering and Computer Sciences
This paper focuses on viable position estimation schemes for timing belt drives where the position of the carriage (load) is to be determined via reference models receiving input from a position sensor attached to the actuator of the timing belt. A detailed analysis of the transmission error sources is presented, and a number of relevant mathematical models are developed using a priori knowledge of the process. This paper demonstrates that such schemes are very effective when the drive system is not subjected to external loads and operating conditions do not change considerably i.e. ambient temperature, belt tension.
Precise Position Control Using Shape Memory Alloy Wires,
2010
TÜBİTAK
Precise Position Control Using Shape Memory Alloy Wires, Burcu Dönmez, Bülent Özkan, Fevzi̇ Suat Kadioğlu
Turkish Journal of Electrical Engineering and Computer Sciences
Shape memory alloys (SMAs) are active metallic ``smart'' materials used as actuators and sensors in high technology smart systems [1]. The term shape memory refers to ability of certain materials to ``remember'' a shape, even after rather severe deformations: once deformed at low temperatures, these materials will stay deformed until heated, whereupon they will return to their original, pre-deformed ``learned'' shape [2]. This property can be used to generate motion and/or force in electromechanical devices and micro-machines. However, the accuracy of SMA actuators is severely limited by their highly nonlinear stimulus-response characteristics. In this work, modeling, simulation, and experimental efforts …
Direct Discrete-Time Control Of Port Controlled Hamiltonian Systems,
2010
TÜBİTAK
Direct Discrete-Time Control Of Port Controlled Hamiltonian Systems, Yaprak Yalçin, Leyla Gören Sümer
Turkish Journal of Electrical Engineering and Computer Sciences
The direct discrete time control of Port Controlled Hamiltonian Systems (PCHS) in the sense of energy shaping and damping injection is considered. In order to give a direct discrete time design method for PCHS, firstly an appropriate discrete gradient is proposed, which enables the derivation of a discrete time equation corresponding to the discrete time counterpart of Hamiltonian Systems. Using this proposed discrete-time model, the discrete-time counterpart of Passivity Based Control (PBC) technique is developed for n-degrees-of-freedom mechanical systems. The discrete-time control rules which correspond to the energy shaping and damping assignment are obtained directly using the discrete time model …
The Use Of Fpga In Field-Oriented Control Of An Induction Machine,
2010
TÜBİTAK
The Use Of Fpga In Field-Oriented Control Of An Induction Machine, Özkan Akin, İrfan Alan
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, the feasibility of embedding the field oriented control (FOC) of an induction machine into field programmable gate arrays (FPGA) is investigated. An indirect FOC of an induction machine is simulated in a Matlab Simulink environment using a Xilinx System Generator implemented in a Xilinx Spartan-3 XC3S200 FPGA board. Design of the developed controller for the induction machine is simulated via a Simulink full digital platform. The resulting design has a flexible and modular structure where the designer can customize the hardware blocks by changing the number of inputs, outputs, and algorithm when it is compared to the …
Detection Of Static Eccentricity For Permanent Magnet Synchronous Motors Using The Coherence Analysis,
2010
TÜBİTAK
Detection Of Static Eccentricity For Permanent Magnet Synchronous Motors Using The Coherence Analysis, Mehmet Akar, Sezai̇ Taşkin, Şahi̇n Serhat Şeker, İlyas Çankaya
Turkish Journal of Electrical Engineering and Computer Sciences
This paper reports on work to detect the static eccentricity faults for permanent magnet synchronous motor (PMSM) using spectral analysis methods. Measurements are carried out by collecting the stator current and voltage, torque and speed for healthy and faulty cases of the motor. Static eccentricity case is formed by changing the rotor position in the manner of sliding the shaft on a horizontal axis. As a result of the spectral analysis for the motor currents, side band effects appeared at around the fundamental frequency are determined as a most important indicator of the eccentricity. In addition to this determination, the …
Using Covariates For Improving The Minimum Redundancy Maximum Relevance Feature Selection Method,
2010
TÜBİTAK
Using Covariates For Improving The Minimum Redundancy Maximum Relevance Feature Selection Method, Olcay Kurşun, Cemal Okan Şakar, Oleg Favorov, Ni̇zametti̇n Aydin, Sadik Fi̇kret Gürgen
Turkish Journal of Electrical Engineering and Computer Sciences
Maximizing the joint dependency with a minimum size of variables is generally the main task of feature selection. For obtaining a minimal subset, while trying to maximize the joint dependency with the target variable, the redundancy among selected variables must be reduced to a minimum. In this paper, we propose a method based on recently popular minimum Redundancy-Maximum Relevance} (mRMR) criterion. The experimental results show that instead of feeding the features themselves into mRMR, feeding the covariates improves the feature selection capability and provides more expressive variable subsets.
Usage Of Spline Interpolation In Catheter-Based Cardiac Mapping,
2010
TÜBİTAK
Usage Of Spline Interpolation In Catheter-Based Cardiac Mapping, Bülent Yilmaz, Uğur Cunedi̇oğlu, Engi̇n Baysoy
Turkish Journal of Electrical Engineering and Computer Sciences
Due to their minimal invasiveness catheters are highly preferred in cardiac mapping techniques used in the source localization of rhythm disturbances in the heart. In cardiac mapping, standard steerable catheters and multielectrode basket catheters are the two alternatives for the characterization of the underlying tissue on the inner (endocardium) and outer (epicardium) surfaces of the heart. As with any discrete sampling technique, an important question for catheter-based cardiac mapping is how to determine values at locations from which direct measurements are not available. Interpolation is the most common approach for providing values at unmeasured sites using the available measurements. In …
