Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (67)
- Classification (66)
- Machine learning (65)
- Optimization (60)
- Genetic algorithm (58)
-
- Particle swarm optimization (50)
- Support vector machine (35)
- Artificial neural network (34)
- Feature extraction (33)
- Wireless sensor networks (31)
- Feature selection (30)
- Power quality (28)
- Artificial neural networks (27)
- Fuzzy logic (26)
- Distributed generation (25)
- Induction motor (24)
- Convolutional neural network (23)
- Clustering (21)
- Support vector machines (20)
- Convolutional neural networks (19)
- Image processing (19)
- Neural networks (19)
- Sliding mode control (19)
- Energy efficiency (18)
- Renewable energy (18)
- Electric vehicle (17)
- Natural language processing (17)
- Neural network (17)
- Reliability (17)
- Adaptive control (16)
- Publication Year
Articles 2701 - 2730 of 3106
Full-Text Articles in Computer Engineering
Voltage Stability Via Energy Function Analysis On Reduced Order Model Of Power System, Ahmet Çi̇fci̇, Yilmaz Uyaroğlu, Mehmet Ali̇ Yalçin
Voltage Stability Via Energy Function Analysis On Reduced Order Model Of Power System, Ahmet Çi̇fci̇, Yilmaz Uyaroğlu, Mehmet Ali̇ Yalçin
Turkish Journal of Electrical Engineering and Computer Sciences
A power system is a typical nonlinear dynamical system and voltage stability is an important subject of power system stability. This paper describes the use of the variable gradient method in a reduced order model of a single-machine infinite-bus power system. Additionally, the system's Lyapunov (energy) function is created and thus the system's energy level changes' effects on the system's stability are shown using the MACSYMA program. The Lyapunov function allows the determination of stability for nonlinear systems without the need to find exact solutions.
Application Of The Posicast Control Method To Static Shunt Compensators, Amir Ghorbani, Siamak Masoudi, Arash Shabani
Application Of The Posicast Control Method To Static Shunt Compensators, Amir Ghorbani, Siamak Masoudi, Arash Shabani
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, the Posicast control method is used for decreasing the reactive power oscillations of static shunt compensators. Shunt compensators such as the static synchronous compensator (STATCOM) and static VAR compensator (SVC) are considered to be FACTS devices. The applied control method decreases the amount of oscillations in the outputs of STATCOM and SVC considerably, with fast damping. In this paper, a PI controller is added to the model to decrease the sensitivity of the Posicast controller to the parameter variations and plant model mismatch. Simplicity and applicability are the main features of this controller. The model is simulated …
Optimal Design Of Upfc-Based Damping Controller Using Imperialist Competitive Algorithm, Ali Ajami, Reza Gholizadeh
Optimal Design Of Upfc-Based Damping Controller Using Imperialist Competitive Algorithm, Ali Ajami, Reza Gholizadeh
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, the optimal design of supplementary controller parameters of a unified power flow controller (UPFC) to damp low-frequency oscillations in a weakly connected system is investigated. The individual design of the UPFC controller, using the imperialist competitive algorithm (ICA) technique over a wide range of operating conditions, is discussed. The effectiveness and validity of the proposed controller on damping low-frequency oscillations is tested through a time-domain simulation and eigenvalue analysis under 4 loading conditions and a large disturbance. The simulation results, carried out using MATLAB/Simulink software, reveal that the tuned ICA-based UPFC controller has an excellent capability of …
Broken Rotor Bar Fault Detection In Inverter-Fed Squirrel Cage Induction Motors Using Stator Current Analysis And Fuzzy Logic, Mehmet Akar, İlyas Çankaya
Broken Rotor Bar Fault Detection In Inverter-Fed Squirrel Cage Induction Motors Using Stator Current Analysis And Fuzzy Logic, Mehmet Akar, İlyas Çankaya
Turkish Journal of Electrical Engineering and Computer Sciences
This paper presents the implementation of broken rotor bar fault detection in an inverter-fed induction motor using motor current signal analysis (MCSA) and prognosis with fuzzy logic. Recently, inverter-fed induction motors have become very popular because of their adjustable speed drive. They have been used in many vital control applications such as rolling mills, variable speed compressors, pumps, and fans. The condition monitoring of these motors can significantly reduce the cost of maintenance in the early detection of faults. In this study, MCSA is applied to an inverter-fed induction motor to detect broken rotor bar faults. The diagnosis of a …
Fractional Pid Controllers Tuned By Evolutionary Algorithms For Robot Trajectory Control, Zafer Bi̇ngül, Oğuzhan Karahan
Fractional Pid Controllers Tuned By Evolutionary Algorithms For Robot Trajectory Control, Zafer Bi̇ngül, Oğuzhan Karahan
Turkish Journal of Electrical Engineering and Computer Sciences
The aim of this paper is to compare the performances of a fractional order proportional integral derivative (FOPID) controller tuned with evolutionary algorithms for robot trajectory control. In order to make this comparison, a 2-degrees-of-freedom planar robot was controlled by a FOPID controller tuned with particle swarm optimization (PSO) and a real coded genetic algorithm (GA). In order to see the effects of the cost functions on the optimum parameters of the FOPID controller, 3 different cost functions were used: the root mean squared error (MRSE), mean absolute error (MAE), and mean minimum fuel and absolute error (MMFAE). In order …
An Implementation Of Modified Scatter Search Algorithm To Transmission Expansion Planning, Majid Zeinaddini Maymand, Masoud Rashidinejad, Hamid Khorasani, Mohsen Rahmani, Amin Mahmoudabadi
An Implementation Of Modified Scatter Search Algorithm To Transmission Expansion Planning, Majid Zeinaddini Maymand, Masoud Rashidinejad, Hamid Khorasani, Mohsen Rahmani, Amin Mahmoudabadi
Turkish Journal of Electrical Engineering and Computer Sciences
Transmission network expansion planning (TNEP) is one of the most important tasks in the field of power systems, especially in deregulated power system environments. TNEP is a nonlinear mixed integer programming problem that can be solved via hybrid heuristic algorithms. This paper presents a modified scatter search algorithm (MSSA) to reinforce the ordinary scatter search algorithm (SSA) to be equipped for handling large scale transmission expansion planning (TEP) problems. The proposed methodology is based on the SSA, incorporating some improved strategies so as to decrease the number of linear programming problems required to be solved iteratively. In this study, it …
Analysis And Characterization Of Longitudinal Flux Single-Sided Linear Switched Reluctance Machines, Lenin Chokkalingam, Arumugam Rengasamy
Analysis And Characterization Of Longitudinal Flux Single-Sided Linear Switched Reluctance Machines, Lenin Chokkalingam, Arumugam Rengasamy
Turkish Journal of Electrical Engineering and Computer Sciences
Linear switched reluctance motors (LSRMs) have recently gained more popularity for propulsion drives. This paper contributes a certain design improvement to reduce the force ripple in LSRMs. By affixing a pole cap in the stator pole, the target is achieved. Finite element analysis has been carried out to predict the performance of the basic and proposed structures. Motor performances for different load conditions are simulated. The application of fast Fourier transform has been utilized to envisage the vibration frequencies. The experimental results are well correlated with the predicted results.
Analysis, Nonlinear Control, And Chaos Generator Circuit Of Another Strange Chaotic System, İhsan Pehli̇van, Zhouchao Wei
Analysis, Nonlinear Control, And Chaos Generator Circuit Of Another Strange Chaotic System, İhsan Pehli̇van, Zhouchao Wei
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we introduce a new 3-dimensional quadratic continuous autonomous chaotic system. This system can generate strange and interesting attractors. Some basic dynamical properties, such as bifurcations, and chaotic behaviors of the new chaotic system are investigated analytically and numerically. We propose a nonlinear control scheme to discuss codimension 1 and 2 Hopf bifurcations. In addition, a new circuit implementation of the chaotic attractor is reported and examined in PSpice. The new system is suitable for purposefully generating chaos in chaos-based engineering applications.
Dynamic Stability Enhancement Of A Multimachine Electric Power System Using Statcom, Hasan Fayazi Boroujeni, Reza Hemmati, Sayed Mojtaba Shirvani Boroujeni
Dynamic Stability Enhancement Of A Multimachine Electric Power System Using Statcom, Hasan Fayazi Boroujeni, Reza Hemmati, Sayed Mojtaba Shirvani Boroujeni
Turkish Journal of Electrical Engineering and Computer Sciences
With the expansion of electric power systems, the size and complexity of the network is increased. One of the most important drawbacks of network expansion is the reduction in the damping torque of the whole system. The lack of damping torque can lead to fluctuations and instability in the power system. With regard to this problem, power system stabilizers (PSSs) have been widely utilized to improve power system stability. However, due to some drawbacks of the conventional PSSs, the need for finding a better substitution still remains. Therefore, in this paper, the application of a static synchronous compensator (STATCOM) to …
A Neural-Based Electromagnetic Inverse Scattering Approach To The Detection Of A Conducting Cylinder Coated With A Dielectric Material, Senem Makal, Ahmet Kizilay
A Neural-Based Electromagnetic Inverse Scattering Approach To The Detection Of A Conducting Cylinder Coated With A Dielectric Material, Senem Makal, Ahmet Kizilay
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, a radial basis function neural network approach is applied for the estimation of the localization and the radius of a conducting cylinder with a circular cross-section coated with a dielectric material. A set of features, the radar cross-section (RCS) values, are derived from scattered fields, which are calculated using the surface equivalence principle and the method of moment. RCS values are obtained using 10 different scattering angles that are fed into the network. The outputs of the network are the location (x_0, y_0) and the radius (r_p) of the conducting cylinder. This is an application of the …
Considering Transmission Loss For An Economic Dispatch Problem Without Valve-Point Loading Using An Ep-Epso Algorithm, Sevugarathinam Muthu Vijaya Pandian, Keppanagowder Thanushkodi
Considering Transmission Loss For An Economic Dispatch Problem Without Valve-Point Loading Using An Ep-Epso Algorithm, Sevugarathinam Muthu Vijaya Pandian, Keppanagowder Thanushkodi
Turkish Journal of Electrical Engineering and Computer Sciences
Economic dispatch (ED) is one of the most important optimization problems in a power system. The objective of ED is sharing the power demand among the online generators while keeping the minimum cost of generation as a constraint. The aim of this paper is to operate an electric power system as economically as possible within its security limits. This paper proposes the following 2 new particle swarm optimization (PSO) algorithms to solve a nonconvex economic dispatch problem: an efficient PSO is termed as efficient particle swarm optimization (EPSO), and a hybrid of evolutionary programming (EP) and EPSO is termed as …
Resolution Enhancement Of Video Sequences By Using Discrete Wavelet Transform And Illumination Compensation, Sara Izadpanahi, Çağri Özçinar, Gholamreza Anbarjafari, Hasan Demirel
Resolution Enhancement Of Video Sequences By Using Discrete Wavelet Transform And Illumination Compensation, Sara Izadpanahi, Çağri Özçinar, Gholamreza Anbarjafari, Hasan Demirel
Turkish Journal of Electrical Engineering and Computer Sciences
This research paper proposes a new technique for video resolution enhancement that employees an illumination compensation procedure before the registration process. After the illumination compensation process, the respective frames are registered using the Irani and Peleg technique. In parallel, the corresponding frame is decomposed into high-frequency (low-high, high-low, and high-high) and low-frequency (low-low) subbands using discrete wavelet transform (DWT). The high-frequency subbands are superresolved using bicubic interpolation. Afterwards, the interpolated high-frequency subbands and superresolved low-frequency subband obtained by registration are used to construct the high-resolution frame using inverse DWT. The superiority of the proposed resolution enhancement method over well-known video …
Model Selection And Score Normalization For Text-Dependent Single Utterance Speaker Verification, Osman Büyük, Mustafa Levent Arslan
Model Selection And Score Normalization For Text-Dependent Single Utterance Speaker Verification, Osman Büyük, Mustafa Levent Arslan
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we investigate model selection and channel variability issues on a text-dependent single utterance (TDSU) speaker verification application. Due to the lack of an appropriate database for the task, a multichannel speaker recognition database, which consists of multiple recordings of a single Turkish utterance, is collected. The first set of experiments is devoted to model selection. Phonetic hidden Markov model (HMM)-based, sentence HMM-based, and Gaussian mixture model (GMM)-based methods are compared to find the most appropriate modeling approach for the target application. Based on the experimental results, the HMM-based methods outperform the GMM. The sentence HMM yields the …
Using A Game-Based Learning Model As A New Teaching Strategy For Computer Engineering, Kristijan Kuk, Dragica Jovanovic, Dusan Jokanovic, Petar Spalevic, Marko Caric, Stefan Panic
Using A Game-Based Learning Model As A New Teaching Strategy For Computer Engineering, Kristijan Kuk, Dragica Jovanovic, Dusan Jokanovic, Petar Spalevic, Marko Caric, Stefan Panic
Turkish Journal of Electrical Engineering and Computer Sciences
Interactive multimedia simulations and computer game elements can be successfully combined in order to create new advanced educational resources for teaching today's generation of students. Such a learning environment, a game-based learning model (GBLm), has been designed as a research prototype. This paper describes one type of GBLm for computer engineering, which we have used in the subject of computer graphics for the teaching unit Z-buffer algorithm, in order to facilitate the learning process. The implementation of a GBLm for graphical algorithms (GBL4CAl) is presented in detail as a multimedia interactive learning module designed to motivate students by making learning …
On The Degradation Of Ota-C--Based Cmos Low-Power Filter Circuits For Biomedical Instrumentation, Yasi̇n Özçelep, Ayten Kuntman, Hulusi̇ Hakan Kuntman
On The Degradation Of Ota-C--Based Cmos Low-Power Filter Circuits For Biomedical Instrumentation, Yasi̇n Özçelep, Ayten Kuntman, Hulusi̇ Hakan Kuntman
Turkish Journal of Electrical Engineering and Computer Sciences
In this work, we propose a degraded transistor-based circuit degradation simulation method to investigate the degradation effect in complementary metal-oxide semiconductor (CMOS) biomedical devices. The method is demonstrated on an operational transconductance amplifier and capacitor (OTA-C)-based CMOS filter structure. First, we simulate the degradation of the symmetrical CMOS OTA by determining the degraded transistors in the structure. The simulation results are compared with the experimental results of our previous study. First- and second-order low-pass filter degradations are also simulated to demonstrate the accuracy of the proposed method. Finally, the degradation in the electroencephalogram band-pass filter and its effect on the …
Adaptive Optimization Of Edca Parameters For Improved Qos In Multi-Media Applications, Alparslan Çi̇l, Mehmet Akar, Emi̇n Anarim
Adaptive Optimization Of Edca Parameters For Improved Qos In Multi-Media Applications, Alparslan Çi̇l, Mehmet Akar, Emi̇n Anarim
Turkish Journal of Electrical Engineering and Computer Sciences
IEEE 802.11e Enhanced Distributed Channel Access (EDCA) has been incorporated into the standard as an effective medium access mechanism in order to provide the desired QoS for multimedia applications such as VoIP and IPTV. This paper presents an adaptive optimization algorithm in EDCA which strives to provide improved QoS from both delay and throughput perspectives. As a first step towards this goal, a Markov model of the EDCA mechanism has been introduced, which is subsequently used to compute the estimates of throughput and delay. Based on the analytical model that is validated via real-time simulations in OPNET, a new algorithm …
Hybrid Mpi+Upc Parallel Programming Paradigm On An Smp Cluster, Zeki̇ Bozkuş
Hybrid Mpi+Upc Parallel Programming Paradigm On An Smp Cluster, Zeki̇ Bozkuş
Turkish Journal of Electrical Engineering and Computer Sciences
The symmetric multiprocessing (SMP) cluster system, which consists of shared memory nodes with several multicore central processing units connected to a high-speed network to form a distributed memory system, is the most widely available hardware architecture for the high-performance computing community. Today, the Message Passing Interface (MPI) is the most widely used parallel programming paradigm for SMP clusters, in which the MPI provides programming both for an SMP node and among nodes simultaneously. However, Unified Parallel C (UPC) is an emerging alternative that supports the partitioned global address space model that can be again employed within and across the nodes …
Improved Computerized Evaluation Of Abdominal Aortic Aneurysm, Semi̇h Utku, Hulusi̇ Baysal, Reyat Yilmaz, Aytaç Gülcü, Recep Alp Kut, Ahmet Yi̇ği̇t Göktay
Improved Computerized Evaluation Of Abdominal Aortic Aneurysm, Semi̇h Utku, Hulusi̇ Baysal, Reyat Yilmaz, Aytaç Gülcü, Recep Alp Kut, Ahmet Yi̇ği̇t Göktay
Turkish Journal of Electrical Engineering and Computer Sciences
Accurate measurements of arterial anatomy are emerging as the most important determinants of endovascular abdominal aneurysm repair. It is quite difficult to define and measure arterial anatomy features quantitatively due to the complex structure of the aneurysm and insufficient visual feedback. During decision making, to assist operators in diagnosing abdominal aortic aneurysms, a specialized preprocessing Abdominal Aortic Aneurysm Measurement and Evaluation Tool (AMET) was developed. AMET provides visual interfaces with broad measurement capabilities to generate a 3D model of the aorta for a better diagnosis and accurate stent selection. The accuracy and usability of the tool was tested with a …
Electromagnetic Scattering From Layered Strip Geometries: The Method Of Moments Study With The Sinc Basis, Taner Oğuzer, Fadil Kuyucuoğlu, İbrahi̇m Avgin
Electromagnetic Scattering From Layered Strip Geometries: The Method Of Moments Study With The Sinc Basis, Taner Oğuzer, Fadil Kuyucuoğlu, İbrahi̇m Avgin
Turkish Journal of Electrical Engineering and Computer Sciences
Electromagnetic scattering from strips of layers is analyzed using the method of moments (MoM) for both polarizations in spatial domain with the sinc-type orthogonal sets as basis and testing functions. We exploited the sinc function's properties of exponential convergence, the orthogonality, easy convolution and better handling of singular kernels in MoM procedure resulting in fast performance and reasonable accuracy even in ordinary MoM treatment. We transferred the integral of the Hankel function multiplied by sinc functions to Hankel function introducing a slight error with large band width. We proved that this relative error during the generation of the main matrix …
Automatic Knowledge Extraction For Filling In Biography Forms From Turkish Texts, İlknur Pehli̇van, Zeynep Orhan
Automatic Knowledge Extraction For Filling In Biography Forms From Turkish Texts, İlknur Pehli̇van, Zeynep Orhan
Turkish Journal of Electrical Engineering and Computer Sciences
This study presents a method for building an automatic knowledge extraction system for filling in biography forms from Turkish texts. Several biographies are analyzed in order to choose the set of biography categories to be studied. The fields of the biography form to be created are also defined based on this analysis. Information extraction techniques are used for implementation. A separate testing platform is designed to evaluate the accuracy of the extracted data. Results of the testing platform have shown this study to be a promising process to be further developed especially for creating forms in the Turkish language.
Neuro-Fuzzy Soft-Switching Hybrid Filter For Impulsive Noisy Environments, Şaban Özer, Hasan Zorlu
Neuro-Fuzzy Soft-Switching Hybrid Filter For Impulsive Noisy Environments, Şaban Özer, Hasan Zorlu
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, a new soft-switching hybrid filter based on a neuro-fuzzy network for impulsive noisy environments is proposed. The hybrid filter was built by combining an adaptive finite impulse response (FIR) filter, an adaptive weighted myriad (WMy) filter, and a soft-switching mechanism based on a neuro-fuzzy (NF) network. Performance of the hybrid filter was tested in \alpha-stable noisy situations and compared with adaptive FIR, WMy, and weighted median (WMd) filter performances. According to the simulation results; the proposed hybrid filter has better performance than the adaptive FIR, WMy, and WMd filters, and has the ability of effectively suppressing the …
Simulation Of Storage Time Versus Reverse Bias Current For P^+N And Pin Diodes, Mehmet Serhat Keserli̇oğlu, Hasan Hüseyi̇n Erkaya
Simulation Of Storage Time Versus Reverse Bias Current For P^+N And Pin Diodes, Mehmet Serhat Keserli̇oğlu, Hasan Hüseyi̇n Erkaya
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, the reverse-recovery behaviors of pin and p^+n diodes were simulated as a function of the reverse current and carrier lifetime. For this purpose, a 1-D simulation program was written to solve the semiconductor equations. MatLab partial differential equation solver was used. The reverse recovery response of pin and p^+n diodes was obtained for various values of a resistor in series and of carrier lifetime. The transient response for voltage and current was determined.
Determining Wave Propagation Characteristics Of Mv Xlpe Power Cable Using Time Domain Reflectometry Technique, Ghulam Murtaza Hashmi, Ruslan Papazyan, Matti Lehtonen
Determining Wave Propagation Characteristics Of Mv Xlpe Power Cable Using Time Domain Reflectometry Technique, Ghulam Murtaza Hashmi, Ruslan Papazyan, Matti Lehtonen
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, the wave propagation characteristics of single-phase medium voltage (MV) cross-linked polyethylene (XLPE) power cable are determined using time domain reflectometry (TDR) measurement technique. TDR delivers the complex propagation constant (attenuation and phase constant) of lossy cable transmission line as a function of frequency. The frequency-dependent propagation velocity is also determined from the TDR measurements through the parameters extraction procedure. The calibration of the measuring system (MS) is carried-out to avoid the effect of multiple reflections on the accuracy of measurements. The results obtained from the measurements can be used to localize the discontinuities as well as the …
Asynchronous Signal Processing For Brain-Computer Interfaces, Seda Senay, Luis F. Chaparro, Mingui Sun, Robert Sclabassi, Aydin Akan
Asynchronous Signal Processing For Brain-Computer Interfaces, Seda Senay, Luis F. Chaparro, Mingui Sun, Robert Sclabassi, Aydin Akan
Turkish Journal of Electrical Engineering and Computer Sciences
Brain-computer interfaces (BCIs) provide a way to monitor and treat neurological diseases. An important application of BCIs is the monitoring and treatment of epilepsy, a neurological disorder characterized by recurrent unprovoked seizures, symptomatic of abnormal, excessive or synchronous neuronal activity in the brain. BCIs contain an array of sensors that gather and transmit data under the constrains of low-power and minimal data transmission. Asynchronous sigma delta modulators (ASDMs) are considered an alternative to synchronous analog to digital conversion. ASDMs are non-linear feedback systems that enable time-encoding of analog signals, from which the signal can be reconstructed. An efficient reconstruction of …
Fully Integrated Universal Biquads Using Operational Transresistance Amplifiers With Mos-C Realization, Ahmet Gökçen, Selçuk Kilinç, Uğur Çam
Fully Integrated Universal Biquads Using Operational Transresistance Amplifiers With Mos-C Realization, Ahmet Gökçen, Selçuk Kilinç, Uğur Çam
Turkish Journal of Electrical Engineering and Computer Sciences
Universal biquadratic filters employing operational transresistance amplifiers are presented. All 5 different second-order filtering functions, namely low-pass, high-pass, band-pass, notch, and all-pass, can be realized. The quality factor of the filters can be adjusted electronically without affecting resonant frequency. The configuration can be made fully integrated based on MOS-C realization, by making use of the current differencing and internally grounded inputs of OTRA. PSpice simulation results are given to verify the theoretical analysis.
Obtaining The Secondary Impedance Of Single-Sided Linear Induction Motor With A Double Layer Reaction Rail: A New Approach, Ali̇ Suat Gerçek, Vedat Mehmet Karsli
Obtaining The Secondary Impedance Of Single-Sided Linear Induction Motor With A Double Layer Reaction Rail: A New Approach, Ali̇ Suat Gerçek, Vedat Mehmet Karsli
Turkish Journal of Electrical Engineering and Computer Sciences
In the performance calculations of single-sided linear induction motor (SLIM),the equivalent circuit technique (ECT) is used. In this paper, a new approach is proposed for obtaining the secondary impedance of single-sided linear induction motor (SLIM) with a double layer reaction rail by using the layered secondary model. The proposed method improves the ECT technique by considering the saturation effect and the non-linear complex equivalent relative permeability. This study also examines the contributions of other electromagnetic effects, such as longitudinal end effect and transverse edge effect as well. Our method is applied to the SLIM and computed results of the method …
Online Speed Control Of A Brushless Ac Servomotor Based On Artificial Neural Networks, Si̇bel Partal, İbrahi̇m Şenol, Ahmet Faruk Bakan, Kamuran Nur Beki̇roğlu
Online Speed Control Of A Brushless Ac Servomotor Based On Artificial Neural Networks, Si̇bel Partal, İbrahi̇m Şenol, Ahmet Faruk Bakan, Kamuran Nur Beki̇roğlu
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, an alternative approach to speed estimation of brushless AC servomotors is presented. Speed control is realized in the following steps. First, the servomotor was mathematically modelled; the driver system was designed and speed control of the servomotor was accomplished with feedback. Next, a network structure representing the electrical and mechanical properties of the servomotor was built via Artificial Neural Network (ANN) and trained with the results of the first step. The weights obtained from the neural nwork training were inserted into the control algorithm in accordance with the ANN. Finally, speed estimation was achieved based on the …
A Logic Method For Efficient Reduction Of The Space Complexity Of The Attribute Reduction Problem, Mehmet Hacibeyoğlu, Fati̇h Başçi̇ftçi̇, Şi̇rzat Kahramanli
A Logic Method For Efficient Reduction Of The Space Complexity Of The Attribute Reduction Problem, Mehmet Hacibeyoğlu, Fati̇h Başçi̇ftçi̇, Şi̇rzat Kahramanli
Turkish Journal of Electrical Engineering and Computer Sciences
The goal of attribute reduction is to find a minimal subset (MS) R of the condition attribute set C of a dataset such that R has the same classification power as C. It was proved that the number of MSs for a dataset with n attributes may be as large as (_{n/2}^n) and the generation of all of them is an NP-hard problem. The main reason for this is the intractable space complexity of the conversion of the discernibility function (DF) of a dataset to the disjunctive normal form (DNF). Our analysis of many DF-to-DNF conversion processes showed that approximately …
Performance Evaluation Of Nonparametric Ica Algorithm For Fetal Ecg Extraction, Yusuf Sevi̇m, Ayten Atasoy
Performance Evaluation Of Nonparametric Ica Algorithm For Fetal Ecg Extraction, Yusuf Sevi̇m, Ayten Atasoy
Turkish Journal of Electrical Engineering and Computer Sciences
Fetal electrocardiograms (FECG) contain important indications about the health and condition of the fetus. In this respect, it is crucial to apply a robust algorithm to ECG data for extraction of the FECG signal. Most of the independent component analysis (ICA) algorithms used for this purpose rely on simple statistical models. Such algorithms can fail to separate desired signals when the assumed statistical model is inaccurate. Statistical models can be estimated accurately using kernel density estimation methods. Therefore, the kernel density estimation method was used in this paper for building an ICA algorithm (nonparametric ICA: NpICA) and the algorithm was …
A Vision Based Feedback Mechanism For 6-Dof Stewart Platform, Utku Büyükşahi̇n
A Vision Based Feedback Mechanism For 6-Dof Stewart Platform, Utku Büyükşahi̇n
Turkish Journal of Electrical Engineering and Computer Sciences
Eyes are the most ubiquitous sensors of humankind. However, ``Vision Based Sensors" are not as common as what this fact would suggest. A survey of the previous work on image processing would reveal that the bulk of the research in this area have been conducted since the year 2000. These facts clearly show that image processing is the technology of our century, and is very open to further development. In this work, a system that combines a classical mechanism of the 20th century with the recent technology of the 21st century is presented and the design, theoretical background, the software …