Mühendislik-Mimarlık Fakültesi Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12402/1080

Listeleniyor 1 - 20 / 21

Palmprint recognition based gabor wavelet transform using K-NN classification
(European Journal of Technique (EJT), 2016-04-01) Çalışkan, Abidin
Palmprint recognition system is regarded as the reliable and accurate biometric identification system available. Viewed in the palmprint recognition system of biometric approaches, compared to other models because it is a new handheld biometric feature recognition system has recently attracted the attention of researchers. In this study, palmprint recognition system based on Gabor wavelet transform has been developed. Firstly, image coordinate system is defined to facilitate image alignment for feature extraction. Then, region of interest is cropped from the palmprint images. With developed system feature extracted of region of interest and given of k-NN classifier.
Three-dimensional modeling in medical image processing by using fractal geometry
(Journal of Computers, 2017-09) Çalışkan, Abidin; Çevik, Ulus
Medical images are visualized by computer and processed to obtain larger, more organized, and three-dimensional (3D) images. Thus, significant images are provided. The processed data facilitate diagnosis and treatment in the medical fields. The 3D surface models of related areas are formed by using volumetric data obtained by employing medical imaging methods such as Magnetic Resonance (MR) and Computer Tomography (CT). The purpose of this study is to obtain 3D images from the two-dimensional CT slices. These slices are obtained from the existing medical imaging devices and transferred to the z space and a mesh structure is provided between them. In addition, we investigated 3D imaging techniques, visualization, basic data types, conversion into main graphical components, and imaging algorithms. At the phase of obtaining 3D images; the image processing methods such as surface and volume imaging techniques, smoothing, denoising, and segmentation were used. The complexity and efficiency properties of the imaging algorithms were investigated and image enhancement algorithms were utilized.
Organik arayüzey tabakalı Al/CuPc /p-InP kontakların fabrikasyonu ve elektriksel parametrelerinin incelenmesi
(Batman Üniversitesi, 2015-07-01) Aslan, Filiz; Güllü, Ömer; Ocak, Yusuf Selim; Rüzgar, Şerif; Tombak, Ahmet; Özaydın, Cihat; Pakma, Osman; Arsel, İsmail
Bu çalışmada termal buharlaştırma metodu kullanılarak bakır fitalosiyanin (CuPc) p-InP kristali üzerine kaplandı. Yine termal buharlaştırma sistemi kullanılarak oluşan ince organik film üzerine vakum ortamında alüminyum metali kaplandı ve Al/CuPc/p-InP diyot yapısı oluşturuldu. Al/CuPc/p-InP diyotunun oda sıcaklığında, karanlık ve aydınlık ortamda akım-gerilim (I-V) ölçümleri alındı. I-V grafiğinden bu yapının doğrultucu özellik gösterdiği görüldü. Aydınlık ortamda yapılan ölçümler 100 mW/cm2 ışık şiddeti altında yapıldı ve bu ölçümler doğrultusunda diyotun fotodiyot özellik gösterdiği görüldü. Ayrıca farklı yöntemlerle Al/CuPc/p-InP Schottky diyotunun karakteristik parametreleri ( idealite faktörü (n) ,engel yüksekliği (Φb) ve seri direnç (Rs) ) hesaplandı.
Photoelectric and photocapacitance characteristics of Au/pyrene/N-Si MIS structures
(Journal of Non-Oxide Glasses, 2017-04-01) Güllü, Ömer; Pakma, Osman; Özaydın, Cihat; Arsel, İsmail; Turmuş, Mesut
This paper presents in-depth analysis of the current-voltage (I-V) and capacitance-voltage (C-V) characteristics of identically prepared Au/Pyrene(C16H10)/n-Si hybrid organic-oninorganic semiconductor photovoltaic cells (total 43 diodes). The barrier heights, ideality factors and reverse bias saturation currents of all devices were extracted from the electrical characteristics. The mean barrier height, mean ideality factor and mean saturation current from I-V measurements were calculated as 0.79 ± 0.01 eV, 1.40 ± 0.08 and (1.01 ± 0.46)x10-8 A, respectively. Also, the photoelectric (I-V) and photocapacitance (C-V and conductance (G)-voltage (V)) characteristics of the Au/Pyrene/n-Si device under 100 mW/cm2 light illumination were investigated. It has been seen that the light illumination increases strongly the current, capacitance and conductance values of the device due to electron-hole charge pair generation. The C-V and G-V characteristics under illumination have shown a non-monotonic dependence of capacitance on frequency giving rise to a peak. This is attributed to the existence of electrically active traps. The open circuit voltage and short circuit current of the Au/Pyrene/n-Si device were extracted as 80 mV and 30 µA, respectively.
Predicting factors affecting PISA 2015 mathematics literacy via radial basis function artificial neural network
(Batman Üniversitesi, 2019-05-23) Güre Bezek, Özlem; Kayri, Murat; Erdoğan, Fevzi
In this study, radial basis function artificial neural network (RBFN), which is one of the of data mining methods, was employed to determine the factors affecting PISA 2015 (Programme for International Student Assessment - PISA), Mathematics literacy. Mathematics literacy scores, which were made in categorical form with three level dependent variables, 25 independent variables, and considered to have affected the dependent variables, were employed in evaluating and validating the proposed method. Also, in order to determine factors affecting PISA 2015 Mathematics literacy, information obtained from a total of 4422 students (2165 (49%) of whom were males and 2257 (51%) of whom were females) who participated the exam was used. According to the obtained results, the correct classification rate of mathematics achievement in the radial based artificial neural network model was found to be 85.2%. In addition, it is seen that the most important factor that were affecting Mathematics literacy was Turkish language success status and the other variables that were setting significance are targeted point in school life, father education level and mother education level.
Characterization of an Au/n-Si photovoltaic structure with an organic thin film
(Elsevier, 2013-08) Özaydın, Cihat; Akkılıç, Kemal; İlhan, Salih; Rüzgar, Şerif; Güllü, Ömer; Temel, Hamdi
We demonstrate that a copper(II) organic complex can control the electrical characteristics of conventional Au/n-Si metal-semiconductor (MS) contacts. We investigated the electronic and photovoltaic properties of a Cu(II) complex/n-Si heterojunction diode. The ideality factor n and barrier height Φb of the diode were 2.22 and 0.736 eV, respectively. An ideality factor greater than unity indicates that the diode exhibits non-ideal current-voltage behavior. This behavior results from the effect of series resistance and the presence of an interfacial layer. The series resistance and barrier height determined using Norde's method were 6.7 kΩ and 0.77 eV, respectively. The device showed photovoltaic behavior, with a maximum open-circuit voltage of 0.24 V and a short circuit current of 1.7 μA under light of 8 mW/cm2.
The optical characterization of organometallic complex thin films by spectroscopic ellipsometry and photovoltaic diode application
(Elsevier, 2016-05) Özaydın, Cihat; Güllü, Ömer; Pakma, Osman; İlhan, Salih; Akkılıç, Kemal
In this work, organometallic complex (OMC) films have been deposited onto glass or silicon substrates by spin coating technique and their photovoltaic application potential has been investigated. Optical properties and thickness of the film have been investigated by spectroscopic ellipsometry (SE). Also, transmittance spectrum has been taken by UV/vis spectrophotometer. The optical method has been used to determine the band gap value of the films. Also, Au/OMC/n-Si metal/interlayer/semiconductor (MIS) diode has been fabricated. Current-voltage and photovoltaic properties of the structure were investigated. The ideality factor (n) and barrier height (Φb) values of the diode were found to be 2.89 and 0.79 eV, respectively. The device shows photovoltaic behavior with a maximum open-circuit voltage of 396 mV and a short circuit current of 33.8 μA under 300 W light.
Wet chemical methods for producing mixing crystalline phase ZrO 2 thin film
(Elsevier, 2016-07) Pakma, Osman; Özdemir, Cengiz; Kariper, İshak Afşin; Özaydın, Cihat; Güllü, Ömer
The aim of the study is to develop a more economical and easier method for obtaining ZrO 2 thin films at lower temperature, unlike the ones mentioned in the literature. For this purpose, wet chemical synthesis methods have been tested and XRD, UV-VIS and SEM analysis of ZrO 2 thin films have been performed. At the end of the analysis, we identified the best method and it has been found that the features of the films produced with this method were better than the films produced by using different reagents, as well as the films reported in the literature. Especially it has been observed that the transmittance of the film produced with this method were higher and better than the films in the literature and the others. In addition, refractive index of the film produced with this method was observed to be lower. Moreover, by using the same method Al/ZrO 2 /p-Si structure has been obtained and it has been compared with Al/p-Si reference structure in terms of electrical parameters.
Synthesis and characterization of vanadium oxide thin films on different substrates
(Springer Nature, 2017-04-11) Güllü, Ömer; Pakma, Osman; Özaydın, Cihat; Özden, Şadan; Kariper, İshak Afşin
In this study, the V8O15 derivative of vanadium oxide was produced on plain glass, indium tin oxide and silicon wafer substrate layers by taking advantage of wet chemical synthesis which is an easy and economical method. The structural properties of the produced films were examined by XRD and SEM analyses. Besides, Al/VOx/p-Si metal-oxide-semiconductor (MOS) structure was obtained by the same synthesis method. Doping densities of these MOS structures were calculated from frequency dependent capacitance–voltage measurements. It was determined that the interface states which were assigned with the help of these parameters vary according to frequency.
A novel approach for SEMG signal classification with adaptive local binary pattern
(Springer Nature, 2015-12-31) Ertuğrul, Ömer Faruk; Kaya, Yılmaz; Tekin, Ramazan
Feature extraction plays a major role in the pattern recognition process, and this paper presents a novel feature extraction approach, adaptive local binary pattern (aLBP). aLBP is built on the local binary pattern (LBP), which is an image processing method, and one-dimensional local binary pattern (1D-LBP). In LBP, each pixel is compared with its neighbors. Similarly, in 1D-LBP, each data in the raw is judged against its neighbors. 1D-LBP extracts feature based on local changes in the signal. Therefore, it has high a potential to be employed in medical purposes. Since, each action or abnormality, which is recorded in SEMG signals, has its own pattern, and via the 1D-LBP these (hidden) patterns may be detected. But, the positions of the neighbors in 1D-LBP are constant depending on the position of the data in the raw. Also, both LBP and 1D-LBP are very sensitive to noise. Therefore, its capacity in detecting hidden patterns is limited. To overcome these drawbacks, aLBP was proposed. In aLBP, the positions of the neighbors and their values can be assigned adaptively via the down-sampling and the smoothing coefficients. Therefore, the potential to detect (hidden) patterns, which may express an illness or an action, is really increased. To validate the proposed feature extraction approach, two different datasets were employed. Achieved accuracies by the proposed approach were higher than obtained results by employed popular feature extraction approaches and the reported results in the literature. Obtained accuracy results were brought out that the proposed method can be employed to investigate SEMG signals. In summary, this work attempts to develop an adaptive feature extraction scheme that can be utilized for extracting features from local changes in different categories of time-varying signals.
Detection of Parkinson's disease by Shifted One Dimensional Local Binary Patterns from gait
(Elsevier, 2016-09) Ertuğrul, Ömer Faruk; Kaya, Yılmaz; Tekin, Ramazan; Almalı, Mehmet Nuri
The Parkinson's disease (PD) is one of the most common diseases, especially in elderly people. Although the previous studies showed that the PD can be diagnosed by expert systems through its cardinal symptoms such as the tremor, muscular rigidity, disorders of movements and voice, it was reported that the presented approaches, which utilize simple motor tasks, were limited and lack of standardization. To achieve a standard approach in PD detection, an approach, which is built on shifted one-dimensional local binary patterns (Shifted 1D-LBP) and machine learning methods, was proposed. Shifted 1D-LBP is built on 1D-LBP, which is sensitive to local changes in a signal. In 1D-LBP the positions of neighbors around center data are constant and therefore, the number of patterns that can be exacted by it is limited. This drawback was solved by Shifted 1D-LBP by changeable positions of neighbors. In evaluation and validation stages, the Gait in Parkinson's Disease (gaitpdb) dataset, which consists of three gait datasets that were recorded in different tasks or experiment protocols, were employed. Statistical features were exacted from formed histograms of gait signals transformed by Shifted 1D-LBP. Whole features and selected features were classified by machine learning methods. Obtained results were compared with statistical features exacted from signals in both time and frequency domains and results reported in the literature. Achieved results showed that the proposed approach can be successfully employed in PD detection from gait. This work is not only an attempt to develop a PD detection method, but also a general-purpose approach that is based on detecting local changes in time ordered signals.
Application and comparative performance analysis of PSO and ABC algorithms for optimal design of multimachine power system stabilizers
(Gazi Üniversitesi, 2016-06-20) Ekinci, Serdar
This paper presents the application and performance comparison of PSO and ABC optimization techniques, for multi-objective design of power system stabilizers (PSSs) in the multi-machine power system. The design objective is to improve the power system stability. The PSSs parameters tuning problem is converted to an optimization problem with the time domain-based objective function and both PSO and ABC optimization techniques are used to search for optimal stabilizers parameters. The optimized stabilizers are tested on multi-machine electric power system subjected to different disturbances. The performance of both optimization techniques in terms of computational time, convergence rate and solution quality is compared. The eigenvalue analysis, nonlinear timedomain simulation results, critical clearing times and some performance indices studies are introduced and compared in order to demonstrate the effectiveness of both optimization techniques in designing stabilizers, to enhance the dynamic stability of the system. What is more, the potential and superiority of the ABC algorithm over the PSO algorithm are verified.
HPA algoritması ile çok makinalı güç sistemi kararlı kılıcısı tasarımı
(Gazi Üniversitesi, 2017-12-08) Ekinci, Serdar; Hekimoğu, Baran
Bu makale, parçacık sürüsü optimizasyonu (PSO) ve yapay arı kolonisine (ABC) dayalı, çok makinalı güç sisteminde güç sistemi kararlı kılıcısının (PSS) optimal tasarımı için iyimser sonuçlar bulmak için güçlü yetilere sahip HPA tekniği adında yeni bir hibrit yaklaşımı tanımlamaktadır. PSS parametrelerinin en uygun ayarlarının elde edilmesi için PSS parametrelerini seçme problemi, özdeğer tabanlı bir amaç fonksiyonu ile basit bir optimizasyon problemine çevrildi ve HPA tekniği kullanılarak çözüldü. Önerilen HPA tabanlı PSS tasarımının etkinliği özdeğer analizi, zaman domeni simülasyonları ve bazı performans indeksleri aracılığıyla farklı arızalar altındaki 3-makinalı 9-baralı güç sistemi üzerinde doğrulandı. Bu çalışmaların sonuçları, HPA algoritmasının PSS parametrelerinin ayarlanması için alternatif ve daha etkin bir iyileştirici olduğunu ve PSO ile ABC’ye oranla güç sisteminin dinamik kararlılığını büyük oranda artırdığını göstermiştir. Ayrıca hesaplama zamanı, yaklaşım hızı ve çözüm kalitesi açısından HPA algoritmasının PSO ve ABC’ye göre potansiyeli ve üstünlüğü kanıtlanmıştır.
PowSysGUI: A new educational software package for power system stability studies using MATLAB/Simulink
(SAGE, 2017-10-01) Ekinci, Serdar; Demirören, Ayşen; Zeynelgil, Hatice Lale
Graphical user interfaces have been progressively used in the classrooms to provide users of computer simulations with a friendly and visual approach to specify all input parameters with enhanced configuration flexibility. In this paper, an educational software package called PowSysGUI (Power System GUI), which runs on MATLAB and uses graphical user interfaces, has been developed for analysis and simulation of small to large size electric power systems. PowSysGUI is open-source software and anyone can see the inner structure of the program to figure out how to code a power engineering problem. It is designed as a simulation tool for researchers and educators, as it is simple to use and modify. PowSysGUI has algorithms for solving power flow, small signal stability analysis, and time-domain simulation. In the case studies, IEEE 16-machine 68-bus test system is given to show the features of the developed software tool. Moreover, classroom experience has shown that the developed software package helps in consolidating a better understanding of power system stability phenomena.
Improved kidney-inspired algorithm approach for tuning of PID controller in AVR system
(IEEE, 2019-03-22) Ekinci, Serdar; Hekimoğu, Baran
This paper proposes a novel tuning design of proportional integral derivative (PID) controller via an improved kidney-inspired algorithm (IKA) with a new objective function. The main objective of the proposed approach is to optimize the transient response of the AVR system by minimizing the maximum overshoot, settling time, rise time and peak time values of the terminal voltage, and eliminating the steady state error. After obtaining the optimal values of the three gains of the PID controller (K P , K I , and K D ) with the proposed approach, the transient response analysis was performed and compared with some of the current heuristic algorithms-based approaches in literature to show the superiority of the optimized PID controller. In order to evaluate the stability of the automatic voltage regulator (AVR) system tuned by IKA method, the pole/zero map analysis and Bode analysis are performed. Finally, the robustness analysis of the proposed approach has been carried out with variations in the parameters of the AVR system. The numerical simulation results demonstrated that the proposed IKA tuned PID controller has better control performances compared to the other existing approaches. The essence of the presented study points out that the proposed approach may successfully be applied for the AVR system.
An efficient noisy pixels detection model for CT images using extreme learning machines
(Sveuciliste Josipa Jurja Strossmayera u Osijeku, 2018-06) Çalışkan, Abidin; Çevik, Ulus
In this study, a new and rapid hidden resource decomposition method has been proposed to determine noisy pixels by adopting the extreme learning machines (ELM) method. The goal of this method is not only to determine noisy pixels, but also to protect critical structural information that can be used for disease diagnosis. In order to facilitate the diagnosis and also the treatment of patients in medicine, two-dimensional (2-D) images were calculated tomography (CT) which is obtained using medical imaging techniques. Utilizing a large number of CT images, promising results have been obtained from these experiments. The proposed method has shown a significant improvement on mean squared error and peak signal-to-noise ratio. The experimental results indicate that the proposed method is statistically efficient, and it has a good performance with a high learning speed. In the experiments, the results demonstrated that remarkable successive rates were obtained through the ELM method.
Parameter optimization of power system stabilizers via kidney-inspired algorithm
(SAGE, 2018-06-25) Ekinci, Serdar; Demiroren, Aysen; Hekimoğlu, Baran
This article describes the application of a new population-based meta-heuristic optimization algorithm inspired by the kidney process in the human body for the tuning of power system stabilizers (PSSs) in a multi-machine power system. The tuning problem of PSS parameters is formulated as an optimization problem that aims at maximizing the damping ratio of the electromechanical modes and the kidney-inspired algorithm (KA) is used to search for the optimal parameters. The efficacy of the KA-based PSS design was successfully tested on a well-known 16-machine, 68-bus power system. The obtained results are evaluated and compared with the other results obtained by the original particle swarm optimization (PSO) and the bat algorithm (BA) methods. From the detailed eigenvalue analysis, the nonlinear simulation studies and some performance indices it has been found out that for damping oscillations, the performance of the proposed KA approach in this study is better than that obtained by other intelligent techniques (PSO and BA). Moreover, the efficiency and the superior performance of the proposed method over the other two algorithms in terms of computation time, convergence rate and solution quality are confirmed.
Örüntü tanımada hopfield ağının kullanılması
(Batman Üniversitesi, 2012) Sezgin, Necmettin; Tekin, Ramazan; Çalışkan, Abidin
Bilgisayar teknolojisinin hızlı bir şekilde gelişmesi akıllı sistemlerin insan yaşamının birçok alanında kullanılmasını artırmıştır. Bu alanlardan birisi de alfa nümerik karakterlerin otomatik olarak doğru bir şekilde tanınması, istenen bir objenin tespit edilmesi ve seçilmesidir. Hopfield ağı, gürültülü veya bozuk olan desenin kısmi ipuçlarından ve önceden depolanmış desenlerden yararlanarak bu deseni düzeltebilen karakteristik bir yapıya sahiptir. Bu süreçte ağ, girdi örüntüsünde yapılan her ufak değişimin ardından örüntü enerjisini yeniden hesaplayarak morfolojik dönüşümünün kontrolünü sağlar ve bu örüntünün daha önce öğrendiği başka bir örüntüye yakınsamasını zorlar. Bu benzetişim işlemi, enerjideki değişkenlik durağan olana dek sürer. Nesnelerin otomatik olarak tanınması, seçilmesi ve işlenmesi gibi işlemden sorumlu bir ağın kullanıldığı akıllı sistemler özellikle robotik alanında önemli bir yere sahiptir. Bu çalışmada Hopfield ağ yapısını kullanarak örüntü tanıyan bir sistem geliştirilmeye çalışılmıştır.
Gabor dalgacık dönüşümü tabanlı yapay sinir ağı modeli ile zambak yaprağı imgelerinde pas hastalıklarının tespiti
(Batman Üniversitesi, 2012-06-01) Acar, Emrullah; Çalışkan, Abidin; Sezgin, Necmettin
Bitkilerdeki hastalıklar, hasadı ve dolayısıyla verimi etkilemektedir. Hastalıkların önceden kestirilmesi, çiftçilerin alacağı önlemler ile verimi artıracaktır. Verimi etkileyen önemli hastalıkların başında pas hastalığı gelmektedir. Bu çalışmada bitki örneği olarak, zirai uygulamalarla ilgili farklı zirai sitelerden bir uzman yardımıyla elde edilmiş zambak çiçeği yaprak imgeleri kullanılmış olup, Gabor dalgacık dönüşümü tabanlı yapay sinir ağı modeli ile pas hastalığını tespit eden bir sistem tasarlanmıştır. İlk aşamada, imgelere ilişkin Gabor dalgacık dönüşümü kullanılarak her bir sayısal imgeden ayrı bir özellik matrisi elde edilip, matrislerin ortalama, standart sapma ve entropi gibi istatistiksel değerleri hesaplanmıştır. Bu değerler öznitelik vektörüne eklenerek, her bir imge için bir öznitelik vektörü oluşturulmuştur. İkinci aşamada, Gabor dalgacık dönüşümü tabanlı öznitelik vektörleri yapay sinir ağı modelinin girişine verilerek sınıflandırma için performansı en iyi ağ yapısı belirlenmeye çalışılmıştır. Zambak çiçeği yaprak imgeleri iki (1-sağlıklı, 2- hastalıklı) grupta sınıflandırılmış olup sınıflandırma çalışmaları sonucunda, en iyi ortalama performansa %80,00 başarı ile yapay sinir ağı modelinin (3-25-1) ağ yapısında ulaştığı gözlemlenmiştir.
GLCM tabanlı k-nn sınıflandırıcı modeli ile avuç içi tanıma sistemi
(Batman Üniversitesi, 2012-06-01) Çalışkan, Abidin; Acar, Emrullah; Kaya, Yılmaz
K en yakın komşuluk algoritması, sınıflandırma problemini çözen bir algoritmadır. Sınıflandırma, yeni bir imgenin özniteliklerini inceleme ve bu imgeyi önceden tanımlanmış bir sınıfa atamaktır. Önemli olan, her bir sınıfın özelliklerinin önceden belirlenmiş olmasıdır.Bu çalışmada Hongkong Politeknik Üniversitesi veritabanına ait avuç içi imgeleri kullanılmıştır. El imgeleri ön işlemden geçirildikten sonra avuç içi imgeleri elde edilmiştir. Gri seviye eş oluşum matrisi (GLCM) metodu kullanılarak her bir imgeden öz nitelik parametreleri elde edilmiştir. Bu parametreler k en yakın komşuluk algoritması (k-NN) sınıflandırıcısının girişine verilerek performansı en iyi sistem tasarlanmıştır. Sonuç olarak en iyi performans k=1 komşuluk yapısında % 91.4 olarak gözlemlenmiştir.

Güncel Gönderiler