Emrullah Fatih Yetkin

Yetkin, Emrullah Fatih

Name Variants

Y., Emrullah Fatih
Yetkin, E. F.
Emrullah Fatih, Yetkin
Yetkin, Emrullah Fatih
Yetkin, E.
Fatih Yetkin E.
Yetkin, EMRULLAH FATIH
E. Yetkin
YETKIN, Emrullah Fatih
Emrullah Fatih Yetkin
E. F. Yetkin
YETKIN, EMRULLAH FATIH
Yetkin,E.F.
Yetkin E.
Yetkin,Emrullah Fatih
Emrullah Fatih YETKIN
Y.,Emrullah Fatih
EMRULLAH FATIH YETKIN
Yetkin, Emrullah Fatih
E.,Yetkin
E. F. Yetkin
E.,Yetkin
Emrullah Fatih, Yetkin
Yetkin, E. Fatih

Job Title

Dr. Öğr. Üyesi

Email Address

fatih.yetkin@khas.edu.tr

ORCID ID

0000-0003-1115-4454

Full item page

Scholarly Output

25

Articles

13

Citation Count

8

Supervised Theses

3 Scholarly Output Search Results

Now showing 1 - 10 of 25

Citation Count: 1
A Scalable Unsupervised Feature Selection With Orthogonal Graph Representation for Hyperspectral Images
(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Taskin, Gulsen; Yetkin, E. Fatih; Camps-Valls, Gustau
Feature selection (FS) is essential in various fields of science and engineering, from remote sensing to computer vision. Reducing data dimensionality by removing redundant features and selecting the most informative ones improves machine learning algorithms' performance, especially in supervised classification tasks, while lowering storage needs. Graph-embedding (GE) techniques have recently been found efficient for FS since they preserve the geometric structure of the original feature space while embedding data into a low-dimensional subspace. However, the main drawback is the high computational cost of solving an eigenvalue decomposition problem, especially for large-scale problems. This article addresses this issue by combining the GE framework and representation theory for a novel FS method. Inspired by the high-dimensional model representation (HDMR), the feature transformation is assumed to be a linear combination of a set of univariate orthogonal functions carried out in the GE framework. As a result, an explicit embedding function is created, which can be utilized to embed out-of-samples into low-dimensional space and provide a feature relevance score. The significant contribution of the proposed method is to divide an $n$ -dimensional generalized eigenvalue problem into $n$ small-sized eigenvalue problems. With this property, the computational complexity (CC) of the GE is significantly reduced, resulting in a scalable FS method, which could be easily parallelized too. The performance of the proposed method is compared favorably to its counterparts in high-dimensional hyperspectral image (HSI) processing in terms of classification accuracy, feature stability, and computational time.
Citation Count: 1
Active and Reactive Power Load Profiling Using Dimensionality Reduction Techniques and Clustering
(Institute of Electrical and Electronics Engineers Inc., 2019) Yetkin, E. Fatih; Ceylan, Oğuzhan; Papadopoulos, Theofilos A.; Kazaki, Anastasia G.; Barzegkar-Ntovom, Georgios A.
This paper proposes a methodology to characterize active and reactive power load profiles. Specifically, the approach makes use of fast Fourier Transform for conversion into frequency domain, principle component analysis to reduce the dimension and K-means++ to determine the representative load profiles. The data set consists of five-year measurements taken from the Democritus University of Thrace Campus. Test days were also classified as working and non-working. From the results it is observed that the proposed methodology determines representative load profiles effectively both regarding active and reactive power.
Citation Count: 0
On the Selection of Interpolation Points for Rational Krylov Methods
(Springer-Verlag Berlin, 2012) Yetkin, E. Fatih; Dağ, Hasan
We suggest a simple and an efficient way of selecting a suitable set of interpolation points for the well-known rational Krylov based model order reduction techniques. To do this some sampling points from the frequency response of the transfer function are taken. These points correspond to the places where the sign of the numerical derivation of transfer function changes. The suggested method requires a set of linear system's solutions several times. But they can be computed concurrently by different processors in a parallel computing environment. Serial performance of the method is compared to the well-known H-2 optimal method for several benchmark examples. The method achieves acceptable accuracies (the same order of magnitude) compared to that of H-2 optimal methods and has a better performance than the common selection procedures such as linearly distributed points.
Citation Count: 0
Comparative Classification Performances of Filter Model Feature Selection Algorithms in Eeg Based Brain Computer Interface System
(Gazi Univ, Fac Engineering Architecture, 2023) Bulut, Cem; Balli, Tugce; Yetkin, E. Fatih
Brain-computer interface (BCI) systems enable individuals to use a computer or assistive technologies such as a neuroprosthetic arm by translating their brain electrical activity into control commands. In this study, the use of filter-based feature selection methods for design of BCI systems is investigated. EEG recordings obtained from a BCI system designed for the control of a neuroprosthetic device are analyzed. Two feature sets were created; the first set was band power features from six main frequency bands (delta (1.0-4 Hz), theta (4-8 Hz), alpha (8-12 Hz), beta (12-25 Hz), high-beta (25-30Hz) and gamma (30-50 Hz)) and the second set was band power features from ten frequency sub-bands (delta (1-4 Hz), theta (4-8 Hz), alpha1 (8-10 Hz), alpha2 (10-12 Hz), beta1 (12-15 Hz), beta2 (15-18 Hz), beta3 (18-25 Hz), gamma1 (30-35 Hz), gamma2 (35-40 Hz), gamma3 (40-50 Hz)). Ten filter-based feature selection methods are investigated along with linear discriminant analysis, random forests, decision tree and support vector machines algorithms. The results indicate that feature selection methods leads to a higher classification accuracy and eigen value centrality (Ecfs) and infinite feature selection (Inffs) methods have consistently provided higher accuracy rates as compared to rest of the feature selection methods.
Citation Count: 0
Parallel Implementation Of Iterative Rational Krylov Methods For Model Order Reduction
(IEEE, 2010) Yetkin, E. Fatih; Dağ, Hasan
Model order reduction (MOR) techniques are getting more important in large scale computational tasks like large scale electronic circuit simulations. In this paper we present some experimental work on multiprocessor systems for rational Krylov methods. These methods require huge memory and computational power especially in large scale simulations. Therefore these methods are fairly suitable for parallel computing.
Citation Count: 1
Filtre Modelli Öznitelik Seçim Algoritmalarının Eeg Tabanlı Beyin Bilgisayar Arayüzü Sistemindeki Karşılaştırmalı Sınıflandırma Performansları
(2023) Bulut, Cem; Ballı, Tuğçe; Yetkin, E. Fatih
Beyin bilgisayar arayüzleri (BBA), beyin elektriksel aktivitelerini kontrol komutlarına çevirerek bilgisayar veya nöroprostetik kol gibi yardımcı teknolojilerin kullanılmasını sağlayan sistemlerdir. Bu çalışmada filtre tabanlı öznitelik seçim yöntemlerinin farklı sınıflandırma algoritmaları ile birlikte kullanılmasının BBA sistemlerine getirebileceği kazanımlar araştırılmıştır. Bu çerçevede nöroprostetik bir cihazın kontrolü için tasarlanan BBA sisteminden elde edilmiş EEG kayıtları analiz edilmiştir. EEG kayıtlarının analizi için delta (1.0-4 Hz), teta (4-8 Hz), alfa (8-12 Hz), beta (12-25 Hz), yüksek-beta (25-30Hz) ve gama (30-50 Hz) frekans bantlarından ve delta (1-4 Hz), teta (4-8 Hz), alfa1 (8-10 Hz), alfa2 (10-12 Hz), beta1 (12-15 Hz), beta2 (15-18 Hz), beta3 (18-25 Hz), gama1 (30-35 Hz), gama2 (35-40 Hz), gama3 (40-50 Hz) alt frekans bantlarından bant gücü öznitelikleri çıkarılmıştır. Elde edilen iki veri seti öznitelik seçimi uygulamadan ve öznitelik seçimi uygulayarak sınıflandırılmıştır. Çalışmada toplam 10 adet filtre tabanlı öznitelik seçimi yöntemi ile birlikte, doğrusal ayırt eden analizi, rassal ormanlar, karar ağaçları ve destek vektör makinaları sınıflandırma algoritmaları kullanılmıştır. Çalışma sonucunda EEG kayıtlarının sınıflandırılması için öznitelik seçme algoritmalarının uygulanmasının daha yüksek başarımlı sonuçlar verdiği ve bu çalışmada ele alınan öznitelik seçme yöntemlerinden, özdeğer merkeziyetine göre öznitelik seçimi (Ecfs) ve sonsuz öznitelik seçimi (Inffs) yöntemlerinin filtre tabanlı yaklaşımlar arasında en iyi sonuçları verdiği gözlenmiştir.
Citation Count: 0
A Sparsity-Preserving Spectral Preconditioner for Power Flow Analysis
(TUBITAK Scientific & Technical Research Council Turkey, 2016) Yetkin, Emrullah Fatih; Dağ, Hasan
Due to the ever-increasing demand for more detailed and accurate power system simulations the dimensions of mathematical models increase. Although the traditional direct linear equation solvers based on LU factorization are robust they have limited scalability on the parallel platforms. On the other hand simulations of the power system events need to be performed at a reasonable time to assess the results of the unwanted events and to take the necessary remedial actions. Hence to obtain faster solutions for more detailed models parallel platforms should be used. To this end direct solvers can be replaced by Krylov subspace methods (conjugate gradient generalized minimal residuals etc.). Krylov subspace methods need some accelerators to achieve competitive performance. In this article a new preconditioner is proposed for Krylov subspace-based iterative methods. The proposed preconditioner is based on the spectral projectors. It is known that the computational complexity of the spectral projectors is quite high. Therefore we also suggest a new approximate computation technique for spectral projectors as appropriate eigenvalue-based accelerators for efficient computation of power flow problems. The convergence characteristics and sparsity structure of the preconditioners are compared to the well-known black-box preconditioners such as incomplete LU and the results are presented.
Citation Count: 0
Güç akışı analizinin geçici hata duyarlılığının değerlendirilmesi
(2023) Yetkin, Emrullah Fatih
Günümüzün güç sistemleri detaylı modelleme ihtiyaçları nedeniyle çok büyük boyutlara ulaşabilmektedir ve belirli koşullar için sistemin tek bir anlık görüntüsünün çözümü bile büyük boyutlu denklem sistemlerinin çözümünü gerektirir. Bu nedenle de makul bir sürede sonuçları elde etmek için modern yüksek başarımlı hesaplama ortamları kullanılmalıdır. Bununla birlikte, yüksek başarımlı hesaplama ortamlarında artan bileşen sayısı nedeniyle, geçici hata olasılığı da artar. Geçici hatalar, x-ışınları, kozmik parçacık etkileri gibi nedenlerle cihaz bileşenlerinde oluşabilen çeşitli dalgalanmalardan kaynaklı arızalar olarak tanımlanabilir. Bu tür hatalar genellikle herhangi bir hesaplama anında herhangi bir kayan nokta işleminde yaşanan bir bit- kayması ile modellenebilir. Bu makalede, büyük ölçekli güç akışı simülasyonları üzerindeki geçici hata etkileri incelenmektedir. Genel olarak yük akışı hesaplamaları, sistem doğrusal olmayan denklemlerle modellendiği için, Newton-Raphson yöntemi kullanılarak yapılır ve çözüm süreci, her yinelemede Jakobiyen matrisinin tersini almak için doğrusal bir çözücünün kullanılmasını gerektirir. Bu çalışmada, özellikle yenilenebilir enerji kaynaklarının sistemlere eklenmesi ile çok büyük boyutlara ulaşılabilen elektrik yük akış problemlerinde kullanılan matematiksel yöntemlerin geçici-hatalara karşı hassasiyetleri incelenerek, karşılaşılabilecek sorunlar ortaya konulmuştur.
Citation Count: 3
A Hybrid Approach With Gan and Dp for Privacy Preservation of Iiot Data
(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Hindistan, Yavuz Selim; Yetkin, E. Fatih
There are emerging trends to use the Industrial Internet of Things (IIoT) in manufacturing and related industries. Machine Learning (ML) techniques are widely used to interpret the collected IoT data for improving the company's operational excellence and predictive maintenance. In general, ML applications require high computational resource allocation and expertise. Manufacturing companies usually transfer their IIoT data to an ML-enabled third party or a cloud system. ML applications need decrypted data to perform ML tasks efficiently. Therefore, the third parties may have unacceptable access rights during the data processing to the content of IIoT data that contains a portrait of the production process. IIoT data may include hidden sensitive features, creating information leakage for the companies. All these concerns prevent companies from sharing their IIoT data with third parties. This paper proposes a novel method based on the hybrid usage of Generative Adversarial Networks (GAN) and Differential Privacy (DP) to preserve sensitive data in IIoT operations. We aim to sustain IIoT data privacy with minimal accuracy loss without adding high additional computational costs to the overall data processing scheme. We demonstrate the efficiency of our approach with publicly available data sets and a realistic IIoT data set collected from a confectionery production process. We employed well-known privacy six assessment metrics from the literature and measured the efficiency of the proposed technique. We showed, with the help of experiments, that the proposed method preserves the privacy of the data while keeping the Linear Regression (LR) algorithms stable in terms of the R-Squared accuracy metric. The model also ensures privacy protection for hidden sensitive data. In this way, the method prevents the production of hidden sensitive data from the sub-feature sets.
Citation Count: 0
A Topology Detector Based Power Flow Approach for Radial and Weakly Meshed Distribution Networks
(Ieee, 2024) Yetkin, E. Fatih; Ceylan, Oguzhan; Pisica, Ioana; Ozdemir, Aydogan
Power distribution networks may need to be switched from one radial configuration to another radial structure, providing better technical and economic benefits. Or, they may also need to switch from a radial configuration to a meshed one and vice-versa due to operational purposes. Thus the detection of the structure of the grid is important as this detection will improve the operational efficiency, provide technical benefits, and optimize economic performance. Accurate detection of the grid structure is needed for effective load flow analysis, which becomes increasingly computationally expensive as the network size increases. To perform a proper load flow analysis, one has to build the distribution load flow (DLF) matrix from scratch cost of which is unavoidable with the growing size of the network. This will considerably increase the computation time when the system size increases, compromising applicability in online implementations. In this study we introduce a novel graph-based model designed to rapidly detect transitions between radial and weakly meshed systems. By leveraging the characteristic properties of Sparse Matrix-Vector product (SpMV) operations, we accelerate power flow calculations without necessitating the complete reconstruction of the DLF matrix. With this approach we aim to reduce the computational costs and to improve the feasibility of near-online implementations.