Browsing by Author "Yetkin, Emrullah Fatih"

Now showing 1 - 20 of 27

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
Applications of Eigenvalue Counting and Inclusion Theorems in Model Order Reduction
(Springer-Verlag Berlin, 2010) Yetkin, E. Fatih; Dağ, Hasan
We suggest a simple and an efficient iterative method based on both the Gerschgorin eigenvalue inclusion theorem and the deflation methods to compute a Reduced Order Model (ROM) to lower greatly the order of a given state space system. This method is especially efficient in symmetric state-space systems but it works for the other cases with some modifications.
Citation Count: 0
Assesment of soft error sensitivity of power flow analysis
(Gazi Univ, Fac Engineering Architecture, 2023) Yetkin, Emrullah Fatih
Today's power systems are large and interconnected to each other with many buses, lines, loads, and generators. Even the solution of a single snapshot of the system for specific conditions requires the solution of systems of equations with large sizes. Thus, to obtain the results in a reasonable time for large problems like electrical power flow simulations, modern large computational environments should be employed. However, because of the increasing number of components in the modern computational environment, the possibility of soft errors also increases. Soft errors can be defined as failures arising from several fluctuations due to x-rays, cosmic particle effects, etc. These types of errors usually appear at any time of computation as a bit-flip in any floating-point operations. In this paper, we will investigate the soft-error effects on large-scale power flow simulations. Generally, power flow calculations are performed by using Newton Raphson Method. The system is modeled by nonlinear equations and the solution process requires a linear solver is employed to take the inverse of the Jacobian matrix at each iteration. In this study, the soft-error sensitivity of the numerical methods used in load flow was examined, and the problems that may be encountered were revealed.
Citation Count: 3
Assessment of Load and Generation Modelling on the Quasi-Static Analysis of Distribution Networks
(Elsevier, 2021) Lamprianidou, I. S.; Papadopoulos, T. A.; Kryonidis, G. C.; Yetkin, E. Fatih; Pippi, K. D.; Chrysochos, A., I
Quasi-static analysis of power systems can be performed by means of timeseries-based and probability density function-based models. In this paper, the effect of different load and generation modelling approaches on the quasi-static analysis of distribution networks is investigated. Different simplified load and distributed renewable energy sources generation timeseries-based models are considered as well as probabilistic analysis. Moreover, a more sophisticated approach based on cluster analysis is introduced to identify harmonized sets of representative load and generation patterns. To determine the optimum number of clusters, a three-step methodology is proposed. The examined cases include the quasi-static analysis of distribution networks for different operational conditions to identify the simplified modelling approaches that can efficiently predict the network voltages and losses. Finally, the computational efficiency by using the simplified models is evaluated in temperature-dependent power flow analysis of distribution networks. (C) 2021 Elsevier Ltd. All rights reserved.
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.
Durağan Olmayan Bir Zaman Serisinde Değişim Noktalarının Graf Laplasyan ile Tespiti
(2024) Yıldız, Şeyma; Yetkin, Emrullah Fatih; Ballı, Tuğçe
Bu çalışma, durağan olmayan zaman serisi verilerinde değişim noktası tespiti problemine bir çözüm önermektedir. Literatürdeki genel yaklaşımların ötesinde, veri dinamiğine dayalı bir çözüm tasarlamak tahmin kalitesini artırabilmektedir. Bu çalışmada veri dinamiğine bağlı iki grafik tabanlı değişim noktası tespit algoritması önerilmektedir. İlk yaklaşımda Laplacian grafiği oluşturulur ve tespit için eşikten düşük özdeğerlerin sayısı kullanılır. İkinci yaklaşımda Fiedler vektörlerinin işaretleri kümeler halinde gruplandırılarak tespitte kullanılır. Önerilen algoritmaların asıl amacı veri özelliklerindeki değişimi tespit etmektir. Önerilen çözümlerin çıktıları gözlemlenerek değişikliklerin tespiti için başarılı tahminler yapılır. Bu çalışma, optimal bir sayısal algoritma kullanan bir özdeğer çözücü ile endüstriyel bir ortam için çevrimiçi değişim noktası tespit mekanizmasına uyarlanabilir.
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: 4
Generic Dynamic Load Modelling Using Cluster Analysis
(IEEE, 2018) Barzegkar-Ntovom, Georgios A.; Ceylan, Oğuzhan; Papadopoulos, Theofilos A.; Yetkin, E. Fatih
In this paper a new generic load modelling procedure is proposed based on the application of cluster analysis on load model parameters identified from measured dynamic responses. The performance of the proposed approach is assessed using measurements obtained from a low-voltage laboratory scale test configuration. In order to develop robust generalized load models applicable to a wide range of operating conditions different load compositions operating conditions and voltage disturbances are considered in the analysis. The findings of this paper verify the validity of the proposed generic modelling procedure and indicate robust results using the proposed methodology.
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.
Makine Öğrenmesinde Endüstriyel Veri Mahremiyetinin Üretken Düşman Ağları ve Diferansiyel Gizlilik Kullanarak Korunması
(2023) Hindistan, Yavuz Selim; Yetkin, Emrullah Fatih
Yapay Zeka (AI) ve Makine Öğreniminin (ML) hızla yaygınlaşması, mahremiyetin korunmasına ilişkin endişeleri artırdı. Bu teknolojiler, endüstriyel IoT, sosyal medya ve çevrimiçi platformlar gibi kaynaklardan kişisel ve hassas bilgiler içeren ve gizlilik riskleri getiren kapsamlı veri kümelerine dayanır. Güçlü gizlilik koruma önlemlerinin alınması, AI ve ML uygulama risklerini azaltmak için çok önemlidir. Bu tez, AI ve ML sistemlerinde gizliliğin korunmasını incelemektedir. Araştırmamız, ML doğruluğunu korurken bir gizlilik koruma yöntemi geliştirmek için herkese açık veri kümelerinden yararlandı. Gizliliği artırmak için, yaklaşımımızı Diferansiyel Gizlilik (DP) ve Üretken Düşman Ağları (GAN) ile güçlendirdik. Etkinliğini altı gizlilik ölçüsü kullanarak değerlendirdik. Yaklaşımımız, ML performansından ödün vermeden gizliliği koruyarak fizibilite ve etkinlik göstermektedir. Ayıklanan özellik alt kümeleri, ML modelleriyle hassas verileri açığa çıkarabildiğinden, gizli hassas bilgilerin ortaya çıkarılması vurgulanmıştır. Yöntemin mahremiyet endişelerini ele almadaki etkinliğini deneysel bir çalışmada gösteriyoruz. Bulgular, AI ve ML sistemlerinde gizliliğin anlaşılmasına katkıda bulunur. Araştırma, bilgileri korumak için içgörüler ve yaklaşımlar sunarak güvenilir ML sonuçları sağlar. Bu çalışma, gizlilik bilgisini ilerleterek, gizliliğin korunmasında AI ve ML teknolojilerinin sorumlu gelişimini destekler.
Citation Count: 2
A New Preconditioner Design Based on Spectral Division for Power Flow Analysis
(Praise Worthy Prize Srl, 2011) Dağ, Hasan; Yetkin, E. Fatih; Manguoglu, Murat
Solution of large sparse linear systems is the most lime consuming part in many power system simulations. Direct solvers based on LU factorization although robust are known to have limited satiability on parallel platforms. Thus. Krylov subspace based iterative methods (i.e. Conjugate Gradient method Generalized Minimal Residuals (GMRES) method) can be used as alternatives. To achieve competitive performance and robustness however the Krylov subspace methods need a suitable preconditioner. In this work we propose a new preconditioner iterative methods which can be used in Newton-Raphson process of power flow analysis. The suggested preconditioner employs the basic spectral divide and conquer methods and invariant subspaces for clustering the eigenvalues of the Jacobian matrix appearing in Newton-Raphson steps of power flow simulation. To obtain the preconditioner we use Matrix Sign Function (MSF) and to obtain the MSF itself we use Sparse Approximate Inverse (SPAI) algorithm with Newton iteration. We compare the convergence characteristics of our preconditioner against the well-known black-box preconditioners such as incomplete-LU and SPAI. Copyright (C) 2011 Praise Worthy Prize S.r.l. - All rights reserved.
Ölçeklenebilir Manifold Öğrenme Kütüphanesi Geliştirilmesi: Scaman
(2024) Pehlivan, Berke; Yetkin, Emrullah Fatih
This thesis presents an exploration of manifold learning and dimensionality reduction techniques, which are crucial in the fields of data science and machine learning. The center of this study is the development and evaluation of 'Scaman (Scalable Manifold Library), a Python-based computational tool designed to implement these techniques. This thesis investigates the key manifold learning algorithms. Including PCA,MDS, LE, and LLE and emphasizing the importance of eigenvalue solvers in these algorithms. The contribution of this thesis is the integration of advanced eigensolvers like NumPy, SLEPc and FEAST into key manifold algorithms within scaman package. The empirical analysis was conducted using various synthetic and real-world datasets. Those analyses focused on the efficiency, accuracy, and practical utility of scaman in different scenarios. Results demonstrate the tool's effectiveness, especially in handling large datasets. The advantages of FLANN and SLEPc prove scaman's efficiency in the creation of adjacency matrices and eigenvalue computation. The outcome of this thesis provides a computational tool for researchers and practitioners. Future directions include expanding the tool's capabilities by adding more algorithms, improving scalability, and applying various domain specific data-driven scenarios.
Citation Count: 3
On Soft Errors in the Conjugate Gradient Method: Sensitivity and Robust Numerical Detection
(SIAM PUBLICATIONS, 2020) Agullo, Emmanuel; Cools, Siegfried; Yetkin, Emrullah Fatih; Giraud, Luc; Schenkels, Nick; Vanroose, Wim
The conjugate gradient (CG) method is the most widely used iterative scheme for the solution of large sparse systems of linear equations when the matrix is symmetric positive definite. Although more than 60 years old, it is still a serious candidate for extreme-scale computations on large computing platforms. On the technological side, the continuous shrinking of transistor geometry and the increasing complexity of these devices affect dramatically their sensitivity to natural radiation and thus diminish their reliability. One of the most common effects produced by natural radiation is the single event upset which consists in a bit-flip in a memory cell producing unexpected results at the application level. Consequently, future extreme-scale computing facilities will be more prone to errors of any kind, including bit-flips, during their calculations. These numerical and technological observations are the main motivations for this work, where we first investigate through extensive numerical experiments the sensitivity of CG to bit-flips in its main computationally intensive kernels, namely the matrix-vector product and the preconditioner application. We further propose numerical criteria to detect the occurrence of such soft errors and assess their robustness through extensive numerical experiments.
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
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: 2
Parallel Implementation of Iterative Rational Krylov Methods for Model Order Reduction
(IEEE, 2009) Yetkin, Emrullah 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. ©2009 IEEE.
Recommendation of Data Visualization Tools for Non-Technical People
(Kadir Has Üniversitesi, 2019) Omran, Ahmet; Yetkin, Emrullah Fatih
Big data analysis and data science are promising trends. Visualization is critical part. It outlines and presents data as information from different perspectives. Consequently, leaders, decision makers, and end users will grasp concepts and identify patterns with new dimensions. However, while time is still a complex dimension, the number of Information Visualization (InfoVis) software tools are increasing rapidly. This research test out how non-technical people select their InfoVis tools. Generally, end-users have factors affect the selection process of a software tool. A survey is used to detect these features and relations in between. Finally, results are checked and analyzes using python functions of visualization and machine learning functions to outline the grouping of features to simplify the selection process of software visualization tools. The outcome of this research can be used as a general guide to easier understand software visualization capabilities and to compare these tools from end users' perspectives. A framework will be introduced to categorize and suggest InfoVis tools to end users.
Citation Count: 2
Recycling Newton-Krylov algorithm for efficient solution of large scale power systems
(Elsevier Sci Ltd, 2023) Yetkin, E. Fatih; Ceylan, Oguzhan
Power flow calculations are crucial for the study of power systems, as they can be used to calculate bus voltage magnitudes and phase angles, as well as active and reactive power flows on lines. In this paper, a new approach, the Recycling Newton-Krylov (ReNK) algorithm, is proposed to solve the linear systems of equations in Newton-Raphson iterations. The proposed method uses the Generalized Conjugate Residuals with inner orthogonalization and deflated restarting (GCRO-DR) method within the Newton-Raphson algorithm and reuses the Krylov subspace information generated in previous Newton runs. We evaluate the performance of the proposed method over the traditional direct solver (LU) and iterative solvers (Generalized Minimal Residual Method (GMRES), the Biconjugate Gradient Stabilized Method (Bi-CGSTAB) and Quasi-Minimal Residual Method (QMR)) as the inner linear solver of the Newton-Raphson method. We use different test systems with a number of busses ranging from 300 to 70000 and compare the number of iterations of the inner linear solver (for iterative solvers) and the CPU times (for both direct and iterative solvers). We also test the performance of the ReNK algorithm for contingency analysis and for different load conditions to simulate optimization problems and observe possible performance gains.
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.