Browsing by Author "Dağ, Hasan"

Now showing 1 - 20 of 59

The Performance Wise Comparison of the Most Widely Used Nosql Databases
(Kadir Has Üniversitesi, 2015) Aladily, Ahmed; Dağ, Hasan
This work deals with the comparison of the most widely used noSQL databases. Chapter one deals in great details with the SQL databases and the noSQL databases including characteristics and the four types of noSQL databases, the second Chapter deals with the characteristics of the SQL and noSQL databases and the main differences between SQL databases and the noSQL databases. The third chapter deals with the architecture of the Couchdb, Mongodb, Cassandra, and Hbase. Chapter four deals with installation of the Couchdb, Mongodb, Cassandra and Hbase and Chapter five deals with analysis of the four noSQL databases and it also includes the performance wise comparison.
Post-outage state estimations for outage management
(IFAC Secretariat, 2011) Ceylan, Oğuzhan; Ozdemir, Aydogan; Dağ, Hasan
Real time outage information is required to the utility operators for outage management process. In addition to some basic information regarding the outage post-outage system status will help to improve the response to outages and management of system reliability. This paper presents particle swarm optimization based reactive power estimations for branch outages. Post outage voltage magnitudes and reactive power flows results for IEEE 14 and IEEE 30 bus systems are given. Simulation results show that post outage voltage magnitudes and reactive power flows can be computed with a reasonable accuracy. © 2011 IFAC.
Citation - Scopus: 1
Heterosim: Heterogeneous Simulation Framework
(Association for Computing Machinery, 2009) Dursun, Taner; Dağ, Hasan
In order to arrange heterogeneous simulation executions it would be useful to have simulation tools that enable easy and fast creation of simulation sessions employing real-time software components beside simulation codes. Although there have been considerable amount of research activities in simulation community the current simulation tools are not sufficiently capable to support such a cooperation between components working in real-time and simulation-time. In this paper we propose a new approach for constructing hybrid simulations that leverages usage of simulation systems. We introduce HeteroSim a Java-based simulation system that can execute discrete event simulations by employing both simulation and real world software entities. This model is applicable to many software related areas such as scenario-based software testing and development of simulators. As a case study we are able to rely on this model in order to build simulations combining both the simulated elements of a High Performance Computing (HPC) system and already implemented elements of our Policy Based Management (PBM) framework so-called POLICE [1][2]. In this manner it may be possible to study the efficiency of POLICE on management of HPC systems.
Citation - WoS: 2
Citation - Scopus: 6
Branch Outage Simulation Based Contingency Screening by Gravitational Search Algorithm
(Praise Worthy Prize Srl, 2012) Ceylan, Oğuzhan; Özdemir, Aydoğan; Dağ, Hasan
Power systems contingency analysis is an important issue for electric power system operators. This paper performs branch outage simulation based contingency screening using a bounded network approach. Local constrained optimization problem representing the branch outage phenomena is solved by the gravitational search algorithm. The proposed method is applied to IEEE 14 30 57 and 118 Bus Test systems and its performance from the point of capturing violations is evaluated. In addition false alarms and the computational accuracy of the proposed method are also analyzed by using scattering diagrams. Finally the proposed gravitational search based contingency screening is compared with full AC load flow solutions from the point of computational speed. Copyright (C) 2012 Praise Worthy Prize S.r.l. - All rights reserved.
Citation - WoS: 5
Citation - Scopus: 5
Heuristic Methods for Postoutage Voltage Magnitude Calculations
(TUBITAK Scientific & Technical Research Council Turkey, 2016) Ceylan, Oğuzhan; Özdemir, Aydogan; Dağ, Hasan
Power systems play a significant role in every aspect of our daily lives. Hence their continuation without any interruption (or with the least duration of interruption due to faults or scheduled maintenances) is one of the key aims of electrical energy providers. As a result electrical energy providers need to check in great detail the integrity of their power systems by performing regular contingency studies of the equipment involved. Among others line and transformer outage simulations constitute an integral part of an electrical management system. Both accuracy and calculation speed depend on the branch outage model and/or the solution algorithms applied. In this paper the local constrained optimization problem of the single-branch outage problem is solved by intelligent methods: particle swarm optimization differential evolution and harmony search. Simulations of IEEE 14- 30- 118- and 300 -bus systems are computed both by intelligent methods and by AC load flow. The results of the intelligent method -based simulations and AC load flow -based simulations are compared in terms of accuracy and computation speed.
Citation - WoS: 3
Citation - Scopus: 6
Machine Learning Model To Predict an Adult Learner's Decision To Continue Esol Course or Not
(Springer, 2019) Dahman, Mohammed R.; Dağ, Hasan
This study investigated the ability of the demographic and the affective variables to predict the adult learners' decision to continue ESOL courser. 278 adult learners, enrolled on ESOL course at FLS institution in Istanbul, Turkey, participated in the study. The result showed that the continued or dropped out groups, demonstrated statistical differences in the demographic variable (the placement test score) with a magnitude of large effect size (.378). Additionally, the result showed the effect size in the perception of the affective variables (motivation, attitude, and anxiety), accounts for about 50% of the variation between the continuation and dropout groups. Following that, three machine learning models were proposed; all possible subset regression analysis was used to compare the three models. The adequate model, which fitted the demographic variable (the placement test score) and the affective variables (motivation, attitude, and anxiety), correctly predicted 83.3% of the adult learners' decision to continue ESOL course. The model showed about 68% goodness-of-fit. The cultural implications of these findings are discussed, along with suggestions for future research.
Citation - WoS: 3
A Recommender Model Based on Trust Value and Time Decay Improve the Quality of Product Rating Score in E-Commerce Platforms
(IEEE, 2017) Işık, Muhittin; Dağ, Hasan
Most of the existing products rating score algorithms do not take fake accounts and time decay of users' ratings into account when creating the list of recommendations. The trust values and the time decay of users' ratings to an item may improve the quality of product rating score in e-commerce platforms especially when it is thought that nowadays the majority of customers read the reviews before making a purchase. In this paper we first introduce the concept trust value of users by explaining its mathematical definition and redefine the product rating score based on users' trust relationship. Then we calculate the product rating score based on time decay by making the concept time decay clear. After that we execute both algorithms together in order to show their both effects on the quality of product rating score. Finally we present experimentally effectiveness of three approaches on a large real dataset.
Citation - WoS: 39
Citation - Scopus: 54
Feature Extraction Based on Deep Learning for Some Traditional Machine Learning Methods
(Institute of Electrical and Electronics Engineers Inc., 2018) Çayır, Aykut; Yenidoğan, Işıl; Dağ, Hasan
Deep learning is a subfield of machine learning and deep neural architectures can extract high level features automatically without handcraft feature engineering unlike traditional machine learning algorithms. In this paper, we propose a method, which combines feature extraction layers of a convolutional neural network with traditional machine learning algorithms, such as, support vector machine, gradient boosting machines, and random forest. All of the proposed hybrid models and the above mentioned machine learning algorithms are trained on three different datasets: MNIST, Fashion-MNIST, and CIFAR-10. Results show that the proposed hybrid models are more successful than traditional models while they are being trained from raw pixel values. In this study, we empower traditional machine learning algorithms for classification using feature extraction ability of deep neural network architectures and we are inspired by transfer learning methodology to this.
Citation - WoS: 2
Citation - Scopus: 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.
Bellek Tabanli Verı Platformların Karşılaştırması
(Kadir Has Üniversitesi, 2016) Akbari, Amirmahdi; Dağ, Hasan
Bellek tabanli verı platformların karşılaştırması
Random Capsule Network (capsnet) Forest Model for Imbalanced Malware Type Classification Task
(Kadir Has Üniversitesi, 2021) Çayır, Aykut; Dağ, Hasan
Behavior of malware varies depending the malware types, which affect the strategies of the system protection software. Many malware classification models, empowered by machine and/or deep learning, achieve superior accuracy for predicting malware types. Machine learning-based models need to do heavy feature engineering work, which affects the performance of the models greatly. On the other hand, deep learning-based models require less effort in feature engineering when compared to that of the machine learning-based models. However, traditional deep learning architectures' components, such as max and average pooling, cause architecture to be more complex and the models to be more sensitive to data. The capsule network architectures, on the other hand, reduce the aforementioned complexities by eliminating the pooling components. Additionally, capsule network architectures based models are less sensitive to data, unlike the classical convolutional neural network architectures. This thesis proposes an ensemble capsule network model based on the bootstrap aggregating technique. The proposed method is tested on two widely used, highly imbalanced datasets (Malimg and BIG2015), for which the-state-of-the-art results are well-known and can be used for comparison purposes. The proposed model achieves the highest F-Score, which is 0.9820, for the BIG2015 dataset and F-Score, which is 0.9661, for the Malimg dataset. Our model also reaches the-state-of-the-art, using 99.7% lower the number of trainable parameters than the best model in the literature.
Power consumption estimation using in-memory database computation
(Kadir Has Üniversitesi, 2016) Alamin, Mohamed; Dağ, Hasan
Son elektrik tüketimini tahmin etmek amacıyla, hız ve güvenilirliği artırmak gerekir. hız ile ilgili olarak, birçok kat daha hızlı HDD den veri manipüle sağlar en iyi çözümdür IN-Bellek veritabanını kullanır. Bu amaçla, biz "en iyi" açık kaynak In-Memory veritabanı gibi YCSB gibi standart bir kriter kullanarak seçmeniz gerekir. güvenilirlik için, makine öğrenimi algoritmalarını kullanmaktadır. Model performans ve doğruluk verilerine her zaman bağlı olarak değişebilir bu yana, birçok algoritmalar test etmek ve en iyisini seçmek. Bu tezde, Python ve Aerospike bellek veritabanında öğrenme makinesi kullanılarak elektrik tüketimini tahmin etmek Londra Hanehalkı SmartMeter Enerji Tüketimi Verileri kullanın. Çalışma veri seti için en iyi algoritma Torbalama olduğunu göstermektedir. Biz de Ar-kare her zaman en iyi algoritma seçmek için iyi bir test olmadığını kanıtlamak. Son olarak, biz belirli bir zamanda tüketimini tahmin etmek deneyimli olmayan kullanıcılar tarafından kullanılabilir Python kullanarak makine öğrenimi, bir grafiksel kullanıcı arabirimi öneriyoruz
Citation - Scopus: 15
Branch outage solution using particle swarm optimization
(2008) Ceylan, Oğuzhan; Ozdemir, Aydogan; Dağ, Hasan
For post outage MW line flows and voltage magnitude calculations most of the methods use linear methods because of their simplicity. Especially for reactive power flow calculations one can face high errors. In this paper we use a minimization method that minimizes the errors resulting from the linear system model implementation. We solve the optimization problem using particle swarm optimization. We give some outage examples using IEEE 14 bus IEEE 30 bus and IEEE 57 bus data and compare the results with full ac load flow calculation. © 2008 Australasian Universities Power Engineering Conference (AUPEC'08).
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 - WoS: 6
Citation - Scopus: 7
Alternative Credit Scoring and Classification Employing Machine Learning Techniques on a Big Data Platform
(Institute of Electrical and Electronics Engineers Inc., 2019) Hindistan, Yavuz Selim; Kiyakoğlu, Burhan Yasin; Rezaeinazhad, Arash Mohammadian; Korkmaz, Halil Ergun; Dağ, Hasan
With the bloom of financial technology and innovations aiming to deliver a high standard of financial services, banks and credit service companies, along with other financial institutions, use the most recent technologies available in a variety of ways from addressing the information asymmetry, matching the needs of borrowers and lenders, to facilitating transactions using payment services. In the long list of FinTechs, one of the most attractive platforms is the Peer-to-Peer (P2P) lending which aims to bring the investors and borrowers hand in hand, leaving out the traditional intermediaries like banks. The main purpose of a financial institution as an intermediary is of controlling risk and P2P lending platforms innovate and use new ways of risk assessment. In the era of Big Data, using a diverse source of information from spending behaviors of customers, social media behavior, and geographic information along with traditional methods for credit scoring prove to have new insights for the proper and more accurate credit scoring. In this study, we investigate the machine learning techniques on big data platforms, analyzing the credit scoring methods. It has been concluded that on a HDFS (Hadoop Distributed File System) environment, Logistic Regression performs better than Decision Tree and Random Forest for credit scoring and classification considering performance metrics such as accuracy, precision and recall, and the overall run time of algorithms. Logistic Regression also performs better in time in a single node HDFS configuration compared to a non-HDFS configuration.
Predicting Electricity Consumption Using Machine Learning Models With R and Python
(Kadir Has Üniversitesi, 2016) El Oraıby, Maryam; Dağ, Hasan
Electricity load forecasting has become an important field of interest in the last years. Antic- ipating the energy usage is vital to manage resources and avoid risk. Using machine learning techniques it is possible to predict the electricity consumption in the future with high accuracy. This study proposes a machine learning model for electricity usage prediction based on size and time. For that aim multiple predictive models are built and evaluated using two powerful open source tools for machine learning R and Python. The data set used for modeling is publicly accessible and contains real electrical data usage of industrial and commercial buildings from EnerNOC. This type of analysis falls within the electricity demand management.
Citation - Scopus: 6
Parallel-In Implementation of Transient Stability Analysis on a Linux Cluster With Infiniband
(IEEE, 2012) Soykan, Gürkan; Flueck, Alexander J.; Dağ, Hasan
On-line transient stability analysis is an inevitable way to provide real time power system security and control. Parallel computing is one of the most viable ways to perform on-line transient stability analysis. This paper presents the performance results of a parallel-in-space algorithm based on a multilevel partitioning scheme on an Infiniband cluster system. The algorithm decreases the transient stability simulation time using METIS for partitioning in conjunction with the linearized update solution process of the Very Dishonest Newton Method when solving the differential-algebraic systems of equations [1]. Two real power systems a 3493-bus system with 844 generators and a 7935-bus system with 2135 generators are tested on a Linux-cluster system with 16 nodes. Each node has 2 multicore processors and is connected to each other by Infiniband network. The properties of a test system have a large impact on the performance of the parallel algorithm used since it affects communication duration. © 2012 IEEE.
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 - Scopus: 5
Double Branch Outage Modeling and Its Solution Using Differential Evolution Method
(2011) Ceylan, Oğuzhan; Ozdemir, Aydogan; Dağ, Hasan
Power system operators need to check the system security by contingency analysis which requires power flow solutions repeatedly. AC power flow is computationally slow even for a moderately sized system. Thus fast and accurate outage models and approximated solutions have been developed. This paper adopts a single branch outage model to a double branch outage one. The final constrained optimization problem resulted from modeling is then solved by using differential evolution method. Simulation results for IEEE 30 and 118 bus test systems are presented and compared to those of full AC load flow in terms of solution accuracy. © 2011 IEEE.
Applying Machine Learning Algorithms in Sales Prediction
(Kadir Has Üniversitesi, 2019) Sekban, Judi; Dağ, Hasan
Makine öğrenimi bir çok endüstride üzerinde yoğun çalışmalar yapılan bir konu olmuştur, ve neyse ki şirketler kendi problemlerini çözebilecek çeşitli machine learning yaklaşımları hakkında günden güne daha fazla bilgi sahibi oluyorlar. Fakat, farklı makine öğreniminin modellerinden en iyi şekilde sonuç almak ve verimli sonuçlara ulaşabilmek için, modellerin uygulanış biçimlerini ve verinin doğasını iyi anlamak gerekir. Bu tez, belli bir tahmin görevi için, uygulanan farklı makine öğreniminin algoritmalarını ne kadar iyi sonuç verdiklerini araştırır. Bu amaçla tez, 4 faklı algoritma, bir istifleme topluluğu tekniği ve modeli geliştirmek için belirli bir özelllik seçme yaklaşımı sunar ve uygular. Farklı konfigürasyonlar uygulayarak sonuçlar birbiriyle test edilir. Bütün bu işlemler, gerekli veri önislemeleri ve özellik mühendisliği adımları tamamlandıktan sonra yapılır.