31 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 31
Öğe Coordinated design of TCSC and PSS by using PSO algorithm for enhancement of SMIB power system stability(Batman Üniversitesi, 2017) Ekinci, Serdar; Hekimoğlu, BaranThe main aim of this study is to investigate the enhancement of power system stability via individual and coordinated design of Thyristor Controlled Series Compensation (TCSC) and Power System Stabilizer (PSS) in single machine infinite bus (SMIB) power system. The coordinated design problem of PSS and TCSC-based controllers is formulated as an optimization problem with an eigenvalue-based objective function. Then, particle swarm optimization (PSO) algorithm is applied to search for optimal controller parameters. To compare the performance of PSS and TCSC-based controllers, both of them are designed independently at first and then in a coordinated manner for individual and coordinated applications. The proposed stabilizers are tested on a weakly connected power system subjected to various disturbances. The eigenvalue analysis and nonlinear simulation results show the robustness and the effectiveness of the proposed controllers and their ability to provide efficient damping of low frequency oscillations. Matlab/SIMULINK software package is used for the simulations.Öğe A novel approach for spam email detection based on shifted binary patterns(Wiley-Blackwell, 2016-01-11) Kaya, Yılmaz; Ertuğrul, Ömer FarukAdvances in communication allow people flexibility to communicate in various ways. Electronic mail (email) is one of the most used communication methods for personal or business purposes. However, it brings one of the most tackling issues, called spam email, which also raises concerns about data safety. Thus, the requirement of detecting spams is crucial for keeping the users safe and saving them from the waste of time while tackling those issues. In this study, an effective approach based on the probability of the usage of the characters that has similar orders with respect to their UTF-8 value by employing shifted one-dimensional local binary pattern (shifted-1D-LBP) was used to extract quantitative features from emails for spam email detection. Shifted-1D-LBP, which can be described as an ordered set of binary comparisons of the center value with its neighboring values, is a content-based approach to spam detection with low-level information. To validate the performance of the proposed approach, three benchmark corpora, Spamassasian, Ling-Spam, and TREC email corpuses, were used. The average classification accuracies of the proposed approach were 92.34%, 92.57%, and 95.15%, respectively. Analysis and promising experimental results indicated that the proposed approach was a very competitive feature extraction method in spam email filtering.Öğe Forecasting financial indicators by generalized behavioral learning method(Springer Nature, 2017-08-09) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminForecasting financial indicators (indexes/prices) is a complex and a quite difficult issue because they depend on many factors such as political events, financial ratios, and economic variables. Also, the psychological facts or decision-making styles of investors or experts are other major reasons for this difficulty. In this study, a generalized behavioral learning method (GBLM) was employed to forecast financial indicators, which are the indexes/prices of 34 different financial indicators (24 stock indexes, 2 forexes, 3 financial futures, and 5 commodities). The achieved results were compared with the reported results in the literature and the obtained results by artificial neural network, which is widely used and suggested for forecasting financial indicators. These results showed that GBLM can be successfully employed in short-term forecasting financial indicators by detecting hidden market behavior (pattern) from their previous values. Also, the results showed that GBLM has the ability to track the fluctuation and the main trend.Öğe Determining relevant features in estimating short-term power load of a small house via feature selection by extreme learning machine(IEEE, 2017-11-02) Ertuğrul, Ömer Faruk; Sezgin, Necmettin; Öztekin, Abdulkerim; Tağluk, Mehmet EminEstimating short-term power load is a fundamental issue in the power distribution system. Since short-term power load is related to many parameters such as weather conditions, and time. The aim of this study is to determine the relevant parameters in estimating short-term power load not only in order to decrease the computational cost, but also to achieve higher success rates. Furthermore, by using selected features the required memory, equipment and communication costs are also decreased in real time applications. Feature selection by extreme learning machine method was used in determining relevant features. The short-term power loads of two houses (one of them has a power generation capability) were used in tests and achieved results showed lower error rates were obtained by using less number of features.Öğe Grasshopper optimization algorithm for automatic voltage regulator system(IEEE, 2018-06-21) Ekinci, Serdar; Hekimoğu, BaranA novel design method is presented to determine optimum proportional-integral-derivative (PID) controller parameters of an automatic voltage regulator (AVR) system utilizing the grasshopper optimization algorithm (GOA). The proposed approach is a simple and effective algorithm that is able to solve many optimization problems even those with unknown search spaces effectively. The simplicity of algorithm provides high quality tuning of optimal PID controller parameters. The integral of time weighted squared error (ITSE) is used as the performance index to confirm the performance of the proposed GOA-PID controller. When compared to the other PID controllers based on Ziegler- Nichols (ZN), differential evolution (DE), and artificial bee colony (ABC) tuning methods, the proposed method is found highly effective and robust to improve AVR system's transient response.Öğe Gender classification from facial images using gray relational analysis with novel local binary pattern descriptors(Springer Nature, 2016-11-18) Kaya, Yılmaz; Ertuğrul, Ömer FarukGender classification (GC) is one of the major tasks in human identification that increase its accuracy. Local binary pattern (LBP) is a texture method that employed successfully. But LBP suffers a major problem; it cannot capture spatial relationships among local textures. Therefore, in order to increase the accuracy of GC, two LBP descriptors, which are based on (1) spatial relations between neighbors with a distance parameter, and (2) spatial relations between a reference pixel and its neighbor on the same orientation, were employed to extract features from facial images. Additionally, gray relational analysis (GRA) was carried out to identify gender through extracted features. Experiments on the FEI database illustrated the effectiveness of the proposed approaches. Achieved accuracies are 97.14, 93.33, and 92.50% by applying GRA with the nLBPd, dLBPα, and traditional LBP features, respectively. Experimental results indicated that the proposed approaches were very competitive feature extraction methods in GC. Present work also showed that the nLBPd, dLBPα methods were obtained more acceptable results than traditional LBP.Öğe Recognition of daily and sports activities(IEEE, 201-01-24) İnanç, Nihat; Kayri, Murat; Ertuğrul, Ömer FarukSince being physically inactive was reported as one of the major risk factor of mortality, classifying daily and sports activities becomes a critical task that may improve human life quality. In this paper, the daily and sports activities dataset was used in order to evaluate and validate the employed approach. In this approach, the statistical features were extracted from the histograms of the local changes in the wearable sensors logs were obtained by one-dimensional local binary patterns. Later, extracted features were classified by extreme learning machines. Results were showed that the proposed approach is enough to recognize the action type, but in order to recognize the actions, or gender, different feature extraction methods must be employed.Öğe A novel version of k nearest neighbor: Dependent nearest neighbor(Elsevier, 2017-06) Ertuğrul, Ömer Faruk; Tağluk, Mehmet Emink nearest neighbor (kNN) is one of the basic processes behind various machine learning methods In kNN, the relation of a query to a neighboring sample is basically measured by a similarity metric, such as Euclidean distance. This process starts with mapping the training dataset onto a one-dimensional distance space based on the calculated similarities, and then labeling the query in accordance with the most dominant or mean of the labels of the k nearest neighbors, in classification or regression issues, respectively. The number of nearest neighbors (k) is chosen according to the desired limit of success. Nonetheless, two distinct samples may have equal distances to query but, with different angles in the feature space. The similarity of the query to these two samples needs to be weighted in accordance with the angle going between the query and each of the samples to differentiate between the two distances in reference to angular information. This opinion can be analyzed in the context of dependency and can be utilized to increase the precision of classifier. With this point of view, instead of kNN, the query is labeled according to its nearest dependent neighbors that are determined by a joint function, which is built on the similarity and the dependency. This method, therefore, may be called dependent NN (d-NN). To demonstrate d-NN, it is applied to synthetic datasets, which have different statistical distributions, and 4 benchmark datasets, which are Pima Indian, Hepatitis, approximate Sinc and CASP datasets. Results showed the superiority of d-NN in terms of accuracy and computation cost as compared to other employed popular machine learning methods.Öğe Forecasting electricity load by a novel recurrent extreme learning machines approach(Elsevier, 2016-06) Ertuğrul, Ömer FarukGrowth in electricity demand also gives a rise to the necessity of cheaper and safer electric supply and forecasting electricity load plays a key role in this goal. In this study recurrent extreme learning machine (RELM) was proposed as a novel approach to forecast electricity load more accurately. In RELM, extreme learning machine (ELM), which is a training method for single hidden layer feed forward neural network, was adapted to train a single hidden layer Jordan recurrent neural network. Electricity Load Diagrams 2011-2014 dataset was employed to evaluate and validate the proposed approach. Obtained results were compared with traditional ELM, linear regression, generalized regression neural network and some other popular machine learning methods. Achieved root mean square errors (RMSE) by RELM were nearly twice less than obtained results by other employed machine learning methods. The results showed that the recurrent type ANNs had extraordinary success in forecasting dynamic systems and also time-ordered datasets with comparison to feed forward ANNs. Also, used time in the training stage is similar to ELM and they are extremely fast than the others. This study showed that the proposed approach can be applied to forecast electricity load and RELM has high potential to be utilized in modeling dynamic systems effectively.Öğe Forecasting local mean sea level by generalized behavioral learning method(Springer Nature, 2017-03-13) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminDetermining and forecasting the local mean sea level (MSL), which is a major indicator of global warming, is an essential issue to set public policies to save our future. Owing to its importance, MSL values are measured and shared periodically by many agencies. It is not easy to model or forecast MSL because it depends on many dynamic sources such as global warming, geophysical phenomena, and circulations in the ocean and atmosphere. Several of researchers applied and recommended employing artificial neural network (ANN) in the estimation of MSL. However, ANN does not take into account the order of samples, which may consist essential information. In this study, the generalized behavioral learning method (GBLM), which is based on behavioral learning theories, was employed in order to achieve higher accuracies by using samples in the training dataset and the order of samples. To evaluate and validate GBLM, MSL of seven stations around the world was picked up. These datasets were employed to forecast the local MSL for the future. Obtained results were compared with the ones obtained by ANN that is trained by extreme learning machine and the literature. The GBLM is found to be successful in terms of the achieved high accuracies and the ability to tracking trends and fluctuations of a local MSL.
