Yazar "Sen, B." seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Cropped Quad-Tree based solid object colouring with CUDA(2013) Çavusoglu, A.; Sen, B.; Özcan, C.; Görgünoglu, S.In this study, surfaces of solid objects are coloured with Cropped Quad-Tree method utilizing GPU computing optimization. There are numerous methods used in solid object colouring. When the studies carried out in different fields are taken into consideration, it is seen that quad-tree method displays a prominent position in terms of speed and performance. Cropped quad-tree is obtained as a result of the developments seen with the frequent use of this method in the field of computer sciences. Two different versions of algorithm which operate recursively on CPU and at the same time which use GPU computing optimization are used in this study. Besides, OpenGL is used for graphics drawing process. Within the setting of the study, results are obtained via CPU and GPU's, at first using Quad-Tree method and then Cropped Quad-Tree method. It is observed that GPU computing is obviously faster than CPU computing and Cropped Quad-Tree method produces rapid results compared to Quad-Tree method as a result of performance. GPU computing method boosted approximately performance by up to 20 times compared to only CPU usage; furthermore, cropped quad-tree method boosted approximately performance of algorithm by up to 25 times on average dependent on screen and object size.Öğe Development of spiritual & historical tourism(Peter Lang AG, 2021) Kuralbayev, A.; Sen, B.[No abstract available]Öğe Early-exit optimization using mixed norm despeckling for SAR images(Institute of Electrical and Electronics Engineers Inc., 2015) Özcan, C.; Sen, B.; Nar, F.Speckle noise which is inherent to Synthetic Aperture Radar (SAR) imaging obstructs various image exploitation tasks such as edge detection, segmentation, change detection, and target recognition. Speckle reduction is generally used as a first step which has to smooth out homogeneous regions while preserving edges and point scatterers. In remote sensing applications, efficiency of computational load and memory consumption of despeckling must be improved for SAR images. In this paper, an early-exit total variation approach is proposed and this approach combines the l1-norm and the l2-norm in order to improve despeckling quality while keeping execution times of algorithm reasonably short. Speckle reduction performance, execution time and memory consumption are shown using spot mode SAR images. © 2015 IEEE.Öğe Fast feature preserving despeckling(IEEE Computer Society, 2014) Ozcan, C.; Sen, B.; Nar, F.Synthetic Aperture Radar (SAR) images contain high amount of speckle noise which causes edge detection, shape analysis, classification, segmentation, change detection and target recognition tasks become more difficult. To overcome such difficulties, smoothing of homogenous regions while preserving point scatterers and edges during speckle reduction is quite important. Besides, due to huge size of SAR images in remote sensing applications efficiency of computational load and memory consumption must be further improved. In this paper, a parallel computational approach is proposed for the Feature Preserving Despeckling (FPD) method which is chosen due to its success in speckle reduction. Speckle reduction performance, execution time and memory consumption of the proposed Fast FPD (FFPD) method is shown using spot mode SAR images. © 2014 IEEE.Öğe Keratoconus Disease and Three-Dimensional Simulation of the Cornea throughout the Process of Cross-Linking Treatment(Elsevier Inc., 2015) Kaya, H.; Çavusoglu, A.; Çakmak, H.B.; Sen, B.; Çalik, E.Keratoconus is a corneal disease characterized by the progressive thinning and tapering of the cornea. Vision gradually decreases as the sphere-shaped cornea becomes more tapered and conical. With corneal cross-linking treatment, which increases the number of cross-links in the connective tissues of the corneal layers, the cornea hardens. The purpose of this chapter is to described the changes in the cornea between the processes before and after the cross-linking treatment. In this study, we used the Cropped Quad-Tree method as the cropping algorithm, Multilayer Perceptron and Logistic Regression methods to prepare the data set, and three-dimensional (3D) imaging methods to model the images in 3D form. With this application, it can be possible to follow up the healing process after the treatment and also monitor whether the treatment has achieved the desired results. This system was developed in order to support eye specialists in the disease diagnosis, treatment, and follow-up stages. It can be seen that the follow-up process of the disease by analyzing two-dimensional (2D) corneal images can be improved by using 3D images. © 2015 Elsevier Inc. All rights reserved.Öğe A novel classification and estimation approach for detecting keratoconus disease with intelligent systems(IEEE Computer Society, 2013) Ucar, M.; Sen, B.; Cakmak, H.B.Keratoconus is an eye disease characterized by progressive thinning of cornea which is the front based transparent layer of the eye. In other words, it is a progressive distortion of corneal layer and at least getting conical shape that should be like a dome camber. The vision reduces more and more while cornea gets shape of cone which should be like a sphere normally. The aim of this study is to define a new classification method for detecting keratoconus based on statistical analysis and to realize the prediction of these classified data with intelligent systems. 301 eyes of 159 patients and 394 eyes of 265 refractive surgery candidates as the control group have been used for this study. Factor analysis, one of the multivariate statistical techniques, has been mainly used to find more meaningful, easy to understand, and independent factors amongst the others. Later, a new classification method has been defined using clustering analysis techniques on these factors and finally estimated by using artificial neural networks and support vector machines. © 2013 The Chamber of Turkish Electrical Engineers-Bursa.Öğe Placement score estimation of secondary education transition system (SETS) using artificial neural networks(2012) Ucar, E.; Sen, B.; Bayir, S.This study offers an approach based on artificial neural networks for predicting the placement score of secondary education transition system (SETS). Artificial neural networks have recently become a very important method in the classification and prediction of the problems. Therefore, Multilayer Perceptron (MLP) and Radial Basis Function (RBF) which are among the most preferred artificial neural network architectures were used in this study. Created expert system was trained and tested on a database including 25000 randomly selected records of primary education 8th grade students. Results of this training and testing are comparatively presented within the study. © Sila Science.Öğe Scattered data estimation on medical images for cranioplasty applications(IEEE Computer Society, 2014) Atasoy, F.; Nar, F.; Sen, B.; Ferat, M.Cranioplasty is a surgical operation to repair hole or defects on skull. 3 dimensional computed tomography (CT) images are used for automatic determination of the shape of implant which is used for repairing defect. The designing implant by mathematical model and manufacturing it before operation lowers the operation cost. In this paper, previous studies are examined, applications are realized by radial basis functions (RBF) and insufficient sections of previous studies are revealed. © 2014 IEEE.Öğe Sparsity-driven despeckling method with low memory usage(Institute of Electrical and Electronics Engineers Inc., 2016) Ozcan, C.; Sen, B.; Nar, F.Speckle noise which is inherent to Synthetic Aperture Radar (SAR) imaging makes it difficult to detect targets and recognize spatial patterns on earth. Thus, despeckling is critical and used as a preprocessing step for smoothing homogeneous regions while preserving features such as edges and point scatterers. In this study, a low-memory version of the previously proposed sparsity-driven despeckling (SDD) method is proposed. All steps of the method are parallelized using OpenMP on CPU and CUDA on GPU. Execution time and despeckling performance are shown using real-world SAR images. © 2016 IEEE.Öğe Subthreshold stimulus encoding on a stochastic scale-free neuronal network(2010) Yilmaz, E.; Özer, M.; Sen, B.Random networks with complex topology arise in many different fields of science. Recently, it has been shown that existing network models fail to incorporate two common features of real networks in nature: First, real networks are open and continuously grow by addition of new elements, and second, a new element connects preferentially to an element that already has a large number of connections. Therefore, a new network model, called a scale-free (SF) network, has been proposed based on these two features. In this study, we study the subthreshold periodic stimulus encoding on a stochastic SF neuronal network based on the collective firing regularity. The network consists of identical Hodgkin-Huxley (HH) neurons. We show that the collective firing (spiking) regularity becomes maximal at a given stimulus frequency, corresponding to the frequency of the subthreshold oscillations of HH neurons. We also show that this best regularity can be obtained if the coupling strength and average degree of connectivity have their optimal values. ©2010 IEEE.Öğe Total variation based 3D skull segmentation(Institute of Electrical and Electronics Engineers Inc., 2016) Atasoy, F.; Sen, B.; Nar, F.; Ozcan, C.; Bozkurt, I.Segmentation is widely used for determining tumor and other lesions and classifying tissues for various analysis purposes in medical images. However, being an ill-posed problem, there is no single segmentation method which can perform successfully for all kind of data. In this study, a novel total variation (TV) based skull segmentation method is proposed. Skull segmentation performance of the proposed method is shown using computed tomography (CT) images. © 2016 IEEE.Öğe Validation of daily precipitation estimates of the regional climate model RegCM4 over the domains in Turkey with NWP verification techniques(Parlar Scientific Publications, 2014) Sen, B.; Kilinç, R.; Sen, B.; Sonuç, E.We present a validation study for a 50-km resolution version of the RegCM4 regional climate model over the East Mediterranean Basin. In this study, the observation and evaluation of the model results against each other as well as graphication, which mostly generates scatter plot graphs of the atmosphere for operational weather forecasting models (NWP, numerical weather prediction), with 11 different statistical verification score values were evaluated by calculating the regional climate model results. As a result of the analysis, it has been estimated that the rainfall is 42% higher than the estimated average amount RegCM4 simulations based on the 50 observation stations. Meteorological Service (TSMS, Turkish State Meteorological Service) observation network monitored 50 stations based on the average of Frequency Bias Index (FBI), Proportion Correct (PC), Probability of Detection (POD), False Alarm Ratio (FAR), False Alarm Rate (F), Hanssen-Kuipers Skill Score (KSS), the Threat Score (TS), Equitable Threat Score (ETS), Heidke Skill Score (HSS), The Odds Ratio (OR), and Odds Ratio Skill Score (ORSS) values which are as follows, respectively: 0.70, 0.70, 0.52, 0.32, 0.38, 0.39, 0.21, 0.34, 5.99, and 0.69. The objective score values calculated for RegCM4 climate model were found to be close to the score values of the NWP models. Given these values, which were found to be successful for RegCM4 model dynamics, the results generated by other models, recovery/adaptation techniques will be used for the application of hydrological studies. © by PSP.
