Yazar "Ozkaya, Umut" seçeneğine göre listele
Listeleniyor 1 - 8 / 8
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Combining Different Image Parts of Instruments with Image Mosaicing(IEEE, 2017) Ozturk, Saban; Ozkaya, Umut; Akdemir, Bayram; Seyfi, Levent A.; Kulaksiz, AfsinIn this study, the different image parts belonging to one instrument are combined to obtain a high resolution and full-bodied image as a whole. Images of different sizes that represent different regions of the same instrument are properly combined to obtain a full representation of the instrument. First, properties of images are obtained by using the histogram of gradient (HOG) features. Then, features similar to those obtained features are searched in other images. For this, the obtained properties are applied using convolution in all image. The regions having the highest convolution value are selected as junction regions. There are two problems in the image combining process. These are: the dimensions of the instrument parts in the images may be different, and the location where these parts are located may not overlap. An approach for automatic image sliding and automatic scale synchronization has been proposed for these problems. Finally, the merged pixels of the resulting image are softened. So, the contrast differences between the images due to the light is minimized. The proposed method was tested using different instruments in experiments. Successful results have been achieved for all compelling test images.Öğe A comparative study on parameters of leaf-shaped patch antenna using hybrid artificial intelligence network models(SPRINGER LONDON LTD, 2018) Ozkaya, Umut; Seyfi, LeventThis study proposes a very compact coaxial-fed planar antenna for X band applications. The antenna design includes a tulip-shaped radiator on the FR4 dielectric substrate. The antenna parameters, such as return losses, bandwidth and operating frequency, have close relationships with patch geometry. In order to obtain desired antenna parameters for X band application, patch dimension is necessary to be optimized. In this article, four different hybrid artificial intelligence network models are suggested for optimization. These are particle swarm optimization, differential evolution, grey wolf optimizer and vortex search algorithm. Also, they are combined with artificial neural network for the purpose of estimating dimension of patch. Therefore, the comparison of different proposed algorithms is analyzed to obtain higher characteristics for antenna design. Their results are compared with each other in HFSS 13.0 software. The antenna with the most suitable return loss, bandwidth and operating frequency is selected to be used in antenna design.Öğe Convolution Kernel Size Effect on Convolutional Neural Network in Histopathological Image Processing Applications(IEEE, 2018) Ozturk, Saban; Ozkaya, Umut; Akdemir, Bayram; Seyfi, LeventIn this study, the change in the classification success of the convolutional neural network (CNN) is investigated when the dimensions of the convolution window are altered. For this purpose, four different linear convolution neural network architectures are constructed. The first architecture includes 4 convolution layers with 3x3 convolution window dimensions. The second architecture includes 4 convolution layers with 5x5 convolution window dimensions. The third architecture includes 4 convolution layers with 7x7 convolution window dimensions. The fourth architecture includes 4 convolution layers with 9x9 convolution window dimensions. A dataset consisting of histopathological image patches is used to test the CNN architects that are created. 2000 training images and 250 validation images on dataset are applied to all architectures with the same order, in order to fair assessment. In conclusion, the effect of convolution dimensions on classification of histopathological images by deep learning methods is determined. The test results of four different linear convolutional neural network architectures are evaluated using sensitivity, specificity and accuracy parameters.Öğe Deep dictionary learning application in GPR B-scan images(SPRINGER LONDON LTD, 2018) Ozkaya, Umut; Seyfi, LeventThis paper introduces GPR B-scan database which contains 180 labelled images to facilitate research in developing presentation algorithm for this challenging scenario. Along with GPR B-scan images, there are several other detections of buried objects that are explored in the literature. The next contribution of this research is a novel multilevel deep dictionary learning-based presentation buried object detection algorithm that can discern different kinds of materials. An efficient layer by layer training approach is formulated to learn the deep dictionaries followed by different classifiers as types of shape for buried objects. By changing the number of layers in proposed algorithm, performances in different classifiers are compared. It is possible to integrate the proposed algorithm with real-time systems because it is supervised and has high classification accuracy with 94.4%.Öğe Dimension Optimization of Microstrip Patch Antenna in X/Ku Band via Artificial Neural Network(ELSEVIER SCIENCE BV, 2015) Ozkaya, Umut; Seyfi, LeventThis paper is aimed at designing the effective shape of a microstrip patch antenna for X Band (8 to 12 GHz) and Ku Band (12 GHz to 18 GHz). Artificial Neural Network is used for optimizing microstrip antenna dimensions. The Network takes the different microstrip antenna parameters as inputs and delivers its dimensions in the X/Ku Band satellite communication. The error and validity analysis of neural network results are carried out in Matlab. Finally, HFSS simulation software results for prototype microstrip antenna, which has the best antenna parameters, is compared with real value. (C) 2015 The Authors. Published by Elsevier Ltd.Öğe MODELING AND ANALYSIS OF ABSORBING BOUNDARY CONDITION IN ANTENNA DESIGN(CENTRAL BOHEMIA UNIV, 2016) Ozkaya, Umut; Seyfi, LeventIn this study, the absorbing boundary condition is modelled and analyzed by particle swarm optimization for antenna designs. Two pieces of circular and rectangular microstrip patch antennas are designed for results by means of High Frequency Structure Simulator (HFSS) simulation program. These antennas are implemented by printed circuit board technologies. The results of measurements and simulation performed for the antenna determined the optimal absorbing boundary distance.. In order to be closer with simulation and measurement results, data set is generated by varying in absorbing boundary size. Average square error between simulation and measurement data is necessary to be optimized as an objective function. For this reason, optimization algorithm based on swarm intelligence is preferred to be minimized the error function. Thanks to the results of measurements and simulation performed with the antenna, optimal absorbing boundary distance is determined by Particle Swarm Optimization.Öğe A NOVEL FUZZY LOGIC MODEL FOR INTELLIGENT TRAFFIC SYSTEMS(ST JOHN PATRICK PUBL, 2016) Ozkaya, Umut; Seyfi, Levent[Abstract not Available]Öğe Weighting and Classification of Image Features using Optimization Algorithms(IEEE, 2018) Ozturk, Saban; Ozkaya, Umut; Akdemir, Bayram; Seyfi, LeventIn this study, importance ratios of features extracted from images using feature extraction algorithms are examined. A significance coefficient is determined for each feature parameter. The number of features is reduced according to the weight of the importance calculated for each feature. The classification success is examined for each case. Firstly, six feature extraction algorithms are used for this purpose. The classification success of all these feature extraction algorithms has been examined separately. Then, all properties are combined to form a single property matrix. The obtained property matrix is reduced by using principal component analysis and relieff methods. New feature matrices provide increased classification performance. However, it is inefficient to classify a high number of properties in real-time applications. To overcome this problem, the effect of classifying each parameter in the property matrix is examined and the insignificant properties are discarded. The proposed method is tested using histopathological images. Histopathological images are divided into 4 separate classes. The proposed method reduces the raw feature matrix by 50% with 97.2% classification success.
