Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/11
Browse
8 results
Search Results
Now showing 1 - 8 of 8
Article Citation - WoS: 5Citation - Scopus: 7Fast Texture Classification of Denoised Sar Image Patches Using Glcm on Spark(Türkiye Klinikleri Journal of Medical Sciences, 2020) Özcan, Caner; Ersoy, Okan; Oğul, İskender ÜlgenClassification of a synthetic aperture radar (SAR) image is an essential process for SAR image analysis and interpretation. Recent advances in imaging technologies have allowed data sizes to grow, and a large number of applications in many areas have been generated. However, analysis of high-resolution SAR images, such as classification, is a time-consuming process and high-speed algorithms are needed. In this study, classification of high-speed denoised SAR image patches by using Apache Spark clustering framework is presented. Spark is preferred due to its powerful open-source cluster-computing framework with fast, easy-to-use, and in-memory analytics. Classification of SAR images is realized on patch level by using the supervised learning algorithms embedded in the Spark machine learning library. The feature vectors used as the classifier input are obtained using gray-level cooccurrence matrix which is chosen to quantitatively evaluate textural parameters and representations. SAR image patches used to construct the feature vectors are first applied to the noise reduction algorithm to obtain a more accurate classification accuracy. Experimental studies were carried out using naive Bayes, decision tree, and random forest algorithms to provide comparative results, and significant accuracies were achieved. The results were also compared with a state-of-the-art deep learning method. TerraSAR-X images of high-resolution real-world SAR images were used as data.Article Citation - Scopus: 1Reconstruction of Geometrical and Reflection Properties of Surfaces by Using Structured Light Imaging Technique(Türkiye Klinikleri Journal of Medical Sciences, 2018) Ozan, Şükrü; Gümüştekin, ŞevketWhen a robust and dense surface reconstruction is aimed, structured light imaging techniques are usually much appreciated. In this paper we propose a method to reconstruct both geometrical and reflective properties of surfaces by using structured light imaging. We use a technique where a camera and a projector are both treated as viewing devices. They are calibrated in the same manner. Each visible point can be correctly located on both image planes without solving a correspondence problem; hence, a dense reconstruction can be obtained. Since both the camera and the projector are explicitly calibrated, lighting and viewing directions can be identified for each surface point. It is also possible to measure reflected radiance by using high dynamic range (HDR) images for each surface point. The lighting and viewing directions that are known after calibration are combined with the reflected radiance and the incoming irradiance measurements to determine the bidirectional reflectance distribution function (BRDF) values of the material at the reconstructed surface points. We illustrate the reconstruction of surface reflection properties of sample surfaces by fitting the Phong BRDF model to the BRDF measurements.Article Citation - WoS: 2Citation - Scopus: 2Quantification of Resistive Wall Instability for Particle Accelerator Machines(Türkiye Klinikleri Journal of Medical Sciences, 2019) Yaman, FatihThe aim of this study is to quantify longitudinal resistive wall impedances, corresponding wake functions, and wake potentials for different accelerator machines of interest. Accurate calculations of wake potentials by particle-in-cell codes are extremely difficult for the investigated parameters; therefore, we use an analytical approach and consider large domains with fine discretization for the required numerical integrations. The semianalytical wake potential computations are benchmarked against numerical general purpose 2D/3D Maxwell solver software codes and a different analytical approach for a certain set of parameters. We report examples to illustrate limitations of wake potential estimations from coupling impedances, and computations for the machines using realistic beam parameters and machine conditions. A numerical example where the aim is to find the wake potential of the machine from the 5% noisy impedance data is given.Article Citation - WoS: 2Citation - Scopus: 2Investigating the Experimental Limits of the Brewster’s Angle Method(Türkiye Klinikleri Journal of Medical Sciences, 2018) Sümer, Can; Kuştepeli, Alp; Dinleyici, Mehmet SalihWe present the method, analysis, and experimental results of the Brewster’s angle method commonly used for determining the refractive indices of optical films. We show the significance of the intersection of reflectance curves, in that the necessity for substrate refractive index and film layer thickness knowledge are both eliminated. We present the conditions for the existence of the second intersection of reflectance curves and introduce a method for determining the refractive index of the substrate layer by using the angular information alone. Analytical results reveal impressive practical sensitivity and accuracy limits for the method, where the experimental results also support the theoretical analysis.Article Skewed Alpha-Stable Distributions for Modeling and Classification of Musical Instruments(Türkiye Klinikleri Journal of Medical Sciences, 2012) Özbek, Mehmet Erdal; Çek, Mehmet Emre; Savacı, Ferit AcarMusic information retrieval and particularly musical instrument classification has become a very popular research area for the last few decades. Although in the literature many feature sets have been proposed to represent the musical instrument sounds, there is still need to find a superior feature set to achieve better classification performance. In this paper, we propose to use the parameters of skewed alpha-stable distribution of sub-band wavelet coefficients of musical sounds as features and show the effectiveness of this new feature set for musical instrument classification. We compare the classification performance with the features constructed from the parameters of generalized Gaussian density and some of the state-of-the-art features using support vector machine classifiers.Article Citation - WoS: 3Citation - Scopus: 4Perceptual Quality Evaluation of Asymmetric Stereo Video Coding for Efficient 3d Rate Scaling(Türkiye Klinikleri Journal of Medical Sciences, 2014) Özbek, Nükhet; Ertan, Gizem; Karakuş, OktayIn 3D perception, the binocular suppression of the human vision, perceiving high quality 3D video in the case of a view in higher quality, can be exploited in asymmetric stereo video coding for efficient 3D rate scaling. Hence, the best stereo rate-visual distortion performance may be gained by asymmetric coding, which is the reduction of the spatial and/or quantization resolution of the low-quality view, while keeping the high-quality view in full resolution. However, how to determine the level of asymmetry and what type of scaling should be chosen are still in question. In this work, we try to assess the overall performance of the scalability options with several test contents. The test videos are encoded at critical bitrates with symmetric options and spatial or signal-to-noise ratio (SNR) asymmetric coding, and are subjectively evaluated in a stereo-polarized projection 3D display system. Two different types of evaluation methodologies are used: the Double-Stimulus Continuous-Quality Scale (DSCQS) and Subjective Evaluation of Stereo Video Quality (SESVIQ). Dense visual tests show that the spatial scaling is generally inferior when compared to SNR scaling, except that high motion scenes and symmetric SNR are more preferable for a higher bitrate. The characteristics of the video content should be taken into consideration for efficient stereo rate scaling.Article Citation - WoS: 45Citation - Scopus: 47A Comparative Performance Evaluation of Various Approaches for Liver Segmentation From Spir Images(Türkiye Klinikleri Journal of Medical Sciences, 2015) Göçeri, Evgin; Ünlü, Mehmet Zübeyir; Dicle, OğuzDeveloping a robust method for liver segmentation from magnetic resonance images is a challenging task because of the similar intensity values between adjacent organs, the geometrically complex liver structure, and injection of contrast media. Most importantly, a high anatomical variability of a healthy or diseased liver is a major challenge in defining the exact boundaries of the liver. Several artifacts of pulsation, motion, and partial volume effects are also among the variety of factors that make automatic liver segmentation difficult. In this paper, we present an overview of liver segmentation methods in magnetic resonance images and show comparative results of seven different pseudo-3D liver segmentation approaches chosen from deterministic (K-means-based), probabilistic (Gaussian model-based), supervised neural network (multilayer perceptron-based), and deformable model-based (level set) segmentation methods. The results of quantitative and qualitative analyses using sensitivity, specificity, and accuracy metrics show that the multilayer perceptron-based approach and a level set-based approach, both of which use distance regularization terms and signed pressure force function, are the most successful methods for liver segmentation from spectral presaturation inversion recovery (SPIR) images. However, the multilayer perceptron-based segmentation method has a higher computational cost. The automatic method using the distance regularized level set evolution with signed pressure force function avoids the sensitivity of a user-defined initial contour for each slice, gives the most efficient results for liver segmentation after the preprocessing steps, and also requires less computational time.Article Citation - WoS: 4Citation - Scopus: 5Learning Control of Robot Manipulators in the Presence of Additive Disturbances(Türkiye Klinikleri Journal of Medical Sciences, 2011) Tatlıcıoğlu, EnverIn this paper, a learning controller for robot manipulators is developed. The controller is proven to yield in a semi-global asymptotic result in the presence of additive input and output disturbances. Lyapunovbased techniques are used to guarantee that the tracking error is asymptotically driven to zero. Numerical simulation results are presented to demonstrate the viability of the proposed learning controller.