Elektrik Elektronik Mühendisliği Bölümü Yayın Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/411
Browse
6 results
Search Results
Article Efficient Task Scheduling in Cloud Systems With Adaptive Discrete Chimp Algorithm(2022) Gündüzalp, Emrullah; Yıldırım, Güngör; Tatar, YetkınSuccessful task scheduling is one of the priority actions to increase energy efficiency, commercial earnings, and customer satisfaction in cloud computing. On the other hand, since task scheduling processes are NP-hard problems, it is difficult to talk about an absolute solution, especially in scenarios with large task numbers. For this reason, metaheuristic algorithms are frequently used in solving these problems. This study focuses on the metaheuristic-based solution of optimization of makespan, which is one of the important scheduling problems of cloud computing. The adapted Chimp Optimization Algorithm, with enhanced exploration and exploitation phases, is proposed for the first time to solve these problems. The solutions obtained from this adapted algorithm, which can use different mathematical functions, are discussed comparatively. The proposed solutions are also tested in the CloudSim simulator for different scenarios and they prove their performance in the cloud environment.Article Ear Semantic Segmentation in Natural Images With Tversky Loss Function Supported Deeplabv3+ Convolutional Neural Network(2022) Kacar, Umit; Inan, TolgaSemantic segmentation is a fundamental problem for computer vision. On the other hand, for studies in the field of biometrics, semantic segmentation is gaining more importance. Many successful biometric recognition systems require a high- performance semantic segmentation algorithm. In this study, we present an effective ear segmentation technique in natural images. A convolutional neural network is trained for pixel-based ear segmentation. DeepLab v3+ network structure, with ResNet-18 as the backbone and Tversky lost function layer as the last layer, has been trained with natural and uncontrolled images. We perform the proposed network training using only the 750 images in the Annotated Web Ears (AWE) training set. The corresponding tests are performed on the AWE Test Set, University of Ljubljana Test Set, and the Collection A of In-The-Wild dataset. For the Annotated Web Ears (AWE) dataset, intersection over union (IoU) is measured as 86.3% for the AWE database. To the best of our knowledge, this is the highest performance achieved among the algorithms tested on the AWE test set.Article Line-Of Rate Construction for a Roll-Pitch Gimbal Via a Virtual Pitch-Yaw Gimbal(Tubitak Scientific & Technological Research Council Turkey, 2021) Cifdaloz, OguzhanIn this paper, a method to construct the line of sight rate of a target with a roll-pitch gimbal and tracker is described. Construction of line-of-sight rate is performed via utilizing a virtual pitch-yaw gimbal. Kinematics of both the roll-pitch and pitch-yaw gimbals are described. A dynamical model for the roll-pitch gimbal is developed, and a nested control structure is designed to control the angular rates and line of sight angles. A kinematic model of the tracker is developed and a tracker controller is designed to keep the target in the field of view. Conversion equations between roll-pitch and pitch-yaw gimbal configurations are provided. Finally, constructed line of sight rates are compared to true line of sight rates via simulations. Obtained results indicate that the constructed line of sight rates pertaining to a target satisfactorily converge to the actual line of sight rates.Article A Hybrid Framework for Matching Printing Design Files To Product Photos(2020) Akagunduz, Erdem; Kaplan, AlperWe propose a real-time image matching framework, which is hybrid in the sense that it uses both hand - crafted features and deep features obtained from a well -tuned deep convolutional network. The matching problem, which we concentrate on, is specific to a certain application, that is, printing design to product photo matching. Printing designs are any kind of template image files, created using a design tool, thus are perfect image signals. For this purpose, we create an image set that includes printing design and corresponding product photo pairs with collaboration of an actual printing facility. Using this image set, we benchmark various hand-crafted (SIFT, SURF, GIST, HoG) and deep features for matching performance. Various segmentation algorithms including deep learning based segmentation methods are applied to select feature regions. Results show that SIFT features selected from deep segmented regions achieves up to 96% product photo to design file matching success in our dataset. We propose a framework in which deep learning is utilized with highest contribution, but without disabling real-time operation using an ordinary desktop computer.Article Citation - WoS: 3Citation - Scopus: 3Filter Design for Small Target Detection on Infrared Imagery Using Normalized-Cross Layer(Tubitak Scientific & Technological Research Council Turkey, 2020) Demir, H. Seckin; Akagunduz, ErdemIn this paper, we introduce a machine learning approach to the problem of infrared small target detection filter design. For this purpose, similar to a convolutional layer of a neural network, the normalized-cross-correlational (NCC) layer, which we utilize for designing a target detection/recognition filter bank, is proposed. By employing the NCC layer in a neural network structure, we introduce a framework, in which supervised training is used to calculate the optimal filter shape and the optimum number of filters required for a specific target detection/recognition task on infrared images. We also propose the mean-absolute-deviation NCC (MAD-NCC) layer, an efficient implementation of the proposed NCC layer, designed especially for FPGA systems, in which square root operations are avoided for real-time computation. As a case study we work on dim-target detection on midwave infrared imagery and obtain the filters that can discriminate a dim target from various types of background clutter, specific to our operational concept.Article Dynamic Optımızatıon of Image Brıgthness Level With Optimal Gamma Value Assessment (OGVA) Method(2020) Preveze, BarbarosIn this study, the proposed Optimum Gamma Value Assignment (OGVA) method is intended to dynamically optimize the image intensity level in non-desired images due to undesired light levels. For this purpose, it is aimed to make the dark images which cannot be seen due to lack of light, while bright images are dynamically dimmed by using the optimum gamma correction value applied on the image momentarily. It has been shown that this novel method, which will only be implemented as software, without requiring any additional hardware, yields satisfying results even at different light levels.