Yazar "Kutucu, Hakan" seçeneğine göre listele
Listeleniyor 1 - 20 / 29
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Advancements in AI-Based Information Technologies: Solutions for Quality and Security(Mdpi, 2024) Hovorushchenko, Tetiana; Izonin, Ivan; Kutucu, Hakan[No abstract available]Öğe Analysis of the Early Posttraumatic Period Pathophysiology in Case of the Severe Combined Thoracic Trauma Using Multivariate Logistic Regression(Rwth Aachen, 2019) Stupnytskyi, Myroslav; Zhukov, Viktor; Gorbach, Tatyana; Biletskii, Oleksii; Kutucu, HakanSeverely injured patients are always challenging, even more so when they have suffered critical trauma to the chest. The aim of this study is to create a prognostic tool for outcome prediction for patients with combined thoracic trauma based on the determination of main homeostasis parameters on the 1st and 2nd day after injury. Multivariate logistic regression analysis with forward elimination of the variables was used for modeling the dependence of outcome on clinical and laboratory parameters that reflects main pathophysiological mechanisms developed on the 1st and 2nd day after combined thoracic trauma. 73 Male patients with combined thoracic trauma were included in the study. The results of fitting a logistic regression model show the relationship between mortality and six independent variables: transferrin saturation, percentage of eosinophils, TNF-a concentration, total iron binding capacity, inspiratory fraction of oxygen and albumin concentration. Besides that, forward elimination of the variables into the logistic regression equation helps to recognize relatively independent pathophysiological mechanisms involved to progression of wound dystrophy. The likelihood ratio tests can reflect the contribution degree of each pathogenesis rout responsible for the negative outcomes of the severe combined thoracic trauma. The study contributes to our understanding of interaction between pathophysiological mechanisms that make harmful effects and are involved in the progression of wound dystrophy and compensatory reactions directed on stabilization of vital function disturbances and maintenance of homeostasis during this type of wound dystrophy.Öğe An automated system for electrical power symbol placement in electrical plan drawing(Taylor & Francis Ltd, 2022) Akgul, Bayram; Kutucu, HakanAn electrical plan drawing-sometimes called a wiring diagram or electrical drawing-consists of lines and symbols. Electrical plan drawings are prepared on 2D architectural floor plans using Computer-Aided Design and/or Drafting (CAD) programs. The placement/drawing of electrical power symbols-such as sockets, lights, and switches-is the first step of an electrical plan drawing. For this purpose, a smart system has been developed in this study to automatically draw/place electrical power symbols in appropriate locations. The system is based on the detection and classification/recognition of furnishing (decorative) symbols in the floor plans. We have created a furnishing symbol dataset drawing on dozens of architectural plan drawings that contain symbols of the most commonly used tools in floor plans, such as furniture, appliances, plumbing, doors, and windows. We used a Deep Convolutional Neural Network (D-CNN) with transfer learning-Inception-v3 model- to classify furnishing symbols. We tested the model on 20 real floor plans and achieved a very satisfactory accuracy of 97.05% in furnishing symbol classification. The symbol drawing step, which is the first step of drawing the electrical plan, was automated using the work developed, thus achieving the aim of saving time and labour. Experimental studies show the effectiveness of the proposed automated system.Öğe Automatic identification for field butterflies by convolutional neural networks(Elsevier - Division Reed Elsevier India Pvt Ltd, 2020) Almryad, Ayad Saad; Kutucu, HakanIn today's competitive conditions, producing fast, inexpensive and reliable solutions are an objective for engineers. Development of artificial intelligence and the introduction of this technology to almost all areas have created a need to minimize the human factor by using artificial intelligence in the field of image processing, as well as to make a profit in terms of time and labor. In this paper, we propose an automated butterfly species identification model using deep neural networks. We collected 44,659 images of 104 different butterfly species taken with different positions of butterflies, the shooting angle, butterfly distance, occlusion and background complexity in the field in Turkey. Since many species have a few image samples we constructed a field-based dataset of 17,769 butterflies with 10 species. Convolutional Neural Networks (CNNs) were used for the identification of butterfly species. Comparison and evaluation of the experimental results obtained using three different network structures are conducted. Experimental results on 10 common butterfly species showed that our method successfully identified various butterfly species. (C) 2020 Karabuk University. Publishing services by Elsevier B.V.Öğe The band collocation problem(Springer, 2020) Kutucu, Hakan; Gursoy, Arif; Kurt, Mehmet; Nuriyev, UrfatIn order to reduce costs in the telecommunication sector, many mathematical models have been developed. Over time, these models either fall out out of use or are revised according to new technological developments. The Bandpass Problem (BP) is an optimization problem introduced in 2004 to reduce hardware costs in communication networks. However, over time, technological advances in fiber-optic networks have caused the BP to lose functionality and usability. Major changes should be made to the model to make the BP functional again. It is necessary to define the problem after having made these changes as a new problem, not as a revised problem. In this paper, we first review the BP. We then discuss the notion that the BP has become unusable due to technological developments. We introduce a new problem called the Band Collocation Problem (BCP), which fixes the issues in the BP. We also develop several mathematical models of the BCP. Furthermore, we prove that the BCP is NP-hard. In order to encourage further research, we develop a Library of Band Collocation Problems. Finally, we present heuristic and meta-heuristic methods to solve the BCP and compare the computational results.Öğe Bases of polymatroids and problems on graphs(Tubitak Scientific & Technological Research Council Turkey, 2020) Kutucu, HakanIn the paper, we present new theorems to show that a Hamiltonian path and circuit on an undirected graph can be formulated in terms of bases of polymatroids or extended polymatroids associated with submodular functions defined on subsets of the node-set of a given graph. In this way, we give a new formulation of the well-known traveling salesman problem including constraints in these terms. The main result in the paper states that using a special base of the polymatroid, a Hamiltonian path on an undirected graph can be solved effectively. Since the determination of a Hamiltonian circuit can be reduced to finding a Hamiltonian path between some node and its adjacent nodes, an efficient Hamiltonian path algorithm will lead to solving the Hamiltonian circuit problem. Finding some special base is the main problem in solving these NP-hard problems.Öğe Detection of Bone Fractures using Image Processing Techniques and Artificial Neural Networks(Ieee, 2017) Ozturk, Ozgur; Kutucu, HakanThe use of computer technology in medical sciences is spreading with technology. The use of computers especially for imaging has become a third eye for physicians. In orthopedic surgeons, after simple roentgenograms for fracture detection, the use of computerized tomography and magnetic resonance has provided great convenience in the detection of fracture, typing, and therefore the appropriate treatment of the patient. The advancing technology has increased the quality of the images in the x-rayograms, reduced artifacts and enabled digital measurements. In this study, image processing and learning techniques were used to diagnose long bone fractures. The proposed artificial neural network has 89% success rate.Öğe Genetic Approach to Improve Cryptographic Properties of Balanced Boolean Functions Using Bent Functions(Mdpi, 2023) Ozcekic, Erol; Kavut, Selcuk; Kutucu, HakanRecently, balanced Boolean functions with an even number n of variables achieving very good autocorrelation properties have been obtained for 12 <= n <= 26. These functions attain the maximum absolute value in the autocorrelation spectra (without considering the zero point) less than 2 n2 and are found by using a heuristic search algorithm that is based on the design method of an infinite class of such functions for a higher number of variables. Here, we consider balanced Boolean functions that are closest to the bent functions in terms of the Hamming distance and perform a genetic algorithm efficiently aiming to optimize their cryptographic properties, which provides better absolute indicator values for all of those values of n for the first time. We also observe that among our results, the functions for 16 <= n <= 26 have nonlinearity greater than 2n 1 2 n2. In the process, our search strategy produces balanced Boolean functions with the best-known nonlinearity for 8 <= n <= 16.Öğe Global distribution center number of some graphs and an algorithm(Edp Sciences S A, 2019) Durgut, Rafet; Kutucu, Hakan; Turaci, TufanThe global center is a newly proposed graph concept. For a graph G = (V(G), E(G)), a set S subset of V(G) is a global distribution center if every vertex v is an element of V(G)\S is adjacent to a vertex u is an element of S with |N[u] boolean AND S| >= |N[v] boolean AND (V(G)\S)|, where N(v) = {u is an element of V(G)|uv is an element of E(G)} and N[v] = N(v) ? {v}. The global distribution center number of a graph G is the minimum cardinality of a global distribution center of G. In this paper, we investigate the global distribution center number for special families of graphs. Furthermore, we develop a polynomial time heuristic algorithm to find the set of the global distribution center for general graphs.Öğe A Heuristic Algorithm for the Band Collocation Problem(Ieee, 2016) Gursoy, Arif; Kurt, Mehmet; Kutucu, Hakan; Nuriyev, UrfatIn this paper we present a heuristic algorithm for the The Band Collocation Problem (BCP) which may have some applications in the field of telecommunication. First, we give the definition the BCP. Second, we explain how we create the problem instances with known optimal solutions as a library. Third, we propose the heuristic algorithm. Then, we analysis and interpret the results of the proposed algorithm on the problem instances with known optimal solutions. Finally, we suggest new ideas about the BCP and its solution approaches.Öğe A heuristic algorithm to find rupture degree in graphs(Tubitak Scientific & Technological Research Council Turkey, 2019) Durgut, Rafet; Turaci, Tufan; Kutucu, HakanSince the problem of Konigsberg bridge was released in 1735, there have been many applications of graph theory in mathematics, physics, biology, computer science, and several fields of engineering. In particular, all communication networks can be modeled by graphs. The vulnerability is a concept that represents the reluctance of a network to disruptions in communication after a deterioration of some processors or communication links. Furthermore, the vulnerability values can be computed with many graph theoretical parameters. The rupture degree r(G) of a graph G = (V, E) is an important graph vulnerability parameter and defined as r(G) = max{omega(G - S) - vertical bar S vertical bar - m(G - S) : omega(G - S) >= 2, S subset of V}, where omega(G - S) and m(G - S) denote the number of connected components and the size of the largest connected component in the graph G - S, respectively. Recently, it has been proved that finding the rupture degree problem is NP- complete. In this paper, a heuristic algorithm to determine the rupture degree of a graph has been developed. Extensive computational experience on 88 randomly generated graphs ranging from 20% to 90% densities and from 100 to 200 vertices shows that the proposed algorithm is very effective.Öğe Heuristic Architecture Search Using Network Morphism for Chest X-Ray Classification(Rwth Aachen, 2020) Radiuk, Pavlo; Kutucu, HakanNowadays, the demand for medical image computing is exceptionally high. This growth was mostly driven by the manual development of machine learning models, in particular neural networks. However, due to the constant evolution of domain requirements, manual model development has become insufficient. The present study proposes a heuristic architecture search that can be in an excellent service for the task of medical image classification. We implemented a novel approach called network morphism to the search algorithm. The proposed search method utilizes the enforced hill-climbing algorithm and functional-saving modifications. As a result of computational experiments, the search method found the optimal architecture in 28 GPU hours. The model formed by the found architecture achieved performance of 73.2% in validation accuracy and 84.5% in AUC on the validation dataset that is competitive to the state-of-the-art hand-crafted networks. Moreover, the proposed search method managed to find the architecture that contains four times fewer parameters. Besides, the model requires almost ten times less physical memory, which may indicate the practical usefulness of our method in medical image analysis.Öğe Hybridization of the SGTM Neural-like Structure through Inputs Polynomial Extension(Ieee, 2018) Vitynskyi, Pavlo; Tkachenko, Roman; Izonin, Ivan; Kutucu, HakanIn this paper, a new approach for increasing the approximation accuracy with the use of computational intelligence tools is described. It is based on the compatible use of the neural-like structure of the Successive Geometric Transformations Model and the inputs polynomial extension. To implement such an extension, second degree Wiener polynomial is used. This combination improves the method accuracy for solving various tasks, such as classification and regression, including short-term and long-term prediction, dynamic pricing, as well as image recognition and image scaling, e-commerce. Due to the use of SGTM neural-like structure, the high speed of the system is maintained in both training and using modes. The simulation of the described approach is carried out on real data, the time results of the neural-like structure work and the accuracy results (MAPE, RMSE, R) are given. A comparison of the operation of the method with existing ones, such as Support vector regression, Classic linear SGTM neural-like structure, Linear regression (using Stochastic Gradient Descent), Random Forest, Multilayer Perceptron, AdaBoost are made. The advantages of the developed approach, in particular with regard to the highest accuracy among existing ones were experimentally established.Öğe LINEAR PROGRAMMING PROBLEMS WITH FUNDAMENTAL CUT MATRICES(Yildiz Technical Univ, 2018) Sharifov, Firdovsi; Kutucu, HakanIn the paper, we consider a linear programming problem with con-straint matrices whose rows are 0, 1 characteristics vectors of fundamental cuts in a given undirected graph G = (V, E). We prove that the simplex algorithm finds an optimal solution in at most m-n+1 (m = vertical bar E vertical bar, n = vertical bar V vertical bar) iterations. We also consider the question whether a given binary matrix is a 0, 1 characteristic vector of fundamental cuts in the graph G.Öğe A Mathematical Model For Finding The Rainbow Connection Number(Ieee, 2013) Nuriyeva, Fidan; Ugurlu, Onur; Kutucu, HakanThe rainbow connection problem belongs to the class of NP-Hard graph theoretical problems. The rainbow connection of a connected graph G, denoted by rc(G), is the smallest number of colors that are needed in order to make G rainbow edge-connected. In this study, we present a new mathematical model for the rainbow connection problem.Öğe Maximum cut problem: new models(Ramazan Yaman, 2020) Kutucu, Hakan; Sharifov, FirdovsiThe maximum cut problem is known to be NP-hard, and consists in determining a partition of the vertices of a given graph such that the sum of the weights of the edges having one end node in each set is maximum. In this paper, we formulate the maximum cut problem as a maximization of a simple non-smooth convex function over the convex hull of bases of the polymatroid associated with a submodular function defined on the subsets of vertices of a given graph. In this way, we show that a greedy-like algorithm with O(mn(2)) time complexity finds a base of a polymatroid that is a solution to the maximum cut problem with different approximation ratio. Moreover, with respect to a base of a polymatroid, we formulate the maximum cut problem as a maximum flow problem between a source and a sink. We then investigate the necessary and sufficient conditions on the optimality of the base in terms of network flow.Öğe A Method for Constructing a Barker-like Sequences Based on Ideal Ring Bundles(Rwth Aachen, 2019) Riznyk, Oleg; Kynash, Yurii; Balych, Bohdan; Vynnychuk, Roksolana; Kret, Igor; Kutucu, HakanTo date, all major reserves for improving the quality of wireless communication are almost exhausted. It is becoming clear to all wireless network designers and manufacturers that instead of using the standard principles of network efficiency enhancement, they should focus their efforts on implementing other principles of radio exchange by creating new code sequences. The Barker-like sequence is taken as the main sequence, and then each element of the main sequence is replaced by a direct or inverse additional Barker-like sequence, depending on whether there is zero or one in the main Barker-like sequence. An algorithm for the synthesis of Barker-like sequences using ideal ring bundles of different types is proposed. The method of constructing Barker combined signals and their autocorrelation functions are considered. The simulation of the obtained Barker-like sequences in the LabVIEW software environment is performed.Öğe Modeling of Solar Energy Potential in Libya using an Artificial Neural Network Model(Ieee, 2016) Kutucu, Hakan; Almryad, AyadIn this work, we develop an artificial neural network model to predict the potential of solar power in Libya. We use multilayered, feed-forward, back-propagation neural networks for the mean monthly solar radiation using the data of 25 cities spread over Libya for the period of 6 years (2010-2015). Meteorological and geographical data (longitude, latitude, and altitude, month, mean sunshine duration, mean temperature, and relative humidity) are used as input to the network. The solar radiation is in the output layer of the network. The results show that the correlation coefficients between the ANN predictions and actual mean monthly global solar radiation for training and testing datasets are higher than 98%. Hence, the predictions from ANN model in locations where solar radiation data are not available has a high reliability.Öğe A NETWORK DESIGN PROBLEM WITH TWO-EDGE MATCHING FAILURES(Edp Sciences S A, 2015) Sharifov, Firdovsi; Kutucu, HakanIn this paper, we introduce a network design problem with two-edge matching failures. Given a graph, any two edges non-incident to the same node form a two-edge matching. The problem consists in finding a minimum-cost subgraph such that, when deleting any two-edge matching of the graph, every pair of terminal nodes remains connected. We give mixed integer linear programming formulations for the problem and propose a heuristic algorithm based on the Branch-and-Bound method to solve it. We also present computational results.Öğe New heuristics and meta-heuristics for the Bandpass problem(Elsevier - Division Reed Elsevier India Pvt Ltd, 2017) Gursoy, Arif; Kurt, Mehmet; Kutucu, Hakan; Nuriyev, UrfatThe Bandpass problem (BP), modelled by Babayev et al., is a combinatorial optimization problem arising in optical communication networks using wavelength division multiplexing technology. The BP aims to design an optimal packing of information flows on different wavelengths into groups to obtain the highest available cost reduction. In this paper, we propose new methods to solve the BP. Firstly, we present two new heuristic algorithms which generate better solutions than the algorithm introduced by Babayev et al. for almost all of the problem instances of the BP library. Secondly, we present a new meta-heuristic algorithm using three different crossover and five different mutation operators. Totally, fifteen implementations have been created and tested using two different outputs which are obtained by our proposed heuristics as the initial population. The experimental results show that the proposed meta-heuristic algorithm improves the solutions. (C) 2017 Karabuk University. Publishing services by Elsevier B.V.
