Bilgisayar Mühendisliği Bölümü

Permanent URI for this communityhttps://hdl.handle.net/20.500.12416/13

Browse

Now showing 1 - 20 of 23

Citation - WoS: 40
Citation - Scopus: 40
A density functional study of bare and hydrogenated platinum clusters
(Elsevier, 2006) Sebetci, Ali; 20965; İç Mimarlık
We perform density functional theory calculations using Gaussian atomic-orbital methods within the generalized gradient approximation for the exchange and correlation to study the interactions in the bare and hydrogenated platinum clusters. The minimum-energy structures, binding energies, relative stabilities. vibrational frequencies and the highest occupied and lowest unoccupied molecular-orbital gaps of PtnHm (n = 1-5, m = 0-2) clusters are calculated and compared with previously studied pure platinum and hydrogenated platinum clusters. We investigate any magic behavior in hydrogenated platinum clusters and find that Pt4H2 is snore stable than its neighboring sizes. The lowest energy structure of Pt-4 is found to be a distorted tetrahedron and that of Pt-5 found to be a bridge site capped tetrahedron which is a new global minimum for Pt-5 cluster. The successive addition of H atoms to Pt-n clusters leads to an oscillatory change in the magnetic moment of Pt-3-Pt-5 clusters. (c) 2006 Elsevier B.V. All rights reserved.
Citation - WoS: 6
Citation - Scopus: 6
Auction-Based Serious Game for Bug Tracking
(Wiley, 2019) Usfekes, Cagdas; Tuzun, Eray; Yilmaz, Murat; Macit, Yagup; Clarke, Paul
Today, one of the challenges in software engineering is utilising application lifecycle management (ALM) tools effectively in software development. In particular, it is hard for software developers to engage with the work items that are appointed to themselves in these ALM tools. In this study, the authors have focused on bug tracking in ALM where one of the most important metrics is mean time to resolution that is the average time to fix a reported bug. To improve this metric, they developed a serious game application based on an auction-based reward mechanism. The ultimate aim of this approach is to create an incentive structure for software practitioners to find and resolved bugs that are auctioned where participants are encouraged to solve and test more bugs in less time and improve quality of software development in a competitive environment. They conduct hypothesis tests by performing a Monte Carlo simulation. The preliminary results of this research support the idea that using a gamification approach for an issue tracking system enhances the productivity and decreases mean time to resolution.
Citation - WoS: 2
Citation - Scopus: 2
Binary background model with geometric mean for author-independent authorship verification
(Sage Publications Ltd, 2023) Canbay, Pelin; Sever, Hayri; Sezer, Ebru A.; Sever, Hayri; 11916; Bilgisayar Mühendisliği
Authorship verification (AV) is one of the main problems of authorship analysis and digital text forensics. The classical AV problem is to decide whether or not a particular author wrote the document in question. However, if there is one and relatively short document as the author's known document, the verification problem becomes more difficult than the classical AV and needs a generalised solution. Regarding to decide AV of the given two unlabeled documents (2D-AV), we proposed a system that provides an author-independent solution with the help of a Binary Background Model (BBM). The BBM is a supervised model that provides an informative background to distinguish document pairs written by the same or different authors. To evaluate the document pairs in one representation, we also proposed a new, simple and efficient document combination method based on the geometric mean of the stylometric features. We tested the performance of the proposed system for both author-dependent and author-independent AV cases. In addition, we introduced a new, well-defined, manually labelled Turkish blog corpus to be used in subsequent studies about authorship analysis. Using a publicly available English blog corpus for generating the BBM, the proposed system demonstrated an accuracy of over 90% from both trained and unseen authors' test sets. Furthermore, the proposed combination method and the system using the BBM with the English blog corpus were also evaluated with other genres, which were used in the international PAN AV competitions, and achieved promising results.
Citation - WoS: 38
Citation - Scopus: 41
Detection of hip osteoarthritis by using plain pelvic radiographs with deep learning methods
(Springer, 2020) Ureten, Kemal; Arslan, Tayfun; Gultekin, Korcan Emre; Demir, Ayse Nur Demirgoz; Ozer, Hafsa Feyza; Bilgili, Yasemin
Objective The incidence of osteoarthritis is gradually increasing in public due to aging and increase in obesity. Various imaging methods are used in the diagnosis of hip osteoarthritis, and plain pelvic radiography is the first preferred imaging method in the diagnosis of hip osteoarthritis. In this study, we aimed to develop a computer-aided diagnosis method that will help physicians for the diagnosis of hip osteoarthritis by interpreting plain pelvic radiographs. Materials and methods In this retrospective study, convolutional neural networks were used and transfer learning was applied with the pre-trained VGG-16 network. Our dataset consisted of 221 normal hip radiographs and 213 hip radiographs with osteoarthritis. In this study, the training of the network was performed using a total of 426 hip osteoarthritis images and a total of 442 normal pelvic images obtained by flipping the raw data set. Results Training results were evaluated with performance metrics such as accuracy, sensitivity, specificity, and precision calculated by using the confusion matrix. We achieved accuracy, sensitivity, specificity and precision results at 90.2%, 97.6%, 83.0%, and 84.7% respectively. Conclusion We achieved promising results with this computer-aided diagnosis method that we tried to develop using convolutional neural networks based on transfer learning. This method can help clinicians for the diagnosis of hip osteoarthritis while interpreting plain pelvic radiographs, also provides assistance for a second objective interpretation. It may also reduce the need for advanced imaging methods in the diagnosis of hip osteoarthritis.
Citation - WoS: 56
Citation - Scopus: 64
Detection of Rheumatoid Arthritis From Hand Radiographs Using A Convolutional Neural Network
(Springer London Ltd, 2020) Ureten, Kemal; Erbay, Hasan; Maras, Hadi Hakan
Introduction Plain hand radiographs are the first-line and most commonly used imaging methods for diagnosis or differential diagnosis of rheumatoid arthritis (RA) and for monitoring disease activity. In this study, we used plain hand radiographs and tried to develop an automated diagnostic method using the convolutional neural networks to help physicians while diagnosing rheumatoid arthritis. Methods A convolutional neural network (CNN) is a deep learning method based on a multilayer neural network structure. The network was trained on a dataset containing 135 radiographs of the right hands, of which 61 were normal and 74 RA, and tested it on 45 radiographs, of which 20 were normal and 25 RA. Results The accuracy of the network was 73.33% and the error rate 0.0167. The sensitivity of the network was 0.6818; the specificity was 0.7826 and the precision 0.7500. Conclusion Using only pixel information on hand radiographs, a multi-layer CNN architecture with online data augmentation was designed. The performance metrics such as accuracy, error rate, sensitivity, specificity, and precision state shows that the network is promising in diagnosing rheumatoid arthritis.
Citation - WoS: 9
Citation - Scopus: 10
Diagnosis of osteoarthritic changes, loss of cervical lordosis, and disc space narrowing on cervical radiographs with deep learning methods
(Turkish Joint Diseases Foundation, 2022) Maras, Yuksel; Tokdemir, Gül; Tokdemir, Gul; Ureten, Kemal; Atalar, Ebru; Duran, Semra; Maras, Hakan; 17411; 34410; Bilgisayar Mühendisliği
Objectives: In this study, we aimed to differentiate normal cervical graphs and graphs of diseases that cause mechanical neck pain by using deep convolutional neural networks (DCNN) technology. Materials and methods: In this retrospective study, the convolutional neural networks were used and transfer learning method was applied with the pre-trained VGG-16, VGG-19, Resnet-101, and DenseNet-201 networks. Our data set consisted of 161 normal lateral cervical radiographs and 170 lateral cervical radiographs with osteoarthritis and cervical degenerative disc disease. Results: We compared the performances of the classification models in terms of performance metrics such as accuracy,
Citation - WoS: 7
Citation - Scopus: 8
Fragmentation of water clusters: molecular-dynamics simulation study
(Springer-verlag, 2001) Erkoç, S; Kökten, H; Güvenç, Z
The fragmentation of water clusters, [(H2O)(n): n = 2-8], have been investigated by using molecular-dynamics simulation method. In the simulations a polarizable-dissociable potential energy function for water has been used. Particular attention has been paid to investigate the effect of structural properties and cluster size of the fragmentation.
Citation - WoS: 49
Citation - Scopus: 49
Global minima of Al(N), Au(N) and Pt(N), N <= 80, clusters described by the Voter-Chen version of embedded-atom potentials
(Iop Publishing Ltd, 2005) Sebetci, A; Güvenç, ZB
We report the global minima for aluminium, gold and platinum metal clusters modelled by the Voter-Chen version of the embedded-atom model potential containing up to 80 atoms using the basin-hopping Monte Carlo minimization approach. The results show that the global minima of the Al, Au and Pt clusters have structures based on either octahedral, decahedral, icosahedral or a mixture of decahedral and icosahedral packing. The 54-atom icosahedron without a central atom is found to be more stable than the 55-atom complete icosahedron for all of the elements considered in this work. Most of the Al global minima are identified as face-centred cubic structures and many of the An global minima are found to be low symmetric structures, both of which are in agreement with the previous theoretical and experimental Studies. Although many of the Pt global minima are identical with the global minima of the corresponding Au clusters, the most stable sizes of the Pt clusters correspond to the same sizes of the Al clusters.
Citation - WoS: 2
Citation - Scopus: 2
Guest Editorial: Gamification and Persuasive Games for Software Engineering
(inst Engineering Technology-iet, 2019) Yilmaz, Murat; Yılmaz, Murat; O'Connor, Rory V.; Colomo-Palacios, Ricardo; Clarke, Paul; Yazılım Mühendisliği
Citation - WoS: 11
Citation - Scopus: 15
Integration of accessibility design patterns with the software implementation process of ISO/IEC 29110
(Wiley, 2019) Sanchez-Gordon, Sandra; Yılmaz, Murat; Sanchez-Gordon, Mary; Yilmaz, Murat; O'Connor, Rory V.; 55248; Yazılım Mühendisliği
The Web Content Accessibility Guidelines was developed by World Wide Web Consortium with a goal of providing a single shared standard for web content accessibility that meets the needs of individuals, organizations, and governments. Given that there is a large percentage of very small entities that develop software who also utilize the ISO/IEC software process standard, the purpose of this study is the development of software design patterns for users with visual disabilities. As a result, four accessibility design patterns are defined: Authentication adapter, Blindness adapter, Dichromatic color vision adapter, and Blurry vision adapter. These patterns will help to improve the design of the web applications built using them while being compliant with the ISO/IEC 29110 standard. The use of design patterns also enables the transfer of design experience to programming practices and improves the software documentation. To validate the set of patterns, an online course for Spanish speakers was developed, and the evaluation was carried out using simulators, automated tools, experts, and users. Simulators and automated tools showed no accessibility errors and experts evaluated 10 heuristics principles and did not identify any severity issues. Taken together, our results provide positive evidence that users with visual disabilities could benefit from the proposed features.
Citation - WoS: 22
Citation - Scopus: 28
Interactive three-dimensional virtual environment to reduce the public speaking anxiety levels of novice software engineers
(inst Engineering Technology-iet, 2019) Nazligul, M. Denizci; Güleç, Ulaş; Yilmaz, M.; Gulec, U.; Yilmaz, A. E.; Isler, V.; O'Connor, R. V.; Clarke, P.; 47439; Bilgisayar Mühendisliği
Software engineering is a set of activities that rely not only on the technical tasks but also require abilities focused on social duties such as daily meetings and product introduction presentations. However, engineers may experience elevated levels of anxiety when required to present their work in an unfamiliar environment. More specifically, they may suffer from public speaking anxiety even though they are supposed to be effective in those social tasks as well as in their engineering activities. Fortunately, previous studies suggest that the virtual exposure intervention is an effective strategy to reduce public speaking anxiety. In this study, an interactive three-dimensional virtual environment similar to real classrooms and auditoriums was developed to examine whether this might decrease the anxiety levels of novice software engineers. To compare the traditional and virtual exposure intervention, the sample set was divided equally into two groups including one experimental group and one control group. For 4 weeks, the virtual exposure intervention was conducted in the experimental group, whereas the cognitive behaviour therapy-based psychoeducation was used in the control group. The findings from authors' study illustrate that the virtual exposure intervention may represent an alternative solution to the traditional interventions for software engineers seeking to overcome public presentation anxiety.
Citation - WoS: 8
Citation - Scopus: 8
Localization of metallicity and magnetic properties of graphene and of graphene nanoribbons doped with boron clusters
(Taylor & Francis Ltd, 2014) Ozdogan, Cem; Özdoğan, Cem; Kunstmann, Jens; Quandt, Alexander; 40569; Ortak Dersler Bölümü
As a possible way of modifying the intrinsic properties of graphene, we study the doping of graphene by embedded boron clusters with density functional theory. Cluster doping is technologically relevant as the cluster implantation technique can be readily applied to graphene. We find that B-7 clusters embedded into graphene and graphene nanoribbons are structurally stable and locally metallize the system. This is done both by the reduction of the Fermi energy and by the introduction of boron states near the Fermi level. A linear chain of boron clusters forms a metallic "wire" inside the graphene matrix. In a zigzag edge graphene nanoribbon, the cluster-related states tend to hybridize with the edge and bulk states. The magnetism in boron-doped graphene systems is generally very weak. The presence of boron clusters weakens the edge magnetism in zigzag edge graphene nanoribbon, rather than making the system appropriate for spintronics. Thus, the doping of graphene with the cluster implantation technique might be a viable technique to locally metallize graphene without destroying its attractive bulk properties.
Citation - WoS: 57
Citation - Scopus: 65
Molecular dynamics simulation of sintering and surfacepremelting of silver nanoparticles
(Japan inst Metals & Materials, 2013) Alarifi, H. A.; Özdoğan, Cem; Atis, M.; Ozdogan, C.; Hu, A.; Yavuz, M.; Zhou, Y.; 40569; Ortak Dersler Bölümü
Sintering of Ag nanoparticles (NPs) is increasingly being used as a driving mechanism for joining in the microelectronics industry. We therefore performed molecular dynamics simulations based on the embedded atom method (EAM) to study pressureless sintering kinetics of two Ag NPs in the size range of (4 to 20 nm), and sintering of three and four Ag NPs of 4 nm diameter. We found that the sintering process passed through three main stages. The first was the neck formation followed by a rapid increase of the neck radius at 50K for 20 nm particles and at 10 K for smaller NPs. The second was characterized by a gradual linear increase of the neck radius to particle radius ratio as the temperature of the sintered structure was increased to the surface premelting point. Different than previous sintering studies, a twin boundary was formed during the second stage that relaxed the sintered structure and decreased the average potential energy (PE). The third stage of sintering was a rapid shrinkage during surface premelting of the sintered structure. Based on pore geometry, densification occurred during the first stage for three 4 nm particles and during the second stage for four 4 nm particles. Sintering rates obtained by our simulation were higher than those obtained by theoretical models generally used for predicting sintering rates of microparticles.
Citation - Scopus: 3
Oscillation for a nonlinear dynamic system on time scales
(2011) Erbe, L.; Mert, Raziye; Mert, R.; 19485; Matematik
We study the oscillation properties of a system of two first-order nonlinear equations on time scales. This form includes the classical Emden-Fowler differential and difference equations and many of its extensions. We generalize some well-known results of Atkinson, Belohorec, Waltman, Hooker, Patula and others and also describe the relation to solutions of a delay-dynamic system. © 2011 Taylor & Francis.
Citation - WoS: 24
Citation - Scopus: 27
Partially coherent Airy beam and its propagation in turbulent media
(Springer Heidelberg, 2013) Eyyuboglu, Halil T.; Sermutlu, Emre; Sermutlu, Emre; 7688; 17647; Matematik
The properties of partially coherent Airy beam propagating in turbulent media are investigated. Firstly the variations in the intensity profile and the location of the Airy beam peak with respect to dislocation and width parameters are examined. On the source plane, it is shown that there is a threshold value of the dislocation parameter which determines whether the beam peak will lie on the negative or positive side of the axis. The changes in source beam power and source beam size with respect to dislocation and width parameters are also examined. Then analysis is made for partially coherent Airy beam propagating in turbulence against variations in propagation distance, dislocation and width parameters, structure constant and partial coherence. It is found that the peak of the Airy beam will always shift to the right for increasing propagation distance. But this shift will become less as the dislocation and width parameters are increased. Finally it is shown that higher levels of turbulence and partial coherence will lead to more spreading and shift the beam peak more toward the on-axis position.
Citation - WoS: 12
Citation - Scopus: 14
Reactions of small Ni clusters with a diatomic molecule: MD simulation of D(2)+Ni(n) (n=7-10) systems
(Elsevier Science Bv, 2000) Durmus, P; Böyükata, M; Özçelik, S; Güvenç, ZB; Jellinek, J
The kinetics of the reactions of nickel clusters with a deuterium molecule are studied, Dissociative chemisorption probabilities of the D(2) molecule on the small Ni(n) (n=7-10) clusters are computed by a quasi-classical molecular dynamics computer simulation technique. Structures of the clusters are obtained by an embedded-atom potential, and the interaction between the D(2) and Ni(n) is modelled by an LEPS (London-Eyring-Polanyi-Sato) function (energy surface). This analysis includes the chemisorption probabilities as functions of the impact parameter and of the relative translational energy of the D(2). The corresponding reactive cross-sections for the ground state of the molecule are calculated as functions of the collision energy and the size of the cluster. The role of the size of the clusters is examined. An indirect mechanism to the reaction, which involves formation of molecular adsorption as precursors to dissociative adsorption in the low collision energy region (less than 0.1eV), is observed. Results are discussed by comparing with the other similar theoretical and experimental studies. (C) 2000 Elsevier Science B.V. All rights reserved.
Citation - WoS: 8
Citation - Scopus: 7
Sputtering yield and dynamical analysis of Ni(100) surface: A comparison of four different Ar-surface interaction potentials
(Elsevier Science Bv, 2000) Güvenç, ZB; Hundur, Y; Hippler, R
The sputtering process of the Ar + Ni(100) collision system is investigated by means of constant energy molecular dynamics simulations. The Ni(100) is mimicked by an embedded-atom potential, and the interaction between the projectile and the surface is modelled by using four different screened Coulomb type potentials. The Ni atom emission from the lattice is analysed over the range of 10-40 eV collision energy. The maximum penetration depths of Ar, probability distributions of kinetic energy of the reflected Ar, and energy of the Ar and sputtered Ni atoms in the same collision events are evaluated as functions of the impact energy and sputtering time. Further, angular distributions of the scattered Ar are obtained. The calculated sputtering yields are compared with the available theoretical and experimental data. (C) 2000 Elsevier Science B.V. All rights reserved.
Citation - WoS: 0
Citation - Scopus: 1
Surface modification by 1 keV ion impact: molecular dynamics study of an Ar+-Ni(100) collision system
(Iop Publishing Ltd, 2008) Ozdogan, Cem; Özdoğan, Cem; Atis, Murat; Guvenc, Ziya B.; 28225; Ortak Dersler Bölümü
An Ar+-Ni(1 0 0) collision system at 1 keV impact energy was investigated by using realistic isoenergetic molecular dynamics (MD) simulations. The sputtering process upon Ar+ ion impact and damage to the Ni(1 0 0) surface are examined in detail. Studying of high bombarding energy regions leads to the necessity of larger and thick enough slabs, otherwise incoming ions can easily pass through the slab; as a result, investigated physical properties may not be revealed. In addition the simulation time should be long enough to observe and to calculate a reliable macroscopic property such as sputtering yield that is addressed in this study. In order to preserve the total energy in the simulation at this collision energy a small time-step (0.1 fs) is used. We have made use of our developed linear scaling parallel MD program to overcome these demands. The Ni(1 0 0) slab is formed by 63700 atoms (122 angstrom x 122 angstrom x 44 angstrom) and the total observation time for each collision event is about 2.25 ps. Several properties such as penetration depths, angular and energy distributions of the reflected Ar and sputtered Ni atoms as well as dissociation time, embedded, scattering, sputtering patterns and geometries of the sputtered clusters are also reported, and the calculated sputtering yield is found to be in good agreement with the available experimental results.
Citation - WoS: 8
Citation - Scopus: 9
The Diagnosis of Developmental Dysplasia of the Hip From Hip Ultrasonography Images With Deep Learning Methods
(Lippincott Williams & Wilkins, 2023) Atalar, Hakan; Tokdemir, Gül; Ureten, Kemal; Tokdemir, Gul; Tolunay, Tolga; Ciceklidag, Murat; Atik, Osman Sahap; 17411; Bilgisayar Mühendisliği
Background:Hip ultrasonography is very important in the early diagnosis of developmental dysplasia of the hip. The application of deep learning-based medical image analysis to computer-aided diagnosis has the potential to provide decision-making support to clinicians and improve the accuracy and efficiency of various diagnostic and treatment processes. This has encouraged new research and development efforts in computer-aided diagnosis. The aim of this study was to evaluate hip sonograms using computer-assisted deep-learning methods. Methods:The study included 376 sonograms evaluated as normal according to the Graf method, 541 images with dysplasia and 365 images with incorrect probe position. To classify the developmental hip dysplasia ultrasound images, transfer learning was applied with pretrained VGG-16, ResNet-101, MobileNetV2 and GoogLeNet networks. The performances of the networks were evaluated with the performance parameters of accuracy, sensitivity, specificity, precision, F1 score, and AUC (area under the ROC curve). Results:The accuracy, sensitivity, specificity, precision, F1 score, and AUC results obtained by testing the VGG-16, ResNet-101, MobileNetV2, and GoogLeNet models showed performance >80%. With the pretrained VGG-19 model, 93%, 93.5%, 96.7%, 92.3%, 92.6%, and 0.99 accuracy, sensitivity, specificity, precision, F1 score, and AUC results were obtained, respectively. Conclusion:In this study, in addition to the ultrasonography images of dysplastic and healthy hips, images were also included of probe malpositioning, and these images were able to be successfully evaluated with deep learning methods. On the sonograms, which provided criteria appropriate for evaluation, successful differentiation could be made of healthy hips and dysplastic hips.
Citation - WoS: 5
Citation - Scopus: 7
The diagnosis of femoroacetabular impingement can be made on pelvis radiographs using deep learning methods
(Turkish Joint Diseases Foundation, 2023) Atalar, Ebru; Ureten, Kemal; Kanatli, Ulunay; Ciceklidag, Murat; Kaya, Ibrahim; Vural, Abdurrahman; Maras, Yuksel
Objectives: The aim of this study was to evaluate diagnostic ability of deep learning models, particularly convolutional neural network models used for image classification, for femoroacetabular impingement (FAI) using hip radiographs. Materials and methods: Between January 2010 and December 2020, pelvic radiographs of a total of 516 patients (270 males, 246 females; mean age: 39.1 +/- 3.8 years; range, 20 to 78 years) with hip pain were retrospectively analyzed. Based on inclusion and exclusion criteria, a total of 888 hip radiographs (308 diagnosed with FAI and 508 considered normal) were evaluated using deep learning methods. Pre-trained VGG-16, ResNet-101, MobileNetV2, and Inceptionv3 models were used for transfer learning. Results: As assessed by performance measures such as accuracy, sensitivity, specificity, precision, F-1 score, and area under the curve (AUC), the VGG-16 model outperformed other pre-trained networks in diagnosing FAI. With the pre-trained VGG-16 model, the results showed 86.6% accuracy, 82.5% sensitivity, 89.6% specificity, 85.5% precision, 83.9% F1 score, and 0.92 AUC. Conclusion: In patients with suspected FAI, pelvic radiography is the first imaging method to be applied, and deep learning methods can help in the diagnosis of this syndrome.

Browse

Browsing Bilgisayar Mühendisliği Bölümü by WoS Q "Q3"