Bilgisayar Mühendisliği Bölümü Yayın Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/253
Browse
19 results
Search Results
Article Citation - WoS: 11Citation - Scopus: 12Diagnosis of Osteoarthritic Changes, Loss of Cervical Lordosis, and Disc Space Narrowing on Cervical Radiographs With Deep Learning Methods(Turkish Joint Diseases Foundation, 2022) Tokdemir, Gul; Ureten, Kemal; Atalar, Ebru; Duran, Semra; Maras, Hakan; Maras, YukselObjectives: 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,Article Citation - WoS: 43Citation - Scopus: 50Detection 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, YaseminObjective 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.Article Citation - WoS: 3Citation - Scopus: 9Two Majority Voting Classifiers Applied To Heart Disease Prediction(Mdpi, 2023) Karadeniz, Talha; Maras, Hadi Hakan; Tokdemir, Gul; Ergezer, HalitTwo novel methods for heart disease prediction, which use the kurtosis of the features and the Maxwell-Boltzmann distribution, are presented. A Majority Voting approach is applied, and two base classifiers are derived through statistical weight calculation. First, exploitation of attribute kurtosis and attribute Kolmogorov-Smirnov test (KS test) result is done by plugging the base categorizer into a Bagging Classifier. Second, fitting Maxwell random variables to the components and summating KS statistics are used for weight assignment. We have compared state-of-the-art methods to the proposed classifiers and reported the results. According to the findings, our Gaussian distribution and kurtosis-based Majority Voting Bagging Classifier (GKMVB) and Maxwell Distribution-based Majority Voting Bagging Classifier (MKMVB) outperform SVM, ANN, and Naive Bayes algorithms. In this context, which also indicates, especially when we consider that the KS test and kurtosis hack is intuitive, that the proposed routine is promising. Following the state-of-the-art, the experiments were conducted on two well-known datasets of Heart Disease Prediction, namely Statlog, and Spectf. A comparison of Optimized Precision is made to prove the effectiveness of the methods: the newly proposed methods attained 85.6 and 81.0 for Statlog and Spectf, respectively (while the state of the heart attained 83.5 and 71.6, respectively). We claim that the Majority Voting family of classifiers is still open to new developments through appropriate weight assignment. This claim is obvious, especially when its simple structure is fused with the Ensemble Methods' generalization ability and success.Article Citation - WoS: 9Citation - Scopus: 11The 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, YukselObjectives: 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.Article Citation - WoS: 2Citation - Scopus: 2Risk Assessment of Sea Level Rise for Karasu Coastal Area, Turkey(Mdpi, 2023) Genc, Asli Numanoglu; Tora, Hakan; Maras, Hadi Hakan; Eliawa, Ali; Numanoğlu Genç, AslıSea Level Rise (SLR) due to global warming is becoming a more pressing issue for coastal zones. This paper presents an overall analysis to assess the risk of a low-lying coastal area in Karasu, Turkey. For SLR scenarios of 1 m, 2 m, and 3 m by 2100, inundation levels were visualized using Digital Elevation Model (DEM). The eight-side rule is applied as an algorithm through Geographic Information System (GIS) using ArcMap software with high-resolution DEM data generated by eleven 1:5000 scale topographic maps. The outcomes of GIS-based inundation maps indicated 1.40%, 6.02%, and 29.27% of the total land area by 1 m, 2 m, and 3 m SLR scenarios, respectively. Risk maps have shown that water bodies, low-lying urban areas, arable land, and beach areas have a higher risk at 1 m. In a 2 m scenario, along with the risk of the 1 m scenario, forests become at risk as well. For the 3 m scenario, almost all the territorial features of the Karasu coast are found to be inundated. The effect of SLR scenarios based on population and Gross Domestic Product (GDP) is also analyzed. It is found that the 2 and 3 m scenarios lead to a much higher risk compared to the 1 m scenario. The combined hazard-vulnerability data shows that estuarine areas on the west and east of the Karasu region have a medium vulnerability. These results provide primary assessment data for the Karasu region for the decision-makers to enhance land use policies and coastal management plans.Article Structural stability and energetics of single-walled carbon nanotubes under uniaxial strain(2003) Dereli, G.; Özdoğan, CemA (10x10) single-walled carbon nanotube consisting of 400 atoms with 20 layers is simulated under tensile loading using our developed O(N) parallel tight-binding molecular-dynamics algorithms. It is observed that the simulated carbon nanotube is able to carry the strain up to 122% of the relaxed tube length in elongation and up to 93% for compression. Young's modulus, tensile strength, and the Poisson ratio are calculated and the values found are 0.311 TPa, 4.92 GPa, and 0.287, respectively. The stress-strain curve is obtained. The elastic limit is observed at a strain rate of 0.09 while the breaking point is at 0.23. The frequency of vibration for the pristine (10x10) carbon nanotube in the radial direction is 4.71x10(3) GHz and it is sensitive to the strain rate.Article Citation - WoS: 69Citation - Scopus: 90Structural Stability and Energetics of Single-Walled Carbon Nanotubes Under Uniaxial Strain(Amer Physical Soc, 2003) Ozdogan, C; Dereli, GA (10x10) single-walled carbon nanotube consisting of 400 atoms with 20 layers is simulated under tensile loading using our developed O(N) parallel tight-binding molecular-dynamics algorithms. It is observed that the simulated carbon nanotube is able to carry the strain up to 122% of the relaxed tube length in elongation and up to 93% for compression. Young's modulus, tensile strength, and the Poisson ratio are calculated and the values found are 0.311 TPa, 4.92 GPa, and 0.287, respectively. The stress-strain curve is obtained. The elastic limit is observed at a strain rate of 0.09 while the breaking point is at 0.23. The frequency of vibration for the pristine (10x10) carbon nanotube in the radial direction is 4.71x10(3) GHz and it is sensitive to the strain rate.Article Citation - WoS: 4Citation - Scopus: 4Phase Changes in Icosahedral 54-, 55-, 56-Atom Platinum Clusters(World Scientific Publ Co Pte Ltd, 2004) Güvenç, ZB; Kökten, H; Sebetci, AUsing the Voter and Chen version of an embedded-atom model, derived by fitting simultaneously to experimental data both the diatomic molecule and bulk platinum, we have studied the melting behavior of free, icosahedral, 54-, 55- and 56-atom platinum clusters in the molecular dynamics simulation technique. We present an atom-resolved analysis method that includes physical quantities such as the root-mean-square bond-length fluctuation and coordination number for individual atoms as functions of temperature. The effect of a central atom in the icosahedral structure to the melting process is discussed. The results show that the global minimum structures of the 54-, 55- and 56-atom Pt clusters do not melt at a specific temperature, rather, melting processes take place over a finite temperature range. The heat capacity peaks are not delta-functions, but instead remain finite. An ensemble of clusters in the melting region is a mixture of solid-like and liquid-like clusters.Article Citation - WoS: 3Citation - Scopus: 3Finite Size Scaling by Using Scaling Functions in Two-Dimensional Q=2 and 7 State Potts Models(World Scientific Publ Co Pte Ltd, 2001) Seferoglu, N; Aydin, M; Gündüç, Y; Demirtürk, SThe scaling behaviors of the percolation cumulant and the surface renormalization are studied on q = 2 and 7 state Potts models. The results show that the scaling functions can be safely used to determine infinite lattice transition points and the thermal and magnetic exponents indicating that these functions have very small correction to scaling contributions.Article Citation - WoS: 13Citation - Scopus: 17A Mash-Up Application Utilizing Hybridized Filtering Techniques for Recommending Events at a Social Networking Site(Springer Wien, 2011) Kayaalp, Mehmet; Ozyer, Tansel; Ozyer, Sibel T.Event recommendation is one way of gathering people having same likes/dislikes. In today's world, many mass amounts of events are organized at different locations and times. Generally, cliques of people are fans of some specific events. They attend together based on each other's recommendation. Generally, there are many activities that people prefer/opt out attending and these events are announced for attracting relevant people. Rather than, peerto-peer oracles of a local group of people, or sentiments of people from different sources, an intelligent recommendation system can be used at a social networking site in order to recommend people in collaborative and content basis within a social networking site. We have used an existing social environment (http://www.facebook.com) for deployment. Our application has also been integrated with several web sites for collecting information for assessment. Our system has been designed in modules so that it is open to new data sources either by using web services or web scraping. Currently, our application is yet an application that permits users rate events; they have attended or have beliefs on them. Given the social network between people, system tries to recommend upcoming events to users. For this purpose, we have exploited the fact that a similarity relationship between different events can exist in terms of both content and collaborative filtering. Geographical locations have an impact so; we have also taken geographical location information and social concept of an event. Eventually, our system integrates different sources in facebook (http://www.facebook.com) for doing recommendation between people in close relationship. We have performed experiments among a group of students. Experiments led us have promising results.