Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections

Permanent URI for this collectionhttps://hdl.handle.net/20.500.13091/3

Browse

Now showing 1 - 20 of 405

Citation - WoS: 2
Citation - Scopus: 2
Adrenal Lesion Classification With Abdomen Caps and the Effect of Roi Size
(Springer, 2023) Solak, Ahmet; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
Accurate classification of adrenal lesions on magnetic resonance (MR) images are very important for diagnosis and treatment planning. The detection and classification of lesions in medical imaging heavily rely on several key factors, including the specialist's level of experience, work intensity, and fatigue of the clinician. These factors are critical determinants of the accuracy and effectiveness of the diagnostic process, which in turn has a direct impact on patient health outcomes. With the spread of artificial intelligence, the use of computer-aided diagnosis (CAD) systems in disease diagnosis has also increased. In this study, adrenal lesion classification was performed using deep learning on MR images. The data set used was obtained from the Department of Radiology, Faculty of Medicine, Selcuk University, and all adrenal lesions were identified and reviewed in consensus by two radiologists experienced with abdominal MR. Studies were carried out on two different data sets created by T1- and T2-weighted MR images. The data set consisted of 112 benign and 10 malignant lesions for each mode. Experiments were performed with regions of interest (ROIs) of different sizes to increase the working performance. Thus, the effect of the selected ROI size on the classification performance was assessed. In addition, instead of the convolutional neural network (CNN) models used in deep learning, a unique classification model structure called Abdomen Caps was proposed. When the data sets used in classification studies are manually separated for training, validation, and testing, different results are obtained with different data sets for each stage. To eliminate this imbalance, tenfold cross-validation was used in this study. The best results obtained were 0.982, 0.999, 0.969, 0.983, 0.998, and 0.964 for accuracy, precision, recall, F1-score, area under the curve (AUC) score, and kappa score, respectively.
Citation - Scopus: 1
Adrenal Tumor Segmentation on U-Net: a Study About Effect of Different Parameters in Deep Learning
(World Scientific Publ Co Pte Ltd, 2023) Solak, Ahmet; Ceylan, Rahime; Bozkurt, Mustafa Alper; Cebeci, Hakan; Koplay, Mustafa
Adrenal lesions refer to abnormalities or growths that occur in the adrenal glands, which are located on top of each kidney. These lesions can be benign or malignant and can affect the function of the adrenal glands. This paper presents a study on adrenal tumor segmentation using a modified U-Net model with various parameter selection strategies. The study investigates the effect of fine-tuning parameters, including k-fold values and batch sizes, on segmentation performance. Additionally, the study evaluates the effectiveness of different preprocessing techniques, such as Discrete Wavelet Transform (DWT), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Image Fusion, in enhancing segmentation accuracy. The results show that the proposed model outperforms the original U-Net model, achieving the highest scores for Dice, Jaccard, sensitivity, and specificity scores of 0.631, 0.533, 0.579, and 0.998, respectively, on the T1-weighted dataset with DWT applied. These results highlight the importance of parameter selection and preprocessing techniques in improving the accuracy of adrenal tumor segmentation using deep learning.
Adsorptive Separation of Propionic Acid From Aqueous Medium Using Efficient Anion Exchange Resins in Batch and Fixed Bed Column Systems
(Wiley, 2025) Marti, Mustafa Esen; Isik, Murat; Zeidan, Hani
The recovery of propionic acid (PA) from aqueous medium using a strongly basic, Lewatit M-600 (LM-600), and a weakly basic, Lewatit MP-62 (LMP-62), anion exchanger was investigated. Medium conditions such as pH, temperature, PA concentration, and resin dose affected the performance of the process. The highest capacities were achieved at pH 5 and 2 with LM-600 and LMP-62, respectively. Equilibrium was reached in 35 min, and the process followed the pseudo-second-order kinetics for both anion exchangers. LMP-62 was more effective at pH values lower than 5. The exothermic process was found to be spontaneous. The maximum capacities of the strong and weak basic exchangers in batch experiments were 135.7 and 363 mg/g, respectively. However, the breakthrough capacities obtained in fixed bed systems were lower than those attained in batch systems (94.75 and 123.73 mg/g for LM-600 and LMP-62, respectively), and the column was successfully regenerated using 0.6 M NaOH. The Freundlich isotherm model yielded the highest determination coefficients in the isotherm analysis, suggesting that physical forces between PA and resins primarily drive the process.
Citation - WoS: 12
Citation - Scopus: 11
Aerodynamic Optimization of a Swept Horizontal Axis Wind Turbine Blade
(ASME, 2021) Kaya, Mehmet Numan; Köse, Faruk; Uzol, Oğuz; Ingham, Derek; Ma, Lin; Pourkashanian, Mohamed
The aerodynamic shapes of the blades are still of high importance and various aerodynamic designs have been developed in order to increase the amount of energy production. In this study, a swept horizontal axis wind turbine blade has been optimized to increase the aerodynamic efficiency using the computational fluid dynamics method. To illustrate the technique, a wind turbine with a rotor diameter of 0.94 m has been used as the baseline turbine, and the most appropriate swept blade design parameters, namely the sweep start-up section, tip displacement, and mode of the sweep have been investigated to obtain the maximum power coefficient at the design tip speed ratio. At this stage, a new equation that allows all three swept blade design parameters to be changed independently has been used to design swept blades, and the response surface method has been used to find out the optimum swept blade parameters. According to the results obtained, a significant increase of 4.28% in the power coefficient was achieved at the design tip speed ratio with the newly designed optimum swept wind turbine blade. Finally, baseline and optimum swept blades have been compared in terms of power coefficients at different tip speed ratios, force distributions, pressure distributions, and tip vortices.
Citation - WoS: 6
Citation - Scopus: 9
Ağaç-tohum Algoritmasının Cuda Destekli Grafik İşlem Birimi Üzerinde Paralel Uygulaması
(2018) Çınar, Ahmet Cevahir; Kıran, Mustafa Servet
Son yıllarda toplanan verinin artmasıyla birlikte verimli hesaplama yöntemlerinin de geliştirilmesi ihtiyacı artmaktadır. Çoğunlukla gerçek dünya problemlerinin zor olması sebebiyle optimal çözümü garanti etmese dahi makul zamanda yakın optimal çözümü garanti edebilen sürü zekâsı veya evrimsel hesaplama yöntemlerine olan ilgi de artmaktadır. Diğer bir açıdan seri hesaplama yöntemlerinde verinin veya işlemin paralelleştirilebileceği durumlarda paralel algoritmaların da geliştirilmesi ihtiyacı ortaya çıkmıştır. Bu çalışmada literatüre son yıllarda kazandırılmış olan popülasyon tabanlı ağaç-tohum algoritması ele alınmış ve CUDA platformu içerisinde paralel versiyonu geliştirilmiştir. Algoritmanın paralel versiyonunun performansı kıyas fonksiyonları üzerinde analiz edilmiş ve seri versiyonunun performansı ile karşılaştırılmıştır. Kıyas fonksiyonlarında problem boyutluluğu 10 olarak alınmış ve farklı popülasyon ve blok sayıları altında performans analizi yapılmıştır. Deneysel çalışmalar algoritmanın paralel versiyonunun algoritmanın seri sürümüne göre bazı problemler için 184,65 kata performans artışı sağladığı görülmüştür.
Aggloflotation of Bituminous Coal in a New Designed Cell
(Taylor & Francis Inc, 2025) Uslu, Nihat Yusuf; Duzyol, Selma
This study investigated the enrichment of high-ash bituminous coal by aggloflotation technique implemented within a new designed experimental cell. At the same time, this paper aimed to introduce the newly designed aggloflotation cell. This novel cell uniquely integrates the agglomeration and flotation processes into a single, unified unit, thereby simplifying the overall processing sequence. A coal sample, sourced from the Zonguldak & Ccedil;atala & gbreve;z & imath; coal preparation plant, was subjected to a series of tests under varied operational conditions including pH levels, agglomeration time, binder dosage, mixing speed, frother dosage, and dispersant. The performance of the aggloflotation process was evaluated by examining key metrics such as the concentrate's ash content, weight yield, and the combustible recovery. Notably, the experimental outcomes demonstrated that the new designed cell was efficient in processing ultra-fine bituminous coal in a single-stage operation. The process reduced the agglomeration time from 30 minute to just 5 minute, indicating substantial potential for both time and energy savings. Preliminary observations indicate that integrating both processes in one cell may also simplify process control. The outcomes suggest that this experimental setup represents a viable option for coal enrichment, inviting further investigation to determine its potential benefits.
Citation - WoS: 14
Citation - Scopus: 13
All-Dry Hydrophobic Functionalization of Paper Surfaces for Efficient Transfer of Cvd Graphene
(WILEY-V C H VERLAG GMBH, 2019) Çıtak, Emre; İstanbullu, Bilal; Şakalak, Hüseyin; Gürsoy, Mehmet; Karaman, Mustafa
In this study, the successful transfer of chemical vapor deposition (CVD)-grown graphene on an ordinary printing paper surface is demonstrated. Pristine paper is not a suitable substrate for graphene transfer because of its fragile and hydrophilic nature against the chemicals used during the transfer process. Two different fluoroalkyl polymers, namely poly(hexafluorobutyl acrylate) (PHFBA) and poly(perfluorodecyl acrylate) (PPFDA) are coated on paper surfaces by an initiated CVD (iCVD) technique to make the paper surfaces hydrophobic. Hydrophobicity is found to be an important factor in order for the graphene to be transferred onto the paper substrate. Although surfaces coated with PPFDA possess better hydrophobicity owing to their longer perfluoroalkyl group and higher roughness, the graphene transfer is found to be more successful on a PHFBA-coated surface. A thin film of PHFBA on the paper surface acts as a prime layer for effective and defect-free transfer of graphene and makes the paper surface ideal and robust during the graphene transfer process. The as-transferred graphene layer on the PHFBA-coated paper surface shows high conductivity values, even after repeated folding and flattening cycles.
Citation - WoS: 23
Citation - Scopus: 24
All-Dry Patterning Method To Fabricate Hydrophilic/Hydrophobic Surface for Fog Harvesting
(SPRINGER, 2020) Gürsoy, Mehmet
Inspired by natural creatures that live in the arid climate, fog harvesting can be an efficient approach to overcome freshwater scarcity. Fog harvesting ability of the creatures is mainly based on wettability differences of their surfaces. In this study, inspired by creatures that have hydrophilic regions surrounded by hydrophobic areas, a novel all-dry patterning method was applied to fabricate hydrophilic/hydrophobic patterned surfaces for fog harvesting. For this purpose, patterned surfaces were produced using plasma-enhanced chemical vapor deposition (PECVD) method with the help of a commercial magnet and iron powders. The idea behind the use of the magnetic field during PECVD deposition is to hold light iron particles on the substrate under the vacuum environment for masking substrate surface. For the first time, the magnetic field was used to fabricate patterned surfaces in vapor-phase polymerization. Ordinary glass slides were successfully transformed into hydrophilic/hydrophobic patterned glasses. The obtained results showed that the combination of hydrophobic and hydrophilic regions improved the fog harvesting performance.
Analysis of Factors Affecting Travel Costs in Beyşehir Lake National Park
(Tekirdag Namik Kemal University, 2022) Karakayacı, Zuhal; Karakayacı, Özer; Polat, Ahmet
Milli parklar sahip olduğu doğal, kültürel ve tarihi değerlerle rekreasyonel ve turizm amaçlı olarak değerlendirilmektedir. Türkiye’nin ikinci büyük milli parkı olan Beyşehir Gölü Milli Parkı da farklı zenginliklerle birçok insanın ziyaret ettiği yerlerden biridir. Milli parklar rekreasyon ve turizm amacıyla kullanıldığında, kullanıcılara bir maliyet getirmektedir. Seyahat, bir rekreasyonel faaliyet için tamamlayıcı bir nitelik taşımaktadır, çünkü bu faaliyetin gerçekleşebilmesi için söz konusu alana seyahat etmek gerekmektedir. Bu kapsamda, çalışmada Beyşehir Gölü Milli Parkı’nın seyahat maliyeti ve buna etki eden faktörleri incelenmiştir. Beyşehir Gölü Milli Parkı içinde bulunan çeşitli rekreasyon yerleri için ortalama seyahat maliyeti 252.97 TL, kişi başına düşen seyahat maliyeti 74.93 TL olarak hesaplanmıştır. Seyahat maliyetini etkileyen faktörleri incelemek için ziyaretçilerin seyahat maliyetleri yarı logaritmik regresyon modeliyle analiz edilmiştir. Bağımlı değişken seyahat süresince yapılan harcamaların toplamından oluşmakta, seyahat maliyetini etkileyen faktörler olarak, yaş, eğitim, medeni durum, gelir, geliş sıklığı, geliş amacı, geliş mesafesi gibi değişkenler alınmıştır. Analizlerde kullanılan; gelir, eğitim durumu, medeni durumun ‘’evli’’ olması, parka bir defadan fazla gelmiş olma, parka gelinen mesafe, parkı ziyaretin esas amaç olması ve parkta geçirilen zaman faktörleri ile seyahat maliyeti arasında pozitif bir ilişki bulunmaktadır. Yaş, parka geliş sıklığı ve parka şahsi araçla ulaşım sağlamış olma faktörleriyle seyahat maliyeti arasında ise negatif bir ilişki tespit edilmiştir. Seyahat maliyeti analizlerinde bu faktörlerin ele alınması rekreasyon amacıyla kullanılan alanların ekonomik anlamda değerlendirilmesinde yarar sağlayacaktır. Bir ülkenin önemli doğal kaynağı olan milli parkların ekonomik olarak ta değerlendirilerek milli gelire katkı sağlaması gerçekleştirilmelidir. Bu amaçla, milli parkları turizm faaliyetleri açısından sürdürülebilir hale getirecek çalışmalar doğayı koruyarak yapılmalıdır. Bu çalışmada tespit edilen seyahat maliyetini etkileyen faktörler de dikkate alınarak ilgili birimler tarafından programlar planlanmalıdır.
Citation - WoS: 1
Citation - Scopus: 1
Analysis of Fluid Forces Impacting on the Impeller of a Mixed Flow Blood Pump With Computational Fluid Dynamics
(Sage Publications Ltd, 2024) Diallo, Abdoulaye Billo; Cinar, Hasan; Yapici, Rafet
This study presents four different impeller designs to compare hydrodynamic forces. Numerical simulation studies are performed via computational fluid dynamics to specify and investigate the hydraulic forces impacting the impeller of the mixed-flow blood pump with a volute. The design point of this pump is that the flow rate is 5 L/min, the rotational speed is 8000 rpm, and the manometric head is 100 mmHg. The designed impellers are placed in the same volute and simulation studies are performed with the same mesh size (17.3 million cells) of the pumps. The simulation studies have been conducted in setting 1050 kg/m3 blood density, 35 cP fluid viscosity, and SST-k omega turbulence model. Additionally, this study examines the changes in hydraulic forces and hydraulic efficiency with fluid viscosity. As a result of experimental simulation studies, the highest hydraulic efficiencies of 40.87% and 39.5% are achieved in the case of the shaftless-grooveless and shafted-grooveless impeller, respectively. The maximum axial forces are obtained from the pump with the shaftless-grooveless impeller. Whereas radial forces, maximum values are calculated in the pump with the shaftless-outer groove impeller for all flow rates. Finally, the wall shear stresses, which are important for blood pump designs, are evaluated and the maximum value of 227 Pa is observed in the pump impeller with a shaftless-grooved.
Citation - WoS: 4
Citation - Scopus: 4
Analysis of Ionospheric Vtec Retrieved From Multi-Instrument Observations
(MDPI, 2024) Öztan, Gürkan; Duman, Huseyin; Alçay, Salih; Öğütçu, Sermet; Özdemir, Behlül Numan
This study examines the Vertical Total Electron Content (VTEC) estimation performance of multi-instruments on a global scale during different ionospheric conditions. For this purpose, GNSS-based VTEC data from Global Ionosphere Maps (GIMs), COSMIC (F7/C2)-Feng-Yun 3C (FY3C) radio occultation (RO) VTEC, SWARM-VTEC, and JASON-VTEC were utilized. VTEC assessments were conducted on three distinct days: geomagnetic active (17 March 2015), solar active (22 December 2021), and quiet (11 December 2021). The VTEC values of COSMIC/FY3C RO, SWARM, and JASON were compared with data retrieved from GIMs. According to the results, COSMIC RO-VTEC is more consistent with GIM-VTEC on a quiet day (the mean of the differences is 4.38 TECU), while the mean of FY3C RO-GIM differences is 7.33 TECU on a geomagnetic active day. The range of VTEC differences between JASON and GIM is relatively smaller on a quiet day, and the mean of differences on active/quiet days is less than 6 TECU. Besides the daily comparison, long-term results (1 January-31 December 2015) were also analyzed by considering active and quiet periods. Results show that Root Mean Square Error (RMSE) values of COSMIC RO, FY3C RO, SWARM, and JASON are 5.02 TECU, 6.81 TECU, 16.25 TECU, and 5.53 TECU for the quiet period, and 5.21 TECU, 7.07 TECU, 17.48 TECU, and 5.90 TECU for the active period, respectively. The accuracy of each data source was affected by solar/geomagnetic activities. The deviation of SWARM-VTEC is relatively greater. The main reason for the significant differences in SWARM-GIM results is the atmospheric measurement range of SWARM satellites (460 km-20,200 km (SWARM A, C) and 520 km-20,200 km (SWARM B), which do not contain a significant part of the ionosphere in terms of VTEC estimation.
Citation - WoS: 26
Citation - Scopus: 26
Analysis of Land Use/Land Cover Changes and Prediction of Future Changes With Land Change Modeler: Case of Belek, Turkey
(Springer, 2023) Akdeniz, Halil Burak; Serdaroğlu Sağ, Neslihan; İnam, Şaban
In the areas declared to be a tourism center by state planning, a rapid tourism-related development occurs depending on the investments in tourism, which causes a dramatic land use/land cover (LULC) change. Determining, monitoring, and modeling of LULC changes are required in order to ensure the conservation-use balance and sustainability within such vulnerable areas that are under development pressure. This study consists of four steps. In the first step, the Landsat images dated 1985, 2000, 2010, and 2021 were classified using the maximum likelihood method and the LULC of Belek Tourism Center located in Turkey were determined. The second step included the identification of areal and spatial changes between the LULC classes for the four periods. In the third step, the LULC changes in Belek Tourism Center for 2040 were modeled using the land change modeler. Last step evaluated the relationship between the modeled spatial development pattern and the current planning decisions. According to the results obtained during 36 years, the rates of built-up, forest, and water body areas have increased by 11.91%, 13.67%, and 0.82%, respectively, whereas the rates of barren land and agricultural areas have reduced by 22.25% and 4.15%, respectively. The LULC map modeled for 2040 predicts the built-up areas to expand by 8.25% and the agricultural areas to shrink by 5.42% by comparison with 2021. This study will contribute as a key measure for planners, policy-, and decision-makers to make decisions related to sustainable land use in the areas declared to be a tourism center.
Citation - WoS: 1
Citation - Scopus: 1
Analysis of Short-Term Sentinel-1 Data Using the Dinsar Method for Monitoring Displacement Following the Earthquakes of 6 and 20 February in Hatay City
(Ist Nazionale Di Oceanografia E Di Geofisica, 2024) Doganalp, S.; Cokuner, B.; Makineci, H. B.
The Eastern Anatolia Fault Zone (EAFZ) has caused destructive earthquakes. Kahramanmara and Hatay, located on the EAFZ, were hit by devastating earthquakes with magnitudes of 7.7, 7.6, and 6.3, respectively, in February 2023. A tectonic chain of disasters was seen in Hatay in a short time, first on 6 February 2023, with earthquakes centred in Kahramanmara and the subsequent intense earthquake series, and lastly on 20 February 2023, with the Hatay earthquake centred in the Yayladag district. The lithological characteristics of the units in the region increased the destructive effects of the earthquakes. In addition, the location of the study area, where the EAFZ and the Death Sea Fault Zone are close to each other, increases the importance of research. This study aims to monitor the ground displacements caused by the earthquakes in Hatay. Sentinel1A Synthetic Aperture Radar data was acquired on 29 January, and 10 and 22 February, and the Differential Interferometry Synthetic Aperture Radar method was applied. In addition, the elevation change was determined by using two-month global navigation satellite system data from the Continuously Operating Reference Station points (HAT2 and ONIY) in the study area. Thus, considering regional tectonics, ground movements resulting from the earthquakes on 6 and 20 February were identified and examined using geologic, geodesic, and remote sensing techniques.
Citation - WoS: 7
Citation - Scopus: 8
An Analysis of the Effect of Pressure Angle Change on Bending Fatigue Performance in Asymmetrical Spur Gears
(SAGE PUBLICATIONS LTD, 2021) Demet, Seyit Mehmet; Ersoyoğlu, Ali Serhat
In this study, the fatigue performances of symmetrical and asymmetrical spur gears were analyzed by performing single tooth bending fatigue tests. The gears tested were determined to be symmetrical spur gears with a 20 degrees/20 degrees pressure angle, asymmetrical spur gears with a 20 degrees/22 degrees pressure angle, and asymmetrical spur gears with a 20 degrees/25 degrees pressure angle. These gears were made of AISI 4140 material. Single tooth bending fatigue tests were performed under variable loads. Considering the tests performed at the same torque values in asymmetrical spur gears with a 20 degrees/22 degrees pressure angle compared to symmetrical spur gears with a 20 degrees/20 degrees pressure angle, a statistically significant increase in performance was achieved at close to 90%. While gears with 20 degrees/20 degrees and 20 degrees/22 degrees pressure angles break at the tooth root, tooth flank fracture was observed in relatively high numbers of cycles in asymmetric spur gears with a 20 degrees/25 degrees pressure angle. It was observed that the formation of tooth flank damage negatively affected the fatigue performance.
Citation - WoS: 8
Citation - Scopus: 10
Analysis of the Electric Vehicle Charging Stations Effects on the Electricity Network With Artificial Neural Network
(MDPI, 2023) Olcay, Kadir; Çetinkaya, Nurettin
In this study, the effects of electric vehicles, whose usage rate is increasing day by day in the world, on the existing electricity grid have been studied. EV charging stations and similar non-linear loads cause various harmful effects on power systems such as phase imbalances, the effect of harmonic formation, energy quality, voltage, and current imbalance. The study focuses on the harmonic effects of EV charging stations at the point where they are connected to the grid and at lower voltage levels by using IEEE 6-, 14-bus, and 30-bus test power systems. In addition to the existing loads in these grid systems, the effects on the grid as a result of drawing electrical energy from the grid for charging electric vehicles are investigated. These effects have shown how these charging stations on the grid have changed, considering the fact that the number of electric vehicles and the number of charging stations increased over the years when a single electric vehicle provided energy from the grid, and the grid was not renewed. The response of the network to the increase in the load that will occur in addition to the current loads, its harmonic effects, and the effects of the current grid on the increase in the electric vehicle growth rate over the years have been predicted and examined by using artificial neural networks. Solution suggestions are presented for power networks in similar situations.
Citation - WoS: 2
Citation - Scopus: 2
Analysis of the Memory Mechanism in the Pan Evaporation Phenomenon by the Band Similarity Method
(Springer Wien, 2023) Yılmaz, Volkan
In this study, band similarity (BS) method as a new approach, which allows investigation of the memory features of the evaporation phenomenon, was applied on 7 different meteorological data in addition to the monthly pan evaporation data of Beysehir district of Konya city, located in the middle regions of Turkey. The models required for BS were generated with the artificial bee colony (ABC) optimization algorithm. As a result of the study, it has been observed that ABC optimization algorithm produced sufficient evaporation models. Subsequently, it was concluded that the BS method significantly improved the ABC results by using the temporal similarity mechanism. In this direction, it has been observed that the evaporation phenomenon studied remembers its own past. As a result of the BS method, it can be mentioned that there is a seasonal effect in the memory properties. While the memory weakens in the months when evaporation is high and low, it gets stronger especially in the spring and autumn months. Therefore, it has been concluded that the changes of the parameters affecting evaporation have a more intense effect on memory compared to their intensities. It is thought that this study differs from other studies in the literature because the pan evaporation phenomenon was evaluated from a different perspective and the BS method, which is a new method, and was applied for the first time on a hydrological parameter.
Citation - WoS: 7
Citation - Scopus: 7
An Analytical Study About the Use of Steel Plate Shear Walls To Improve Lateral Rigidity of Reinforced Concrete Framed Structures
(LATIN AMER J SOLIDS STRUCTURES, 2020) Korkmaz, Serra Zerrin
Steel plate shear walls are becoming popular for steel structures. In this study, the use of Steel Plate Shear Walls (SPSW) was discussed to increase the horizontal stiffness of reinforced concrete structures. It was aimed to fix the SPSW elements to the exterior of the building. ABAQUS models of SPSW applied 2D frame samples, which were tested in a previous experimental study, were created. Experimental and analytical horizontal load-top displacement curves were found to be in good agreement. In the study, ABAQUS models of a 6-story and 3D reinforced concrete building were also created. In models, SPSW elements were placed at the exterior of the building. The load capacities of the reinforced and non-reinforced building models were compared. The steel sheet thickness and the number of frame openings at which the SPSW element was placed were considered as the variable parameters.
Citation - WoS: 7
Citation - Scopus: 12
Analyzing the Effect of Data Preprocessing Techniques Using Machine Learning Algorithms on the Diagnosis of Covid-19
(Wiley, 2022) Erol, Gizemnur; Uzbaş, Betül; Yücelbaş, Cüneyt; Yücelbaş, Sule
Real-time polymerase chain reaction (RT-PCR) known as the swab test is a diagnostic test that can diagnose COVID-19 disease through respiratory samples in the laboratory. Due to the rapid spread of the coronavirus around the world, the RT-PCR test has become insufficient to get fast results. For this reason, the need for diagnostic methods to fill this gap has arisen and machine learning studies have started in this area. On the other hand, studying medical data is a challenging area because the data it contains is inconsistent, incomplete, difficult to scale, and very large. Additionally, some poor clinical decisions, irrelevant parameters, and limited medical data adversely affect the accuracy of studies performed. Therefore, considering the availability of datasets containing COVID-19 blood parameters, which are less in number than other medical datasets today, it is aimed to improve these existing datasets. In this direction, to obtain more consistent results in COVID-19 machine learning studies, the effect of data preprocessing techniques on the classification of COVID-19 data was investigated in this study. In this study primarily, encoding categorical feature and feature scaling processes were applied to the dataset with 15 features that contain blood data of 279 patients, including gender and age information. Then, the missingness of the dataset was eliminated by using both K-nearest neighbor algorithm (KNN) and chain equations multiple value assignment (MICE) methods. Data balancing has been done with synthetic minority oversampling technique (SMOTE), which is a data balancing method. The effect of data preprocessing techniques on ensemble learning algorithms bagging, AdaBoost, random forest and on popular classifier algorithms KNN classifier, support vector machine, logistic regression, artificial neural network, and decision tree classifiers have been analyzed. The highest accuracies obtained with the bagging classifier were 83.42% and 83.74% with KNN and MICE imputations by applying SMOTE, respectively. On the other hand, the highest accuracy ratio reached with the same classifier without SMOTE was 83.91% for the KNN imputation. In conclusion, certain data preprocessing techniques are examined comparatively and the effect of these data preprocessing techniques on success is presented and the importance of the right combination of data preprocessing to achieve success has been demonstrated by experimental studies.
Citation - WoS: 2
Citation - Scopus: 2
Anatomy of Flash Sintering in Yttria-Stabilized Zirconia Solid-State Electrolyte: High Temporal Resolution Energy-Dispersive X-Ray Diffraction Using a 200 Kev Synchrotron Probe
(Springer Heidelberg, 2023) Savkliyildiz, Ilyas; Degnah, Ahmed; Biçer, Hülya; Salur, Emin; Tsakalakos, Thomas; Akdoğan, Enver Koray
High-energy synchrotron X-ray diffraction enables ultra-rapid data collection to determine unit cell volume evolution of 8YSZ under thermal and electric field (30 V/mm). Such an approach provides unprecedented insight into the anatomy of 8YSZ's flash sintering in the 797-810 & DEG;C interval. The densification due to flash sintering occurs in 40 s during which X-ray spectra were collected every 2 s. The densification of 8YSZ was accompanied by 0.55% anelastic peak shift on (220) reflection. Concomitantly, the applied thermal and electric field led to anelastic expansion of the cubic lattice parameter (+ 0.55%) and unit cell volume (+ 1.57%). Besides, an irreversible increase in the peak intensity (+ 22.6%), a decrease in peak width (- 18.3%), and integrated peak (- 13.6%) are determined. The observed anomalies are attributed to the response of oxygen vacancy generation and redistribution to the combined electric and thermal fields.
Citation - WoS: 8
Citation - Scopus: 7
Ann Estimation Model for Photogrammetry-Based Uav Flight Planning Optimisation
(TAYLOR & FRANCIS LTD, 2022) Makineci, Hasan Bilgehan; Karabörk, H.; Durdu, A.
Artificial intelligence (AI) is undergoing a ground-breaking period. Recently, AI affects almost every part of human life. Using AI in path planning for Unmanned Aerial Vehicle (UAV) attracts attention as a novel need. The inputs that form the base of UAV use in photogrammetry are UAV Type (UT), Ground Sampling Distance (GSD), Overlap Rates (OR), and Atmospheric Conditions (AC). Input parameters directly impact the UAV's Flight Time (FT) and Battery Status (BS). Weighting and optimizing these parameters are the main ideas of this study. The effects of input values (GSD, OR, UT, AC) on the outputs (BS and FT) were optimized using Artificial Neural Networks (ANN) in this study. For the analysis, results have been produced in which different training algorithms are preferred (Gradient Descent - GD - and Levenberg-Marquardt - LM). The GD algorithm has reached 77.65% accuracy in FT estimation and 80.91% estimation accuracy on normalized data on the BS. Then, the correlation between the produced model and the input parameters and the output parameters was determined, and the weights of the inputs were revealed. As a result, it was determined that the AC parameter has the most significant effect on BS and FT. Also, it has been identified that the normalization process has a considerable impact on optimization.

Browse

Browsing Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections by WoS Q "Q3"