WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
22 results
Search Results
Article Vision Transformers-Based Deep Feature Generation Framework for Hydatid Cyst Classification in Computed Tomography Images(Springer, 2025) Sagik, Metin; Gumus, AbdurrahmanHydatid cysts, caused by Echinococcus granulosus, form progressively enlarging fluid-filled cysts in organs like the liver and lungs, posing significant public health risks through severe complications or death. This study presents a novel deep feature generation framework utilizing vision transformer models (ViT-DFG) to enhance the classification accuracy of hydatid cyst types. The proposed framework consists of four phases: image preprocessing, feature extraction using vision transformer models, feature selection through iterative neighborhood component analysis, and classification, where the performance of the ViT-DFG model was evaluated and compared across different classifiers such as k-nearest neighbor and multi-layer perceptron (MLP). Both methods were evaluated independently to assess classification performance from different approaches. The dataset, comprising five cyst types, was analyzed for both five-class and three-class classification by grouping the cyst types into active, transition, and inactive categories. Experimental results showed that the proposed VIT-DFG method achieves higher accuracy than existing methods. Specifically, the ViT-DFG framework attained an overall classification accuracy of 98.10% for the three-class and 95.12% for the five-class classifications using 5-fold cross-validation. Statistical analysis through one-way analysis of variance (ANOVA), conducted to evaluate significant differences between models, confirmed significant differences between the proposed framework and individual vision transformer models (p<0.05\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p < 0.05$$\end{document}). These results highlight the effectiveness of combining multiple vision transformer architectures with advanced feature selection techniques in improving classification performance. The findings underscore the ViT-DFG framework's potential to advance medical image analysis, particularly in hydatid cyst classification, while offering clinical promise through automated diagnostics and improved decision-making.Article Citation - WoS: 9Citation - Scopus: 8A Numerical Method Based on Legendre Wavelet and Quasilinearization Technique for Fractional Lane-Emden Type Equations(Springer, 2024) İdiz, F.; Tanoǧlu, G.; Aghazadeh, N.In this research, we study the numerical solution of fractional Lane-Emden type equations, which emerge mainly in astrophysics applications. We propose a numerical approach making use of Legendre wavelets and the quasilinearization technique. The nonlinear term in fractional Lane-Emden type equations is iteratively linearized using the quasilinearization technique. The linearized equations are then solved using the Legendre wavelet collocation method. The proposed method is quite effective to overcome the singularity in fractional Lane-Emden type equations. Convergence and error analysis of the proposed method are given. We solve some test problems to compare the effectiveness of the proposed method with some other numerical methods in the literature. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Article Citation - WoS: 2Citation - Scopus: 3Design and Manufacturing of a Hip Joint Motion Simulator With a Novel Modular Design Approach(Springer, 2024) Torabnia, S.; Mihçin, D.Ş.; Lazoglu, I.The study is aimed to develop a hip joint wear simulator using a modular design approach to help experimentally monitor and control critical wear parameters to validate in-silico wear models. The proper control and application of wear parameters such as the range of motion, and the applied force values while estimating the lost material due to wear are essential for thorough analysis of wear phenomena for artificial joints. The simulator's dynamics were first modeled, then dynamic loading data was used to calculate the forces, which were further used for topology optimization to reduce the forces acting on each joint. The reduction of the link weights, connected to the actuators, intends to improve the quality of motion transferred to the femoral head. The modular design approach enables topology-optimized geometry, associated gravitational and dynamic forces, resulting in a cost-effective, energy-efficient product. Moreover, this design allows integration of the subject specific data by allowing different boundary conditions following the requirements of industry 5.0. Overall, the in-vitro motion stimulations of the hip-joint prosthesis and the modular design approach used in the study might help improve the accuracy and the effectiveness of wear simulations, which could lead into the development of better and longer-lasting joint prostheses for all. The subject-specific and society-based daily life data implemented as boundary conditions enable inclusion of the personalized effects. Next, with the results of the simulator, CEN Workshop Agreement (CWA) application is intended to cover the personalized effects for previously excluded populations, providing solution to inclusive design for all. © 2023, The Author(s), under exclusive licence to Springer-Verlag France SAS, part of Springer Nature.Article Citation - WoS: 9Citation - Scopus: 11Experimental Investigation of Spray Characteristics of Ethyl Esters in a Constant Volume Chamber(Springer, 2024) Ulu, A.; Yildiz, G.; Özkol, Ü.; Rodriguez, A.D.Abstract: Biodiesels are mainly produced via the utilization of methanol in transesterification, which is the widespread biodiesel production process. The majority of this methanol is currently obtained from fossil resources, i.e. coal and natural gas. However, in contrast with methanol, biomass-based ethanol can also be used to produce biodiesels; this could allow the production line to become fully renewable. This study aimed to investigate the spray characteristics of various ethyl ester type biodiesels derived from sunflower and corn oils in comparison to methyl esters based on the same feedstocks and reference petroleum-based diesel. Spray penetration length (SPL) and spray cone angle (SCA) were experimentally evaluated in a constant volume chamber allowing optical access, under chamber pressures of 0, 5, 10 and 15 bar and injection pressures of 600 and 800 bar. Sauter mean diameter (SMD) values were estimated by using an analytical correlation. Consequently, ethyl esters performed longer SPL (2.8–20%) and narrower SCA (5.1–19%) than diesel under ambient pressures of 5 and 10 bar. Although the SMD values of ethyl esters were 48% higher than diesel on average, their macroscopic spray characteristics were very similar to those of diesel under 15 bar chamber pressure. Moreover, ethyl esters were found to be very similar to methyl esters in terms of spray characteristics. The differences in SPL, SCA and SMD values for both types of biodiesels were lower than 4%. When considering the uncertainty (± 0.84%) and repeatability (±5%) ratios, the difference between the spray characteristics of methyl and ethyl esters was not major. Graphical abstract: [Figure not available: see fulltext.] © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Article Citation - WoS: 1Citation - Scopus: 1Real-Time Superficial Vein Imaging System for Observing Abnormalities on Vascular Structures(Springer, 2024) Altay, A.; Gumus, A.Circulatory system abnormalities might be an indicator of diseases or tissue damage. Early detection of vascular abnormalities might have an important role during treatment and also raise the patient’s awareness. Current detection methods for vascular imaging are high-cost, invasive, and mostly radiation-based. In this study, a low-cost and portable microcomputer-based tool has been developed as a Near-Infrared (NIR) superficial vascular imaging device. The device uses NIR Light-Emitting Diode (LED) light at 850 nm along with other electronic and optical components. It operates as a non-contact and safe infrared (IR) imaging method in real-time. Image and video analysis are carried out using OpenCV (Open-Source Computer Vision), a library of programming functions mainly used in computer vision. Various tests were carried out to optimize the imaging system and set up a suitable external environment. To test the performance of the device, the images taken from three diabetic volunteers, who are expected to have abnormalities in the vascular structure due to the possibility of deformation caused by high glucose levels in the blood, were compared with the images taken from two non-diabetic volunteers. As a result, tortuosity was observed successfully in the superficial vascular structures, where the results need to be interpreted by the medical experts in the field to understand the underlying reasons. Although this study is an engineering study and does not have an intention to diagnose any diseases, the developed system here might assist healthcare personnel in early diagnosis and treatment follow-up for vascular structures and may enable further opportunities. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.Article Citation - WoS: 61Citation - Scopus: 60Performance of Structures in İzmir After the Samos Island Earthquake(Springer, 2022) Yakut, A.; Sucuoǧlu, H.; Binici, B.; Canbay, E.; Dönmez, C.; Ilki, A.; Ay, B.Ö.The October 30, 2020 Earthquake caused unexpectedly significant damage in İzmir considering its distance to the city. This paper evaluates the recorded ground motions, summarizes the performance of structures affected from the earthquake with emphasis on the reasons of damage. A detailed damage assessment was carried out by the Earthquake Engineering Research Center of Middle East Technical University to compile data on the damage of RC and masonry buildings. It was observed that majority of the damage was concentrated in the Bayraklı district due to its peculiar soil properties where many 7–10 story mid-rise RC buildings suffered heavy damage and collapse. The level of amplified ground motions combined with deficiencies of apparently non-code compliant buildings exacerbated the damage. The main reasons of damage were mainly attributed to the presence of soft stories, lack of proper detailing, poor construction quality, presence of heavy overhangs, and hence significant lack of code-compliance in essence. The influence of infill walls on seismic performance of deficient and inadequate buildings was clearly seen in this earthquake. This paper also discusses seismic code requirements in effect and their influence on the observed building performance. The recorded ground motions were compared with the code spectra to evaluate the performance of the buildings. The code response spectra were found to be well above the recorded ground motion spectra at the sites where significant damage was observed. © 2021, The Author(s), under exclusive licence to Springer Nature B.V.Correction Erratum: Measurement of Prompt and Nonprompt Charmonium Suppression in PbPb Collisions at 5.02 TeV (The European Physical Journal C, (2018), 78, 6, (509), 10.1140/Epjc(Springer, 2023) Sirunyan, A.M.; Tumasyan, A.; Adam, W.; Ambrogi, F.; Aşilar, E.; Bergauer, T.; Woods, N.In Fig. 3, the y axis titles were mistakenly written showing a single-differential cross section in either dimuon (Formula presented.) or rapidity, when in fact the cross section is normalized by both the (Formula presented.) and rapidity ranges used for a given measurement point. The corrected version is shown in the new Fig. 3 provided below. (Figure presented.) Differential cross section of prompt (Formula presented.) mesons (left) and (Formula presented.) mesons from b hadrons (nonprompt (Formula presented.) ) (right) decaying into two muons as a function of dimuon (Formula presented.) (upper) and rapidity (lower) in pp and (Formula presented.) collisions. The (Formula presented.) cross sections are normalised by (Formula presented.) for direct comparison. The bars (boxes) represent statistical (systematic) point-by-point uncertainties, while global uncertainties are written on the plots. © 2023, CERN for the benefit of the CMS Collaboration.Article Assessment of Undergraduate Health Students' Perception and Satisfaction on Training and Participation in Community Health Outreach(Springer, 2023) Adegbore, Abidemi Kafayat; Adedokun, Amudatu Ambali; Adegoke, Juliet Ifeoluwa; Lawal, Maruf Ayobami; Oke, MuseAimThe need to improve training of health professionals has increased in recent years due to increasing frequencies of public health events. Consequently, a descriptive cross-sectional survey was carried out to determine the level of satisfaction and knowledge acquired by undergraduate students in the health sciences during a community health outreach program.Subject and methodsStudents were invited to complete an online-administered questionnaire (consisting of both open- and closed-ended questions) to assess their perceptions and experiences on the community health outreach program. Additionally, the survey was carried out to assess the quality of training provided and obtain suggestions for further improvements. Responses were collected and analysed using Microsoft Excel.ResultsMost respondents (>83%) reported satisfaction with the community diagnosis and community intervention briefing and training sessions. All respondents reported familiarity with standard community health outreach instruments and were capable of identifying environmental health risk factors that may contribute to the spread of communicable diseases. Interestingly, respondents reported greater appreciation of health challenges faced by rural communities. However, respondents expressed dissatisfaction with the duration of the outreach program (24%) and funding (15%).ConclusionAlthough respondents reported overall satisfaction with the organization and execution of the health outreach program, certain aspects of the program were deemed unsatisfactory. Despite the shortcomings, we believe that our student-centred learning strategy is readily adaptable for training future healthcare professionals and improving health literacy of rural communities, particularly in sub-Saharan Africa.Conference Object Citation - WoS: 2Evaluation of Streamflow Drought Index in Aegean Region, Turkey(Springer, 2022) Vaheddoost, Babak; Safari, Mir Jafar Sadegh; Gülmez, Ayşe; Mersin, DenizhanWater is an invaluable substance of which ensures the life cycle and hydrological events across the world. In this respect, water deficit also known as drought is a natural disaster related to water scarcity in time and space. Although there is no solid definition for the phenomenon, the outcome of repeated wet and dry spells cause in economic, social, and political problems at regional, country-wide, and world-wide scale. In this study, drought associated with the streamflow in the Aegean region, which has an important economic, historical and wsocio-cultural role in the western Turkey, is investigated through the well-known streamflow drought index (SDI). Therefore, average discharge in the Cicekli-Nif, Besdegirmenler-Dandalas, Bebekler-Rahmanlar and Kocarli-Koprubasi station respectively related to on Gediz, Buyuk Menderes and Kucuk Menderes basins were used. Then SDI with 1, 3, 6,12 months moving average are acquired to express the drought severity associated with the streamflow in the basins. Results showed that the SDI values in all of stations together with the 1, 3, 6, and 12-month moving averages depicts similar results and no abnormal situation exist during the study period.Book Part Citation - WoS: 5Citation - Scopus: 10An Acceptance Model for the Adoption of Smart Glasses Technology by Healthcare Professionals(Springer, 2020) Ozdemir-Gungor, Dilek; Goken, Muge; Basoglu, Nuri; Shaygan, Amir; Dabic, Marina; Daim, Tugrul U.
- «
- 1 (current)
- 2
- 3
- »