TR-Dizin İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://acikerisim2.beykoz.edu.tr/handle/20.500.12879/4

Browse

Now showing 1 - 4 of 4

Detection of Damaged Structures from Satellite Imagery Processed by Autoencoder with Boruta Feature Selection Method
(AVES, 2023) Muzoglu, Nedim; Adiguzel, Ertugrul; Akbacak, Enver; Karaslan, Melike Kaya
Many worldwide changing events, including meteorology, weather forecasting, disaster response, and environmental monitoring, are tracked by states or companies via satellite imagery. Early response to disasters is critical for human life. In these cases, artificial intelligence applications are also used to make rapid determinations about large geographical region. In this study, satellite images of flooded and undamaged structures in Hurricane Harvey were used. An autoencoder process has been applied to this dataset to reduce the noise in satellite imagery. AlexNet and VGG16 deep learning (DL) models are used to extract features from both datasets. The most effective features selected by the Boruta feature selection algorithm were classified with the support vector machine, and the highest classification accuracy of 99.35% was obtained. Since disasters involve the evaluation of very big datasets from large geographic areas, presenting the data with the smallest possible feature will facilitate the process. For this reason, by applying dimensionality reduction to the selected attributes, a 98.29% success was achieved in the classification with only 90 attributes. The proposed approach shows that DL and feature engineering are very effective methods to quickly respond to disaster areas using satellite imagery.
Fault Detection in Pipelines with Graph Convolutional Networks (GCN) Method
(Gazi Üniversitesi, 2024) Şahin, E.; Yüce, H.
Pipeline networks have a wide range of applications, from the transportation of energy sources such as oil and natural gas to the conveyance and distribution of water resources. However, leaks and ruptures in pipelines can cause significant harm to the environment. Therefore, it is crucial to accurately detect pipeline faults in order to avoid economic losses and protect the environment. In this study, pipeline networks carrying water fluid are represented using graph structures. The graph convolutional network (GCN) algorithm is employed for the detection of leaks and blockages in pipeline networks. Experimental methods are employed to collect the necessary data (pressure data) for the GCN algorithm, creating two datasets by considering five different scenarios. The fault detection performance of the GCN algorithm is compared with other graph machine learning algorithms, namely, RGCN, HinSAGE, and GraphSAGE. The results of this study indicate that the performance of the GCN model surpasses that of the other algorithms. Reviewing the literature, accuracy rates for fault diagnosis in pipeline networks using machine learning algorithms range from 78.51% to 99%. In this study, it is found that the GCN, GraphSAGE, HinSAGE, and RGCN algorithms achieve fault detection accuracies of 91%, 90%, 87%, and 89%, respectively, in pipeline networks. Classical machine learning SVM model was used to compare the performance of graph-based algorithms. It is seen that the performances of the algorithms face the literature and the results are above the literature average. © 2024 Gazi Universitesi. All rights reserved.
Lumbar Spine Implant Design with Finite Element Method and Determination of Biomechanical Effects
(Gazi Univ, Fac Engineering Architecture, 2023) Taherzadeh, Paniz; Kelleci, Kubra; Ozer, Sevil
Graphical/Tabular The restoration percentages of two different implants designed and simulated in six different directions are given in Figure A. Figure A. Restoration percentages of theimplant 1 and implant 2 devices in six different directionsPurpose: In this study, it was aimed to design a new pedicle-screw based posterior dynamic stabilization implant that can help stabilize the spine normally. In the study, two different implants were designed using the finite element method (FEM) and their biomechanical effects were compared.Theory and Methods: Stable and treated models of the lumbar spine with two different implants were simulated under physiological loading conditions according to Computed tomography data. Implant and device components were created with the SOLIDWORKS program. All designed devices were used together with ABAQUS CAD simulation program and MATLAB program to calculate range of motion, adjacent level effect and restoration percentages in six different directions (right-left axial rotation, right-left lateral bending and flexion-extension). In the study, 70% restoration percentage, which is an acceptable value in the movement of the spine with the implant, was tried to be achieved in all directions.Results: With the second device, which obtained optimum data and was found to be more flexible, a higher percentage of restoration was obtained in the Z and Y axes. Restoration values are 33% for extension, 53% for flexion, and 68% and 55% for lateral bending and axial rotations, respectively.Conclusion: It can be said that pedicle-screw implants designed with this simulation study will be applicable after experimental validation and clinical trials
De Novo Malignancy Development Following Kidney Transplantation: Managing Risks and Outcomes in Clinical Practice
(Galenos Publ House, 2025) Huseynov, Amil; Cicek, Sevim Nuran Kuslu
Objective: Denovo malignancy is a significant complication following kidney transplantation, attributed to prolonged immunosuppression.This study evaluates the incidence, risk factors, and clinical outcomes of denovo malignancies in kidney transplant recipients. Material and Methods: A retrospective cohort analysis was conducted on 1200 kidney transplant recipients between 2016 and 2023. Patients were categorized based on the presence or absence of de novo malignancies. Statistical analyses were performed to identify risk factors, including age, sex, comorbidities, and immunosuppressive regimens. Patient and graft survival were assessed using Kaplan-Meier analysis and the log-rank test. Results: Among the study population, 43 patients (3.6%) developed de novo malignancies. The most frequent malignancy types were non-melanoma skin cancers (27.9%) and post-transplant lymphoproliferative disorders (18.6%). Patients with malignancies exhibited a lower three-year survival rate (83.7%) compared to those without malignancies (91.4%), though the difference was not statistically significant (p=0.067). Graft survival at three years was slightly lower in the malignancy group (84.0% vs. 88.7%, p=0.146). Older recipient age was identified as a significant risk factor (hazard ratio=1.03 per year, p=0.025). Conclusion: De novo malignancy remains a concern in kidney transplant recipients, particularly among older patients. Regular screening protocols, lifestyle interventions, and individualized immunosuppressive regimens are essential to mitigate risk and improve outcomes.

Browse

Browsing TR-Dizin İndeksli Yayınlar Koleksiyonu by Scopus Q "Q3"