Van Yüzüncü Yıl University Research Information System
Not a member yet
65114 research outputs found
Sort by
Evaluation of the Post-discharge Recovery Process in Elderly Patients Undergoing Surgical Intervention for Hip Fracture
No full textA novel integration of multiple learning methods for detecting misleading information from different datasets during the pandemic
No full textCoronavirus Disease 2019 (COVID-19) was an intensely and commonly discussed topic on social media platforms during the pandemic due to uncertainty about the virus, especially as new variants of the virus emerged around the world. Unfortunately, during the pandemic, people shared many posts about COVID-19 on their social media accounts without paying attention or checking whether they were true or not. In this way, intentionally or unintentionally, they highly manipulated public opinion through their posts. The majority of these posts contained misleading information that negatively affected readers' cognitive and mental health, leading to a new neologism associated with the pandemic: “infodemic.” Therefore, the present study focuses on the classification of Fake News disseminated during the pandemic to mislead people. To this end, five different datasets were first trained independently using natural language processing and machine learning methods, and the results obtained were compared. Later, these datasets were combined according to the different scenarios to improve the model performance. According to the results, the highest accuracy value of 98.1% was obtained with the model Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA) when the datasets were trained independently. Similarly, the highest training accuracy of 94.12% was obtained with the ELECTRA method and the highest test accuracy of 91.71% was obtained with the Random Forest method. In summary, the model ELECTRA, which is less preferred than other pre-trained models, achieved the highest performance scores in all study-specific scenarios
Turkey-Iran Border and Irregular Migration from a Geographical Perspective
No full textThe Turkey-Iran border, which is approximately 560 kilometers long and Turkey's second longest border after the Syrian border, has been at the forefront of irregular migration for many years. A mass of migrants, enters Turkey from here every year. This border is regarded as the most significant used by irregular migrants, mainly from Afghanistan, Pakistan and Iran to enter Turkey and then reach Europe through migrant smugglers. Considering the characteristics of the border, the topographical structure, climate conditions, historical ties between the populations living on both sides of the border, socio-cultural interactions, and economic conditions are important dynamics that ensure the continuity of irregular migration. In this study, the political formation process, the role of geographical factors, and the socio-cultural structure of the border will be discussed. Then, the impact of the geographical structure of the border line on irregular migration will be examined. In addition, the profiles of migrants entering Turkey, the magnitude of the migration, and the actors of irregular migration, particularly smugglers, will be thoroughly investigated.</p
Machine learning application with Bayesian regularization for predicting pressure drop in R134a's annular evaporation and condensation
No full textMAKINE ÖĞRENMESI ILE TURIST PROFILLEME VE MEMNUNIYET TAHMINI: VERI ODAKLI BIR YAKLAŞIM
No full textBu araştırma,turistlerin seyahat tercihlerini anlamak ve kişiselleştirilmiş deneyimlersunmak amacıyla makine öğrenmesi tekniklerini kullanarak kapsamlı bir analizgerçekleştirmektedir. Çalışmada, 5000 kayıttan oluşan bir turizm veri setiüzerinde sınıflandırma, regresyon ve kümeleme yöntemleri uygulanmıştır. Turistmemnuniyetinin tahmini için Random Forest ve XGBoost modelleri kullanılarak,yaş, ziyaret edilen mekanlar, VR deneyim kalitesi ve seyahat süresi gibideğişkenler doğrultusunda tahminleme yapılmış ve modellerin başarı oranlarıkarşılaştırılmıştır. İlgi alanlarına göre profilleme sürecinde, turistlersanat, doğa, tarih ve macera gibi kategorilere ayrılmış, sınıflandırmamodelleri kullanılarak en iyi performans gösteren algoritma belirlenmiştir.Turist segmentasyonu için K-Means kümeleme algoritması uygulanmış, Elbowyöntemiyle optimum küme sayısı tespit edilmiş ve PCA ile görselleştirmegerçekleştirilmiştir. Sonuçlar, turistlerin üç temel gruba ayrıldığını ortayakoymaktadır: kısa turları tercih eden ve daha ileri yaş grubuna ait bireyler,orta düzeyde seyahat süresi planlayan ve dengeli bir deneyim arayanlar ile VRve dijital deneyimlere ilgi duyan teknoloji odaklı grup. Elde edilen bulgular,turizm sektöründe veri odaklı karar alma süreçlerini destekleyerek, müşterimemnuniyetini artırmaya yönelik kişiselleştirilmiş öneri sistemleriningeliştirilmesine olanak tanımaktadır. Bu doğrultuda, çalışmada kullanılanmakine öğrenmesi yaklaşımlarının, seyahat endüstrisinde müşteri odaklıhizmetlerin iyileştirilmesine önemli katkılar sunabileceğideğerlendirilmektedir. </p
Heat transfer in the entrance region of annular laminar flow with constant and different heat flux on two walls
No full textHeat transfer differs in the regions where the flow is developed and develop-ing thermally. These regions can be differentiated by using the thermal entrylength. Many researchers have presented correlations to determine the thermalentry length for natural and forced convection. In this study, heat transfer in theentrance region of a concentric annuli is investigated. It is accepted that begin-ning from the inlet of annuli the flow is developed hydrodynamically and it isdeveloping thermally. Heat transfer is investigated where the internal or externalsurfaces of the annuli are at constant but different heat fluxes. The fluid velocityis assumed to be constant or radially variable. Due to thermal boundary condi-tions, one thermal boundary layer appears on the outer cylinder surface, anotheron the inner cylinder surface. The edge of two boundary layers will be adia-batic and naturally, the temperature of fluid between the two edges will be equalto free stream temperature. Transformation, Separation of Variables method,eigenvalue problem, Sturm-Liouville system, Bessel differential equation andproperties of orthogonal functions are used in solution of the problem. Exactand analytical solutions of the momentum and energy equations are presented.Velocity and temperature distributions, local Nusselt numbers and convectionheat transfer coefficients are calculated for the internal and external surfaces of annuli.</p
Deep Learning-Driven MRI analysis for accurate diagnosis and grading of lumbar spinal stenosis
No full textIn recent years, deep neural networks (DNN) have emerged as an important solution due to the increasing complexity of healthcare data. Machine learning (ML) algorithms provide effective and powerful analytical methods that can uncover hidden patterns and important information from large healthcare data sets that cannot be detected in a reasonable time frame using traditional methods. Deep learning (DL) techniques have shown promise in areas such as pattern recognition and diagnosis in healthcare systems. This study aims to contribute to easier interpretation of medical data by applying different DL algorithms to MRI images of the lumbar spine collected between 2020and 2023 in a private clinic. In this context, Convolutional Neural Network (CNN) variations, EfficientNET models and methods such as k-fold cross-validation for more acceptable results, early stopping to save time and Genetic Algorithm (GA) to optimize hyperparameters are preferred. As a result of the study, success rates between 61% and 83.25% are achieved with CNN and between 86.25% and 91.56% with EfficientNET. Overall, this study aims to support medical professionals by mitigating some of the challenges in diagnosis and classification caused by image complexity when interpreting medical data