Yılmaz, Vadi Su

Profile Picture
Name Variants
Y., Vadi Su
Yilmaz,V.S.
Vadi Su, Yılmaz
V. S. Yilmaz
Yılmaz,V.S.
Vadi Su, Yilmaz
V.S.Yilmaz
Yilmaz, Vadi Su
V.,Yilmaz
Y.,Vadi Su
Yilmaz V.
Yılmaz, Vadi Su
V., Yilmaz
V.,Yılmaz
V.S.Yılmaz
V. S. Yılmaz
Job Title
Araştırma Görevlisi
Email Address
vadi.yilmaz@atilim.edu.tr
ORCID ID
Scopus Author ID
57201855036
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Scholarly Output

7

Articles

4

Citation Count

10

Supervised Theses

1

Filters

2017 - 201942020 - 20233
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 7 of 7
  • Thumbnail Image
    Article
    Citation Count: 0
    Investigating the Impact of Two Major Programming Environments on the Accuracy of Deep Learning-Based Glioma Detection from MRI Images
    (Mdpi, 2023) Yılmaz, Vadi Su; Doruk, Reşat Özgür; Dalveren, Yaser; Dalveren, Yaser; Kara, Ali; Soylu, Ahmet; Electrical-Electronics Engineering; Department of Electrical & Electronics Engineering
    Brain tumors have been the subject of research for many years. Brain tumors are typically classified into two main groups: benign and malignant tumors. The most common tumor type among malignant brain tumors is known as glioma. In the diagnosis of glioma, different imaging technologies could be used. Among these techniques, MRI is the most preferred imaging technology due to its high-resolution image data. However, the detection of gliomas from a huge set of MRI data could be challenging for the practitioners. In order to solve this concern, many Deep Learning (DL) models based on Convolutional Neural Networks (CNNs) have been proposed to be used in detecting glioma. However, understanding which CNN architecture would work efficiently under various conditions including development environment or programming aspects as well as performance analysis has not been studied so far. In this research work, therefore, the purpose is to investigate the impact of two major programming environments (namely, MATLAB and Python) on the accuracy of CNN-based glioma detection from Magnetic Resonance Imaging (MRI) images. To this end, experiments on the Brain Tumor Segmentation (BraTS) dataset (2016 and 2017) consisting of multiparametric magnetic MRI images are performed by implementing two popular CNN architectures, the three-dimensional (3D) U-Net and the V-Net in the programming environments. From the results, it is concluded that the use of Python with Google Colaboratory (Colab) might be highly useful in the implementation of CNN-based models for glioma detection. Moreover, the 3D U-Net model is found to perform better, attaining a high accuracy on the dataset. The authors believe that the results achieved from this study would provide useful information to the research community in their appropriate implementation of DL approaches for brain tumor detection.
  • Thumbnail Image
    Master Thesis
    Endüstriyel uzaktan kontrol sistemleri için 900 MHz'de çalışan minyatür anten tasarımı ve üretimi
    (2019) Yılmaz, Vadi Su; Kara, Ali; Kara, Ali; Aydın, Elif; Electrical-Electronics Engineering; Department of Electrical & Electronics Engineering
    Bu tez, GHz altı bantlarda çalışan antenler için minyatürizasyon tekniklerine ışık tutarken, uzaktan kontrol sistemleri için anten tasarımları yaparak, minyatürizasyon tekniklerinin analizlerini gerçekleştirmeyi hedeflemiştir. Bu evrede birçok tasarım gerçekleştirilmiş ve incelemeler yapılmıştır. Kullanılan FEM tabanlı tasarım araçlarının sonuçlarını, anten teorisini kavramadan anlamak mümkün olmadığından, mikroşerit anten teorisi üzerinde durulmuştur. Anten yamasının tasarımı yapılmış, birçok model belirlenmiş, belirlenen modeller üzerinden, kullanılan tekniklerin geçerlilikleri saptanmıştır. İstenilen değerlere ulaşan antenlerin üretimi ve ölçümleri gerçekleştirilmiştir. Uzaktan kontrol uygulamalarında kullanılan kutu malzemesi üzerine de çalışmalar yapılmıştır. Kutu malzemesi, anten performansını etkilemeyecek şekilde, iyileştirilmeler yapılarak tanımlanmış ve üretimi gerçekleştirilmiştir. Anten kutu içerisine yerleştirilerek, ölçüm ve tasarım sonuçları karşılaştırılmıştır.
  • Thumbnail Image
    Conference Object
    Citation Count: 0
    Design considerations for near to the ground communication system and associated Sub-GHz low profile antenna
    (Institute of Electrical and Electronics Engineers Inc., 2017) Bilgin, Gülsima; Aydın, Elif; Kara, Ali; Kara,A.; Yılmaz, Vadi Su; Department of Electrical & Electronics Engineering; Electrical-Electronics Engineering
    This paper presents propagation aspects of a peer-to peer communication link where antennas are placed near to the ground (low height). First, some of the propagation models are evaluated for understanding of propagation mechanisms. In this regard, as the height of the antennas are very low and the distance is large enough, reflecting angle becomes very small that makes use of two ray model. On the other hand, in the horizontal plane, the positions of the scattering objects, as a source of lateral waves, might vary largely due to the terrain undulations along with variety of objects around the link. This makes propagation mechanisms a little bit complicated. In order to design low profile, high gain sub-GHz antenna for such propagation environment, microstrip antenna with vertical ground was designed and fabricated. The antenna is required to be protected from natural and man-made effects. Therefore, the antenna with associated sensors are embedded into a metal box with a dielectric cover. All these are discussed and some of the findings are presented. © 2017 IEEE.
  • Thumbnail Image
    Article
    Citation Count: 4
    Miniaturised antenna at a sub-GHZ band for industrial remote controllers
    (inst Engineering Technology-iet, 2019) Yılmaz, Vadi Su; Bilgin, Gulsima; Bilgin, Gülsima; Aydın, Elif; Kara, Ali; Electrical-Electronics Engineering; Department of Electrical & Electronics Engineering
    This study presents the design and the fabrication of a miniaturised sub-GHz antenna for remote control applications. Miniaturisation techniques were examined to identify the most appropriate topology for sub-GHz band requirements. First, the design parameters of the antenna were determined, and then, a commercial electromagnetic simulation tool was used for the design and optimisation phases. Then, measurements of the fabricated antenna were undertaken. Parametric studies with several iterations were performed to achieve the best possible results. Second, the effects of the box in which the antenna could be placed were examined as most of such antennas are enclosed by plastic boxes. For this purpose, material properties of a typical industrial box available in the market were studied initially, and the most appropriate material of the box was used in simulations. Finally, a polyamide box with appropriate size was fabricated, and the designed antenna was placed inside the box and the measurements were conducted. The measurement results show that the designed antenna provides resonance at the targeted license-free band with adequate size for industrial remote controllers.
  • Thumbnail Image
    Conference Object
    Citation Count: 0
    Miniaturized 2.4 GHz Antenna Design for UAV communication link;
    (Institute of Electrical and Electronics Engineers Inc., 2020) Kara, Ali; Aydın, Elif; Aydin,E.; Yılmaz, Vadi Su; Department of Electrical & Electronics Engineering; Electrical-Electronics Engineering
    In many communications applications, unlike conventional antennas, lightweight, flexible, small antennas that can adapt to mechanical and industrial constraints are required. In this study, the results of antenna design operating at 2.4 GHz are presented for use in Unmanned Aerial Vehicle (UAV) tele command links. In the parametric and optimization studies carried out on the antenna, it is aimed to increase the gain while keeping the size as small as possible. The requirements of the industry, such as light, aesthetics, miniature and high gain aspects of the antenna were targeted in the design process. Finally, an antenna of 55.2x88 mm size and 7dB gain was achieved using commercial electromagnetic design tools. The designed antenna become satisfying industrial requirements with these features. © 2020 IEEE.
  • Thumbnail Image
    Article
    Citation Count: 6
    Comparative assessment of electromagnetic simulation tools for use in microstrip antenna design: Experimental demonstrations
    (Wiley, 2019) Yılmaz, Vadi Su; Yilmaz, Vadi Su; Bilgin, Gülsima; Kara, Ali; Aydın, Elif; Electrical-Electronics Engineering; Department of Electrical & Electronics Engineering
    This paper presents a better understanding of the use of finite integration techniques (FIT) and finite element method (FEM) in different types of microstrip antennas in order to determine which numerical method gives relatively more accurate results. Although the theoretical formulation based on Maxwell's equations of both FEM and FIT are approached from different aspects in the literature, there is still a lack of comparison of the same antenna type using different numerical methods employing FEM and FIT. Therefore, in this study, FEM and FIT were applied to two different types of microstrip antennas, and their simulation and experimental results was compared. For the first antenna demonstration, a multilayer structure was chosen to achieve one of the significant parameters. Then, a microstrip antenna with a compact structure was used in the second demonstration. Using these two antennas, the accuracy of FEM and FIT in different structures were compared and all simulated return loss and gain results were verified by the measured results. The experimental demonstrations show that FEM performs better for both types of microstrip antennas while FIT provides an adequate result for two-layer microstrip antennas.
  • Thumbnail Image
    Article
    Citation Count: 0
    Classification of Different Recycled Rubber-Epoxy Composite Based on Their Hardness Using Laser-Induced Breakdown Spectroscopy (LIBS) with Comparison Machine Learning Algorithms
    (Mdpi, 2023) Yılmaz, Vadi Su; Eseller, Kemal Efe; Aslan, Özgür; Bayraktar, Emin; Eseller, Kemal Efe; Electrical-Electronics Engineering; Mechanical Engineering; Department of Electrical & Electronics Engineering
    This paper aims toward the successful detection of harmful materials in a substance by integrating machine learning (ML) into laser-induced breakdown spectroscopy (LIBS). LIBS is used to distinguish five different synthetic polymers where eight different heavy material contents are also detected by LIBS. Each material intensity-wavelength graph is obtained and the dataset is constructed for classification by a machine learning (ML) algorithm. Seven popular machine learning algorithms are applied to the dataset which include eight different substances with their wavelength-intensity value. Machine learning algorithms are used to train the dataset, results are discussed and which classification algorithm is appropriate for this dataset is determined.