Person:
YILMAZ, GÜNEŞ

Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

OrgUnit Logo
Organizational Unit

Job Title

Last Name

YILMAZ

First Name

GÜNEŞ

Name

Filters

20202
Reset filters

Settings

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Investigation of the atmospheric attenuation factors in FSO communication systems using the taguchi method
    (Hindawi, 2020-03-12) Demir, Pelin; Yılmaz, Güneş; DEMİR, PELİN; YILMAZ, GÜNEŞ; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Elektrik-Elektronik Mühendisliği Bölümü.; 0000-0001-9768-4194; 0000-0001-8972-1952; ABG-5204-2021; JCE-7740-2023
    In this study, Mie and Rayleigh scattering in free space optics (FSO) communication systems were investigated in terms of the atmospheric attenuation. Because of the movement of the Earth, the communication distance and surrounding gas densities are inconsistent in each region. This change leads to atmospheric attenuation and then data losses and inefficient communication in FSO occur. Therefore, the density change and distance must be calculated in each communication once the data is transmitted. In the literature, it was observed that the atmospheric attenuation is regarding some FSO communication parameters such as transmission distance, visibility, and scatter particle size distribution, the number of particles per unit volume, scatter cross-sectional area, and wavelength. Besides, in real-time communication, it is necessary to update FSO parameters simultaneously. However, this updating process for all parameter takes a long time to adapt to a new position. This paper proposes the design of the experiment method (Doe) to determine the severity of the FSO parameters. And Taguchi's Doe method allows analyzing of FSO communication system parameters to avoid long calculation time. Results show that the proposed method helps in understanding the priorities of the parameters in FSO and reducing the updating time.
  • No Thumbnail Available
    Publication
    Feature selection and analysis EEG signals with sequential forward selection algorithm and different classifiers
    (Ieee, 2020-01-01) Bekiryazıcı, Şule; Demir, Ahmet; Yılmaz, Güneş; BEKİRYAZICI, ŞULE; DEMİR, AHMET; YILMAZ, GÜNEŞ; Bursa Uludağ Universitesi/Mühendislik Fakültesi/Elektrik Elektronik Mühendisliği Bölumü.; 0000-0003-1115-186X; 0000-0001-8972-1952; AAH-4182-2021; AAH-4177-2021; KPP-7123-2024
    In this study, we investigated the features that could best represent EEG signals for brain computer interface systems and classifier accuracy was compared using different classification methods. EEG signals data set were taken from "BCI II Competition". In this study, inadequate features that reduce classification accuracy were determined by using sequential forward selection algorithms and were extracted from real-dimensional feature matrix. The remaining active feature matrix and real-dimensional feature matrix were classified using k-nearest neighbor, subspace K-nearest neighbor, support vector machines, subspace discriminant and random forest decision tree algorithms. As a result of this study, the highest classification accuracy of real-dimensional feature matrix was obtained as 83.8% by random forest decision tree algorithm. In the other, the highest classification accuracy of dimention reductioned feature matrix with sequential forward selection algorthm was obtained as 96.4% by random forest decision tree algorithm.