Yazar "Calisan, Mucahit" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Examination of the effect of the basic parameters of the auto-encoder on coding performance
    (Ieee, 2017) Calisan, Mucahit; Talu, M. Fatih
    In this study, artificial learning approach which can express high dimensional data in a lower space (autocoding) and known as autoencoder in the literature has been investigated in detail without using a predefined ready mathematical model. The most important feature of this method, which can be used in place of traditional feature extraction methods (HOG, SHIFT, SURF, Wavelet, etc.), is the ability to extract data-specific features. By applying the real (MNIST) and synthetic data, the effects on the success of the parameters of the method are measured and the results are presented in a tabular form.
  • Küçük Resim Yok
    Öğe
    Skull Thickness Calculation Using Thermal Analysis and Finite Elements
    (Mdpi, 2021) Calisan, Mucahit; Talu, Muhammed Fatih; Pimenov, Danil Yurievich; Giasin, Khaled
    In this study, the skull bone thicknesses of 150 patients ranging in age from 0 to 72 years were calculated using a novel approach (thermal analysis), and thickness changes were analyzed. Unlike conventional thickness calculation approaches (Beam Propagation, Hildebrand), a novel heat transfer-based approach was developed. Firstly, solid 3D objects with different thicknesses were modeled, and thermal analyses were performed on these models. To better understand the heat transfer of 3D object models, finite element models (FEM) of the human head have been reported in the literature. The FEM can more accurately model the complex geometry of a 3D human head model. Then, thermal analysis was performed on human skulls using the same methods. Thus, the skull bone thicknesses at different ages and in different genders from region to region were determined. The skull model was transferred to ANSYS, and it was meshed using different mapping parameters. The heat transfer results were determined by applying different heat values to the inner and outer surfaces of the skull mesh structure. Thus, the average thicknesses of skull regions belonging to a certain age group were obtained. With this developed method, it was observed that the temperature value applied to the skull was proportional to the thickness value. The average thickness of skull bones for men (frontal: 7.8 mm; parietal: 9.6 mm; occipital: 10.1 mm; temporal: 6 mm) and women (frontal: 8.6 mm; parietal: 10.1 mm; occipital: 10 mm; temporal: 6 mm) are given. The difference (10%) between men and women appears to be statistically significant only for frontal bone thickness. Thanks to the developed method, bone thickness information at any desired point on the skull can be obtained numerically. Therefore, the proposed method can be used to help pre-operative planning of surgical procedures.