Yazar "Yazan, Ersan" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Comparison of the Stochastic Gradient Descent Based Optimization Techniques
    (Ieee, 2017) Yazan, Ersan; Talu, M. Fatih
    The stochastic gradual descent method (SGD) is a popular optimization technique based on updating each theta(k) parameter in the partial derivative J(theta)/partial derivative theta(k) direction to minimize / maximize the (J theta) cost function. This technique is frequently used in current artificial learning methods such as convolutional learning and automatic encoders. In this study, five different approaches (Momentum, Adagrad, Adadelta, Rmsprop ve Adam) based on SDA used in updating the theta parameters were investigated. By selecting specific test functions, the advantages and disadvantages of each approach are compared with each other in terms of the number of oscillations, the parameter update rate and the minimum cost reached. The comparison results are shown graphically.
  • Küçük Resim Yok
    Öğe
    Integration of attention mechanisms into segmentation architectures and their application on breast lymph node images
    (Pamukkale Univ, 2023) Yazan, Ersan; Talu, Muhammed Fatih
    Innovations such as the widespread use of motorized microscopes, the automatic scanning of the tissue taken from the patient and transferring it to a single large image, and the production of deep/adversarial networks specific to segmentation have increased the hope of automatically producing outputs very close to expert labeling in the segmentation problem. Particularly, it is known that segmentation performances are improved by integrating attention modules into classical 3D-UNet or GAN architectures. In this study, the effects of four different attention modules (DAF, DAF3D, DANet and MSA) were analyzed in solving the histopathological image segmentation problem. While single (SLF) and multiple (MLF) layer features are used together in DAF and DAF3D modules, two different mechanisms, position attention module and channel attention module, are used in DANet and MSA modules. As a result of the experimental studies, it has been seen that the DAF3D attention module maximizes the segmentation accuracy (0.76 mIoU and 0.89 PA). At the same time, the method with the lowest segmentation cost (0.156 seconds for 1 image) among the approaches was again DAF3D.
  • Küçük Resim Yok
    Öğe
    KÜRESEL CİSİMLERİN POZİSYON KESTİRİMİNDE KUATERNİYON YAKLAŞIMLARININ DEĞERLENDİRİLMESİ - SIZINTI TESPİT TOPU UYGULAMASI
    (2022) Yazan, Ersan; Talu, Muhammed Fatih
    Su kaynaklarının azalması sebebiyle alınan önlemlerden biri su iletim hattında oluşan sızıntı konumlarının doğru tespitidir. Bu nedenle sızıntı tespiti ile ilgili çalışmalar önem arz etmektedir. Bu çalışmada, su borularındaki sızıntı olan bölgelerin tespitinde kullanılmak üzere küre şeklinde bir top üretilmiş ve bu topun gezinti esnasında anlık konum bilgisinin en doğru hesaplanabileceği yöntemler araştırılmıştır. Xsens firmasının IMU sensörünü içeren topun belirli hareket güzergâhlarında gezintisi sağlanmış ve anlık ivme, açısal hız ve kuaterniyon verileri toplanmıştır. Kuaterniyon değerinin pozisyon üzerindeki etkisini analiz edebilmek için iki farklı Kuaterniyon hesaplama yaklaşımının (Madgwiwck ve Mahony) sonuçları değerlendirilmiştir. Deneysel çalışmalar, pozisyon tahmin doğruluğunun tatmin edici düzeyde olduğunu ve yapılan çalışmanın sızıntı tespit sistemlerinde kullanılabileceğini göstermektedir.
  • Küçük Resim Yok
    Öğe
    Vortex Optimization Algorithm Based Fabric Defect Detection
    (Ieee, 2018) Yazan, Ersan; Celik, Gaffari; Talu, Muhammed Fatih; Yeroglu, Celaleddin
    In textile industry, defects that occur in fabrics during production processes cause the producers to suffer large losses of money. Various studies have been carried out to minimize these losses. There are two types of defect detection methods, that are human-focused and machine-focused defect defect detection. In human-focused systems, defect detection is performed after the production phase. This does not provide an advantage for the manufacturer. Defect detection with machine-focused systems have better results. In this study widely used machine-oriented fabric defect detection approaches have been analyzed and a method is proposed based on using Fourier transform with bandpass filter. The Vortex Optimization Algorithm (GOA) is used to obtain the most suitable parameters of the bandpass filter better.