Yazar "Kosten, Mehmet Muzaffer" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Deep Neural Network Training with iPSO Algorithm
    (IEEE, 2018) Kosten, Mehmet Muzaffer; Barut, Murat; Acir, Nurettin
    Deep learning-based methods are frequently preferred in many areas in recent years. Another issue, which is as important as deep neural networks applications, is the training of deep neural networks. Although many techniques are proposed in the literature for the training of deep nets, most of these techniques use gradient descent based approaches. In this study, differently from the conventional gradient method, Improved Particle Swam Optimisation (IPSO) algorithm is used for the training of deep neural networks. LeNet-5 network is preferred as network structure and MNIST is utilized as data set. Depending on the number of particles, a performance of up to 96.29% was achieved. In the cases after 20 particles, the average performance was over 90%.
  • Küçük Resim Yok
    Öğe
    FPGA-Based Implementation of Basic Image Processing Applications as Low-Cost IP Core
    (IEEE, 2018) Altuncu, Mehmet Ali; Kosten, Mehmet Muzaffer; Cavuslu, Mehmet Ali; Sahin, Suhap
    With technology, rapidly developing image sensors have begun to be used in many areas, from smart phones to unmanned vehicles. In particular, systems that have to process many images at the same time, such as unmanned vehicles, require a high amount of processing power and use expensive equipment. In this work, we describe FPGA based implementation of basic image processing applications that can work on low cost FPGA families for use in applications with high processing power. With the IP core, users can easily perform mirroring, inversion, negation, thresholding, brightness and contrast enhancement / reduction on the image. The IP core platform is designed to be independently. Synthesis results are given with reference to Xilinx's Spartan 7 FPGA. The results show that the developed IP core has a low hardware cost.
  • Küçük Resim Yok
    Öğe
    Rotor Speed and Load Torque Estimations of Induction Motors via LSTM Network
    (Sciendo, 2023) Kosten, Mehmet Muzaffer; Emlek, Alper; Yildiz, Recep; Barut, Murat
    In this study, a long short-term memory (LSTM) based estimator using rotating axis components of the stator voltages and currents as inputs is designed to perform estimations of rotor mechanical speed and load torque values of the induction motor (IM) for electrical vehicle (EV) applications. For this aim, first of all, an indirect vector controlled IM drive is implemented in simulation to collect both training and test datasets. After the initial training, a fine-tuning process is applied to increase the robustness of the proposed LSTM network. Furthermore, the LSTM parameters, layer size, and hidden size are also optimised to increase the estimation performance. The proposed LSTM network is tested under two different challenging scenarios including the operation of the IM with linear and step-like load torque changes in a single direction and in both directions. To force the proposed LSTM network, it is also tested under the variation of stator and rotor resistances for the both-direction scenario. The obtained results confirm the highly satisfactory estimation performance of the proposed LSTM network and its applicability for the EV applications of the IMs.