Yazar "Durdu A." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Classification of EEG signals using spiking neural networks [Darbeli sinir a?lari ile EEG sinyallerinin siniflandirilmasi]
    (Institute of Electrical and Electronics Engineers Inc., 2018) Tahtirvanci A.; Durdu A.; Yilmaz B.
    In signal processing applications of conventional artificial neural networks, the processing time of the data is high and the accuracy rates are not good enough. At the same time, time-dependent processing is not possible. In this study, classification of EEG signals was performed using an artificial neural network including the characteristics of spiking neural networks. Successful results were obtained using large data sets. Moreover, by using the neuron model of Eugene M. Izhikevich as the spiking neural network model, the EEG signals were processed biologically realistically. © 2018 IEEE.
  • Küçük Resim Yok
    Öğe
    Path planning of mobile robots with Q-learning [Q-ögrenme algoritmas ile mobil robotlarn yol planlamasi]
    (IEEE Computer Society, 2014) Cetin H.; Durdu A.
    Robotic systems which rapidly continue its development are increasingly used in our daily life. Mobile robots both draw the map where they may move in their environment and reach to the determined target in the shortest time by going on the shortest way in their prepared map. In this paper, Q-learning-based path planning algorithm is presented to find a target in the maps which are obtained by mobile robots. Q-learning is a kind of reinforcement learning algorithm that detects its environment and shows a system which makes decisions itself that how it can learn to make true decisions about reaching its target. The fact that a mobile robot truly finds targets that are located on different points in a few sample maps by processing our proposed Q-learning-based path planning algorithm is shown at the end of the paper. © 2014 IEEE.
  • Küçük Resim Yok
    Öğe
    Sliding mode control of a two-link robot manipulator using adams matlab software
    (Institute of Electrical and Electronics Engineers Inc., 2018) Ilgen S.; Durdu A.; Gulbahce E.; Cakan A.
    This paper presents the design of a sliding mode controller (SMC) for trajectory tracking problem for a two-link planar robot manipulator. A virtual prototype of the manipulator has been built by using Adams software. Also, the controller works is achieved in Matlab/Simulink software. The system is simulated in both Matlab and Adams software together which is called co-simulation. The manipulator system has two inputs (torques of actuators) and four outputs (angle of 1st joint, angle of 2nd joint and x-y components of end effector position). The sliding mode controller (SMC) is designed with the constant variation reaching law. The simulation results show that the sliding mode controller (SMC) can successfully achieve trajectory tracking of a two-link planar robot manipulator according to the desired trajectory. © 2018 IEEE.