Yazar "Ozturk, Celal" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    A New Modulation Recognition Method Based on Artificial Bee Colony Algorithm
    (IEEE, 2013) Özen, Ali; Ozturk, Celal
    A new digital modulation recognition method has been proposed for classifying baseband signals that are subjected to additive white Gaussian noise (AWGN) channel in this paper. The proposed method (ABC-ANN) is based on artificial neural network (ANN) which is trained by artificial bee colony (ABC) algorithm. The high order cumulants have been employed in the proposed ABC-ANN classifier. ABC algorithm has been used in finding the optimal weight set which directly affects the performance of artificial neural networks. Computer simulation results have demonstrated that the proposed recognizer can reach much better classification accuracy than the existing methods in even -5 dB of signal to noise ratio (SNR) value.
  • [ X ]
    Öğe
    A Novel Modulation Recognition Technique Based on Artificial Bee Colony Algorithm in the Presence of Multipath Fading Channels
    (IEEE, 2013) Özen, Ali; Ozturk, Celal
    In this paper, a novel automatic modulation recognition (AMR) method has been proposed for classifying of the transmitted signals by observing the received data samples in the presence of additive white Gaussian noise (AWGN) and multipath fading channel. The proposed method (ABC-ANN) is based on artificial neural network (ANN) which is trained by artificial bee colony (ABC) algorithm. Because high order statistics are very interesting features to solve the problem of AMR, the high order cumulants have been employed in the proposed ABC-ANN classifier. ABC algorithm is used in finding the optimal weight set of artificial neural networks for classification and the performance of the proposed ABC-ANN algorithm is compared with the performance of ANN classifier (SCG-ANN) using scaled conjugate gradient learning algorithm. Computer simulation results have demonstrated that the proposed recognizer can reach much better classification accuracy than the SCG-ANN in even 0 dB of signal to noise ratio (SNR) value.