Automatic Modulation Recognition based on Artificial Neural Networks Over Wireless Fading Channel in Cognitive Radio
Increasing the number of wireless communication led to increase for using the radio spectrum. With this
increasing, needed to improve and reliable the radio spectrum which it’s a finite resource. Cognitive Radio (CR) is the key
enabling for dynamic spectrum access to achieve efficient spectrum utilization. Through spectrum sensing, CR can obtain
necessary observation about its surrounding radio environment, such as the presence of primary users and appearance of
spectrum holes. In this paper, apply digital and analog classification based on automatic modulations recognition through the
Artificial Neural Network (ANN). Implement and design 8 modulations which are: 2ASK, 2FSK, 2PSK, 64QAM, AM, FM,
DSB, and SSB. The Maximum value of spectral power density of the normalized-centred amplitude, standard deviation of
the absolute value of the centred non-linear component of the instantaneous phase, standard deviation of the absolute value
of the normalized-centred instantaneous amplitude and standard deviation of the absolute value of the centred nonlinear
component of the instantaneous frequency are chosen as key features for automatic modulations recognizer based on ANN.
The contribution done by adding multipath fading channel to the modulations and distributed by AWGN. The overall
numerical results obtain from the simulation show that the ANN could be classified all modulations in its current state of
Keywords- CR, Digital and Analog Modulation, ANN, Multipath Fading Channel and AWGN.