Dendrogram-based Artificial Neural Network modulation classification for dual-hop cooperative relaying communications

This paper contributes to the growing field of Artificial Neural Networks (ANNs) strategies Automatic Modulation Identification (AMI) for Cognitive Radio (CR). Traditional AMI-based ANN methods suffer from many drawbacks such as overfitting due architectures with complex layers, low performance caused by falling into local minima, and increased training time that keeps them being used in real-time applications. We propose generated Dendrogram decompose AMI task sub-components using improved classification accuracy less time. In addition, one most significant challenges is identifying modulation types orders cooperative systems combination several received signals propagating through different unknown channels. dual-hop based on Amplify Forward protocol (DH-AF) relaying system generate dataset train test proposed model. DH-AF provide better coverage signal reliability existing wireless communication systems. consider source communicates destination over a direct link ( S − D ) indirect via an intermediate relay R Distributed Space-Time Block Code (DSTBC). Then we High Order Cumulants (HOC) Moments (HOM) originating DSTBC-decoded features, followed Dendrogram-based (DANN) classifier. The simulation results confirm method outperforms ordinary other counterparts while taking