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