In order to transmit communication signals of different properties, quickly, effectively, and accurately, various different modulation styles can be adopted. Accurate recognition of signal modulation is required at the receive side. Automatic modulation recognition (AMR) is a key technique to identify various styles of modulation of signals received in wireless channels. It can be used in many kinds of communication systems, including single antenna system and multiple antenna system. In this paper, we propose a convolutional neural networks (CNN) aided AMR method for multiple antenna system. Compared with the high order cumulants (HOC) and artificial neural networks (ANN) aided traditional AMR classification method, both with two specific combination strategies, such as relative majority voting method and arithmetic mean method, the proposed AMR with arithmetic mean method has the best classification performance. The experimental results obtained verify that the CNN, one of the representative algorithms of deep learning, has a strong ability to exploit dominant features and classify the modulation styles.

Deep convolutional neural network (DeCNN) is considered one of promising techniques for classifying the high spatial resolution remote sensing (HSRRS) scenes, due to its powerful feature extraction capabilities. It is well-known that huge high quality labeled datasets are required for achieving the better classification performances and preventing over-fitting, during the training DeCNN model process. However, the lack of high quality datasets often limits the applications of DeCNN. In order to solve this problem, in this paper, we propose a HSRRS image scene classification method using transfer learning and DeCNN (TL-DeCNN) model in few shot HSRRS scene samples. Specifically, three typical DeCNNs of VGG19, ResNet50 and InceptionV3, trained on the ImageNet2015, the weights of their convolutional layer for that of the TL-DeCNN are transferred, respectively. Then, TL-DeCNN just needs to fine-tune its classification module on the few shot HSRRS scene samples in a few epochs. Experimental results indicate that our proposed TL-DeCNN method provides absolute dominance results without over-fitting, when compared with the VGG19, ResNet50 and InceptionV3, directly trained on the few shot samples.