Automatic modulation classification (AMC) is the premise for signal detection and demodulation applications, especially in non-cooperative communication scenarios. It has been a popular topic for decades and has gained significant progress with the development of deep learning methods. To further improve classification accuracy, a hierarchical multifeature fusion (HMF) based on a multidimensional convolutional neural network (CNN)-long short-term memory (LSTM) network is proposed in this paper. First, a multidimensional CNN module (MD-CNN) is proposed for feature compensation between interactive features extracted by two-dimensional convolutional filters and respective features extracted by one-dimensional filters. Second, learnt features of the MD-CNN module are fed into an LSTM layer for further exploitation of temporal features. Finally, classification results are obtained by the Softmax classifier. The effectiveness of the proposed method is verified by abundant experimental results on two public datasets, RadioML.2016.10a and RadioML.2016.10b. Satisfying results are obtained as compared with state-of-the-art methods.

Source camera identification has long been a hot topic in the field of image forensics. Besides conventional feature engineering algorithms developed based on studying the traces left upon shooting, several deep-learning-based methods have also emerged recently. However, identification performance is susceptible to image content and is far from satisfactory for small image patches in real demanding applications. In this paper, an efficient patch-level source camera identification method is proposed based on a convolutional neural network. First, in order to obtain improved robustness with reduced training cost, representative patches are selected according to multiple criteria for enhanced diversity in training data. Second, a fine-grained multiscale deep residual prediction module is proposed to reduce the impact of scene content. Finally, a modified VGG network is proposed for source camera identification at brand, model, and instance levels. A more critical patch-level evaluation protocol is also proposed for fair performance comparison. Abundant experimental results show that the proposed method achieves better results as compared with the state-of-the-art algorithms.

Automatic modulation classification plays a significant role in numerous military and civilian applications. Deep learning methods have attracted increasing attention and achieved remarkable success in recent years. However, few methods can generalize well across changes in varying channel conditions and signal parameters. In this paper, based on an analysis of the challenging domain shift problem, we proposed a method that can simultaneously achieve good classification accuracy on well-annotated source data and unlabeled signals with varying symbol rates and sampling frequencies. Firstly, a convolutional neural network is utilized for feature extraction. Then, a multiple kernel maximum mean discrepancy layer is utilized to bridge the labeled source domain and unlabeled target domain. In addition, a real-world signal dataset consisting of eight digital modulation schemes is constructed to verify the effectiveness of the proposed method. Experimental results demonstrate that it outperforms state-of-the-art methods, achieving higher accuracy on both source and target datasets.