Automatic Modulation Recognition Based on Hybrid Neural Network

Abstract

Recognizing signals is critical for understanding the increasingly crowded wireless spectrum space in noncooperative communications. Traditional threshold or pattern recognition-based solutions are labor-intensive and error-prone. Therefore, practitioners start to apply deep learning to automatic modulation classification (AMC). However, the recognition accuracy and robustness of recently presented neural network-based proposals are still unsatisfactory, especially when the signal-to-noise ratio (SNR) is low. In this backdrop, this paper presents a hybrid neural network model, called MCBL, which combines convolutional neural network, bidirectional long-short time memory, and attention mechanism to exploit their respective capability to extract the spatial, temporal, and salient features embedded in the signal samples. After formulating the AMC problem, the three modules of our hybrid dynamic neural network are detailed. To evaluate the performance of our proposal, 10 state-of-the-art neural networks (including two latest models) are chosen as benchmarks for the comparison experiments conducted on an open radio frequency (RF) dataset. Results have shown that the recognition accuracy of MCBL can reach 93% which is the highest among the tested DNN models. At the same time, the computation efficiency and robustness of MCBL are better than existing proposals.

Improving Modulation Recognition Using Time Series Data Augmentation via a Spatiotemporal Multi-Channel Framework

“…In the literature [17,18], constellation map rotation, flip, and random erasing algorithms have been cited as data augmentation techniques combined with LSTM, which eventually achieved a recognition accuracy of about 92%, separately. In [19], a hybrid neural network model MCBL was proposed, which combined a CNN, bidirectional long short-term memory network (BLSTM), and attention mechanism, utilizing their respective capabilities to extract the significant features of space and time embedded in the signal samples; the recognition accuracy reached 93%. To overcome the limitations of a small number of training samples, manual feature extraction, and low recognition accuracy, we proposed a recognition method that combined time series data augmentation and a spatiotemporal multi-channel framework.…”