Automatic Modulation Classification for Underwater Acoustic Communication Signals Based on Deep Complex Networks

Abstract

Automatic modulation classification (AMC) is an important method for monitoring and identifying any underwater communication interference. Since the underwater acoustic communication scenario is full of multi-path fading and ocean ambient noise (OAN), coupled with the application of modern communication technology, which is usually susceptible to environmental influences, automatic modulation classification (AMC) becomes particularly difficult when it comes to an underwater scenario. Motivated by the deep complex networks (DCN), which have an innate ability to process complex data, we explore DCN for AMC of underwater acoustic communication signals. To integrate the signal processing method with deep learning and overcome the influences of underwater acoustic channels, we propose two complex physical signal processing layers based on DCN. The proposed layers include a deep complex matched filter (DCMF) and deep complex channel equalizer (DCCE), which are designed to remove noise and reduce the influence of multi-path fading for the received signals, respectively. Hierarchical DCN is constructed using the proposed method to achieve better performance of AMC. The influence of the real-world underwater acoustic communication scenario is taken into account; two underwater acoustic multi-path fading channels are conducted using the real-world ocean observation dataset, white Gaussian noise, and real-world OAN are used as the additive noise, respectively. Contrastive experiments show that the AMC based on DCN can achieve better performance than the traditional deep neural network based on real value (the average accuracy of the DCN is 5.3% higher than real-valued DNN). The proposed method based on DCN can effectively reduce the influence of underwater acoustic channels and improve the AMC performance in different underwater acoustic channels. The performance of the proposed method was verified on the real-world dataset. In the underwater acoustic channels, the proposed method outperforms a series of advanced AMC method.

Feature Fusion Based on Graph Convolution Network for Modulation Classification in Underwater Communication

“…To demonstrate the effectiveness of the proposed AMC method based on GCN, we compared the performance of the proposed method with those state-of-the-art AMC methods. The achieved methods include deep learning methods (basic CNN [44], InceptionV3 [45], GAN [29], VGGnet [30], ResNet [46,47], LSTM [48,49], deep complex network (DCN) [1]), and feature extraction methods (HOC [3,4] using an SVM classifier, CS [50] with a neural network classifier, and continuous wavelet transform (CWT) [11,51] with an SVM classifier). We carried out the comparison experiments in Ch1 and Ch2, respectively.…”

“…Thus, we could not only accelerate computational speed but also integrate the feature extraction process and forward propagation of the GCN into one computational framework. We compared our proposed method with DCN in our previous work [1]. Figure 16 shows the computational cost comparison of different methods-GCN1 denotes the process of the first step without GPU acceleration and GCN2 denotes the process of the first step with GPU acceleration.…”

“…AMC has been an important method with which to identify the modulation types of the received signals in underwater communication scenarios; this is useful for the monitoring and identification of communication interference, which are core technologies in spectrum surveillance and underwater acoustic countermeasures. The advanced AMC technology has a broad application prospect in the underwater unmanned platform [1]. However, the complexity of underwater communication means the underwater acoustic channel is full of multi-path fading and ocean ambient noise, which can decrease the AMC performance of underwater acoustic communication signals significantly.…”

“…DNNs can learn high-level features from raw data automatically without much prior knowledge, or can also accept the features from a feature extraction algorithm and work as a classifier. Yao [1] proposed an AMC method based on deep complex networks. They built two complex physical signal processing layers to improve the performance of AMC in underwater acoustic communication.…”

MGFGNet: an automatic underwater acoustic target recognition method based on the multi-gradient flow global feature enhancement network

“…Traditional methods of underwater acoustic target feature extraction can be categorized into signal physics-based and brainlike computing methods (Zhu et al, 2023). Signal physics-based methods rely on basic characteristics, temporal features, and non-Gaussian characteristics of underwater acoustic signals (Yao X. et al, 2023). This includes time-domain features like zero-crossing distribution, frequency-domain features like cepstral analysis (Zhu et al, 2022), and joint time-frequency domain features such as wavelet transforms (Han et al, 2022;Tian et al, 2023).…”